Header logo is


2020


Label Efficient Visual Abstractions for Autonomous Driving
Label Efficient Visual Abstractions for Autonomous Driving

Behl, A., Chitta, K., Prakash, A., Ohn-Bar, E., Geiger, A.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, October 2020 (conference)

Abstract
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, ie, the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (eg, object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.

pdf slides video Project Page [BibTex]

2020

pdf slides video Project Page [BibTex]


Convolutional Occupancy Networks
Convolutional Occupancy Networks

Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.

In European Conference on Computer Vision (ECCV), Springer International Publishing, Cham, August 2020 (inproceedings)

Abstract
Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not scale to more complicated or large-scale scenes. The key limiting factor of implicit methods is their simple fully-connected network architecture which does not allow for integrating local information in the observations or incorporating inductive biases such as translational equivariance. In this paper, we propose Convolutional Occupancy Networks, a more flexible implicit representation for detailed reconstruction of objects and 3D scenes. By combining convolutional encoders with implicit occupancy decoders, our model incorporates inductive biases, enabling structured reasoning in 3D space. We investigate the effectiveness of the proposed representation by reconstructing complex geometry from noisy point clouds and low-resolution voxel representations. We empirically find that our method enables the fine-grained implicit 3D reconstruction of single objects, scales to large indoor scenes, and generalizes well from synthetic to real data.

pdf suppmat video Project Page [BibTex]

pdf suppmat video Project Page [BibTex]


Category Level Object Pose Estimation via Neural Analysis-by-Synthesis
Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

Chen, X., Dong, Z., Song, J., Geiger, A., Hilliges, O.

In European Conference on Computer Vision (ECCV), Springer International Publishing, Cham, August 2020 (inproceedings)

Abstract
Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances. In this paper we combine a gradient-based fitting procedure with a parametric neural image synthesis module that is capable of implicitly representing the appearance, shape and pose of entire object categories, thus rendering the need for explicit CAD models per object instance unnecessary. The image synthesis network is designed to efficiently span the pose configuration space so that model capacity can be used to capture the shape and local appearance (i.e., texture) variations jointly. At inference time the synthesized images are compared to the target via an appearance based loss and the error signal is backpropagated through the network to the input parameters. Keeping the network parameters fixed, this allows for iterative optimization of the object pose, shape and appearance in a joint manner and we experimentally show that the method can recover orientation of objects with high accuracy from 2D images alone. When provided with depth measurements, to overcome scale ambiguities, the method can accurately recover the full 6DOF pose successfully.

Project Page pdf suppmat [BibTex]

Project Page pdf suppmat [BibTex]


Self-supervised motion deblurring
Self-supervised motion deblurring

Liu, P., Janai, J., Pollefeys, M., Sattler, T., Geiger, A.

IEEE Robotics and Automation Letters, 2020 (article)

Abstract
Motion blurry images challenge many computer vision algorithms, e.g., feature detection, motion estimation, or object recognition. Deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this paper, we present a differentiable reblur model for self-supervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on sharp images for supervision. Our key insight is that motion cues obtained from consecutive images yield sufficient information to inform the deblurring task. We therefore formulate deblurring as an inverse rendering problem, taking into account the physical image formation process: we first predict two deblurred images from which we estimate the corresponding optical flow. Using these predictions, we re-render the blurred images and minimize the difference with respect to the original blurry inputs. We use both synthetic and real dataset for experimental evaluations. Our experiments demonstrate that self-supervised single image deblurring is really feasible and leads to visually compelling results.

pdf Project Page Blog [BibTex]

pdf Project Page Blog [BibTex]


Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image

Paschalidou, D., Gool, L., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2020 (inproceedings)

Abstract
Humans perceive the 3D world as a set of distinct objects that are characterized by various low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) properties. Recent methods based on convolutional neural networks (CNNs) demonstrated impressive progress in 3D reconstruction, even when using a single 2D image as input. However, the majority of these methods focuses on recovering the local 3D geometry of an object without considering its part-based decomposition or relations between parts. We address this challenging problem by proposing a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives as well as their latent hierarchical structure without part-level supervision. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives, where simple parts are represented with fewer primitives and more complex parts are modeled with more components. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.

pdf suppmat Video 2 Project Page Slides Poster Video 1 [BibTex]

pdf suppmat Video 2 Project Page Slides Poster Video 1 [BibTex]


GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.

In Advances in Neural Information Processing Systems (NeurIPS), 2020 (inproceedings)

Abstract
While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, eg, the object identity may vary with the viewpoint. In this paper, we propose a generative model for radiance fields which have recently proven successful for novel view synthesis of a single scene. In contrast to voxel-based representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity. By introducing a multi-scale patch-based discriminator, we demonstrate synthesis of high-resolution images while training our model from unposed 2D images alone. We systematically analyze our approach on several challenging synthetic and real-world datasets. Our experiments reveal that radiance fields are a powerful representation for generative image synthesis, leading to 3D consistent models that render with high fidelity.

[BibTex]

[BibTex]


Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

Liao, Y., Schwarz, K., Mescheder, L., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2020 (inproceedings)

Abstract
In recent years, Generative Adversarial Networks have achieved impressive results in photorealistic image synthesis. This progress nurtures hopes that one day the classical rendering pipeline can be replaced by efficient models that are learned directly from images. However, current image synthesis models operate in the 2D domain where disentangling 3D properties such as camera viewpoint or object pose is challenging. Furthermore, they lack an interpretable and controllable representation. Our key hypothesis is that the image generation process should be modeled in 3D space as the physical world surrounding us is intrinsically three-dimensional. We define the new task of 3D controllable image synthesis and propose an approach for solving it by reasoning both in 3D space and in the 2D image domain. We demonstrate that our model is able to disentangle latent 3D factors of simple multi-object scenes in an unsupervised fashion from raw images. Compared to pure 2D baselines, it allows for synthesizing scenes that are consistent wrt. changes in viewpoint or object pose. We further evaluate various 3D representations in terms of their usefulness for this challenging task.

pdf suppmat Video 2 Project Page Video 1 Slides Poster [BibTex]

pdf suppmat Video 2 Project Page Video 1 Slides Poster [BibTex]


Learning Neural Light Transport
Learning Neural Light Transport

Sanzenbacher, P., Mescheder, L., Geiger, A.

Arxiv, 2020 (article)

Abstract
In recent years, deep generative models have gained significance due to their ability to synthesize natural-looking images with applications ranging from virtual reality to data augmentation for training computer vision models. While existing models are able to faithfully learn the image distribution of the training set, they often lack controllability as they operate in 2D pixel space and do not model the physical image formation process. In this work, we investigate the importance of 3D reasoning for photorealistic rendering. We present an approach for learning light transport in static and dynamic 3D scenes using a neural network with the goal of predicting photorealistic images. In contrast to existing approaches that operate in the 2D image domain, our approach reasons in both 3D and 2D space, thus enabling global illumination effects and manipulation of 3D scene geometry. Experimentally, we find that our model is able to produce photorealistic renderings of static and dynamic scenes. Moreover, it compares favorably to baselines which combine path tracing and image denoising at the same computational budget.

arxiv [BibTex]


Exploring Data Aggregation in Policy Learning for Vision-based Urban Autonomous Driving
Exploring Data Aggregation in Policy Learning for Vision-based Urban Autonomous Driving

Prakash, A., Behl, A., Ohn-Bar, E., Chitta, K., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2020 (inproceedings)

Abstract
Data aggregation techniques can significantly improve vision-based policy learning within a training environment, e.g., learning to drive in a specific simulation condition. However, as on-policy data is sequentially sampled and added in an iterative manner, the policy can specialize and overfit to the training conditions. For real-world applications, it is useful for the learned policy to generalize to novel scenarios that differ from the training conditions. To improve policy learning while maintaining robustness when training end-to-end driving policies, we perform an extensive analysis of data aggregation techniques in the CARLA environment. We demonstrate how the majority of them have poor generalization performance, and develop a novel approach with empirically better generalization performance compared to existing techniques. Our two key ideas are (1) to sample critical states from the collected on-policy data based on the utility they provide to the learned policy in terms of driving behavior, and (2) to incorporate a replay buffer which progressively focuses on the high uncertainty regions of the policy's state distribution. We evaluate the proposed approach on the CARLA NoCrash benchmark, focusing on the most challenging driving scenarios with dense pedestrian and vehicle traffic. Our approach improves driving success rate by 16% over state-of-the-art, achieving 87% of the expert performance while also reducing the collision rate by an order of magnitude without the use of any additional modality, auxiliary tasks, architectural modifications or reward from the environment.

pdf suppmat Video 2 Project Page Slides Video 1 [BibTex]

pdf suppmat Video 2 Project Page Slides Video 1 [BibTex]


HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking

Luiten, J., Osep, A., Dendorfer, P., Torr, P., Geiger, A., Leal-Taixe, L., Leibe, B.

International Journal of Computer Vision (IJCV), 2020 (article)

Abstract
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, HOTA (Higher Order Tracking Accuracy), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. HOTA decomposes into a family of sub-metrics which are able to evaluate each of five basic error types separately, which enables clear analysis of tracking performance. We evaluate the effectiveness of HOTA on the MOTChallenge benchmark, and show that it is able to capture important aspects of MOT performance not previously taken into account by established metrics. Furthermore, we show HOTA scores better align with human visual evaluation of tracking performance.

pdf [BibTex]

pdf [BibTex]


Learning Situational Driving
Learning Situational Driving

Ohn-Bar, E., Prakash, A., Behl, A., Chitta, K., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2020 (inproceedings)

Abstract
Human drivers have a remarkable ability to drive in diverse visual conditions and situations, e.g., from maneuvering in rainy, limited visibility conditions with no lane markings to turning in a busy intersection while yielding to pedestrians. In contrast, we find that state-of-the-art sensorimotor driving models struggle when encountering diverse settings with varying relationships between observation and action. To generalize when making decisions across diverse conditions, humans leverage multiple types of situation-specific reasoning and learning strategies. Motivated by this observation, we develop a framework for learning a situational driving policy that effectively captures reasoning under varying types of scenarios. Our key idea is to learn a mixture model with a set of policies that can capture multiple driving modes. We first optimize the mixture model through behavior cloning, and show it to result in significant gains in terms of driving performance in diverse conditions. We then refine the model by directly optimizing for the driving task itself, i.e., supervised with the navigation task reward. Our method is more scalable than methods assuming access to privileged information, e.g., perception labels, as it only assumes demonstration and reward-based supervision. We achieve over 98% success rate on the CARLA driving benchmark as well as state-of-the-art performance on a newly introduced generalization benchmark.

pdf suppmat Video 2 Project Page Video 1 Slides [BibTex]

pdf suppmat Video 2 Project Page Video 1 Slides [BibTex]


On Joint Estimation of Pose, Geometry and svBRDF from a Handheld Scanner
On Joint Estimation of Pose, Geometry and svBRDF from a Handheld Scanner

Schmitt, C., Donne, S., Riegler, G., Koltun, V., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2020 (inproceedings)

Abstract
We propose a novel formulation for joint recovery of camera pose, object geometry and spatially-varying BRDF. The input to our approach is a sequence of RGB-D images captured by a mobile, hand-held scanner that actively illuminates the scene with point light sources. Compared to previous works that jointly estimate geometry and materials from a hand-held scanner, we formulate this problem using a single objective function that can be minimized using off-the-shelf gradient-based solvers. By integrating material clustering as a differentiable operation into the optimization process, we avoid pre-processing heuristics and demonstrate that our model is able to determine the correct number of specular materials independently. We provide a study on the importance of each component in our formulation and on the requirements of the initial geometry. We show that optimizing over the poses is crucial for accurately recovering fine details and that our approach naturally results in a semantically meaningful material segmentation.

pdf Project Page Slides Video Poster [BibTex]

pdf Project Page Slides Video Poster [BibTex]


Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition

Hassan Alhaija, Siva Mustikovela, Varun Jampani, Justus Thies, Matthias Niessner, Andreas Geiger, Carsten Rother

In International Conference on 3D Vision (3DV), 2020 (inproceedings)

Abstract
Neural rendering techniques promise efficient photo-realistic image synthesis while providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been pro-posed for this task, acquiring a dataset of images with accurately aligned 3D models is very difficult. The main contribution of this work is to lift this restriction by training a neural rendering algorithm from unpaired data. We pro-pose an auto encoder for joint generation of realistic images from synthetic 3D models while simultaneously decomposing real images into their intrinsic shape and appearance properties. In contrast to a traditional graphics pipeline, our approach does not require to specify all scene properties, such as material parameters and lighting by hand.Instead, we learn photo-realistic deferred rendering from a small set of 3D models and a larger set of unaligned real images, both of which are easy to acquire in practice. Simultaneously, we obtain accurate intrinsic decompositions of real images while not requiring paired ground truth. Our experiments confirm that a joint treatment of rendering and de-composition is indeed beneficial and that our approach out-performs state-of-the-art image-to-image translation base-lines both qualitatively and quantitatively.

pdf [BibTex]

pdf [BibTex]


Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision
Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision

Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2020 (inproceedings)

Abstract
Learning-based 3D reconstruction methods have shown impressive results. However, most methods require 3D supervision which is often hard to obtain for real-world datasets. Recently, several works have proposed differentiable rendering techniques to train reconstruction models from RGB images. Unfortunately, these approaches are currently restricted to voxel- and mesh-based representations, suffering from discretization or low resolution. In this work, we propose a differentiable rendering formulation for implicit shape and texture representations. Implicit representations have recently gained popularity as they represent shape and texture continuously. Our key insight is that depth gradients can be derived analytically using the concept of implicit differentiation. This allows us to learn implicit shape and texture representations directly from RGB images. We experimentally show that our single-view reconstructions rival those learned with full 3D supervision. Moreover, we find that our method can be used for multi-view 3D reconstruction, directly resulting in watertight meshes.

pdf suppmat Video 2 Project Page Video 1 Video 3 Slides Poster [BibTex]

pdf suppmat Video 2 Project Page Video 1 Video 3 Slides Poster [BibTex]


Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art

Janai, J., Güney, F., Behl, A., Geiger, A.

Arxiv, Foundations and Trends in Computer Graphics and Vision, 2020 (book)

Abstract
Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it becomes increasingly difficult to stay up-to-date or enter the field as a beginner. While several survey papers on particular sub-problems have appeared, no comprehensive survey on problems, datasets, and methods in computer vision for autonomous vehicles has been published. This monograph attempts to narrow this gap by providing a survey on the state-of-the-art datasets and techniques. Our survey includes both the historically most relevant literature as well as the current state of the art on several specific topics, including recognition, reconstruction, motion estimation, tracking, scene understanding, and end-to-end learning for autonomous driving. Towards this goal, we analyze the performance of the state of the art on several challenging benchmarking datasets, including KITTI, MOT, and Cityscapes. Besides, we discuss open problems and current research challenges. To ease accessibility and accommodate missing references, we also provide a website that allows navigating topics as well as methods and provides additional information.

pdf Project Page link Project Page [BibTex]


Learning Implicit Surface Light Fields
Learning Implicit Surface Light Fields

Oechsle, M., Niemeyer, M., Reiser, C., Mescheder, L., Strauss, T., Geiger, A.

In International Conference on 3D Vision (3DV), 2020 (inproceedings)

Abstract
Implicit representations of 3D objects have recently achieved impressive results on learning-based 3D reconstruction tasks. While existing works use simple texture models to represent object appearance, photo-realistic image synthesis requires reasoning about the complex interplay of light, geometry and surface properties. In this work, we propose a novel implicit representation for capturing the visual appearance of an object in terms of its surface light field. In contrast to existing representations, our implicit model represents surface light fields in a continuous fashion and independent of the geometry. Moreover, we condition the surface light field with respect to the location and color of a small light source. Compared to traditional surface light field models, this allows us to manipulate the light source and relight the object using environment maps. We further demonstrate the capabilities of our model to predict the visual appearance of an unseen object from a single real RGB image and corresponding 3D shape information. As evidenced by our experiments, our model is able to infer rich visual appearance including shadows and specular reflections. Finally, we show that the proposed representation can be embedded into a variational auto-encoder for generating novel appearances that conform to the specified illumination conditions.

[BibTex]

[BibTex]

2019


Attacking Optical Flow
Attacking Optical Flow

Ranjan, A., Janai, J., Geiger, A., Black, M. J.

In Proceedings International Conference on Computer Vision (ICCV), pages: 2404-2413, IEEE, 2019 IEEE/CVF International Conference on Computer Vision (ICCV), November 2019, ISSN: 2380-7504 (inproceedings)

Abstract
Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those techniques. Recently, it has been shown that adversarial attacks easily fool deep neural networks to misclassify objects. The robustness of optical flow networks to adversarial attacks, however, has not been studied so far. In this paper, we extend adversarial patch attacks to optical flow networks and show that such attacks can compromise their performance. We show that corrupting a small patch of less than 1% of the image size can significantly affect optical flow estimates. Our attacks lead to noisy flow estimates that extend significantly beyond the region of the attack, in many cases even completely erasing the motion of objects in the scene. While networks using an encoder-decoder architecture are very sensitive to these attacks, we found that networks using a spatial pyramid architecture are less affected. We analyse the success and failure of attacking both architectures by visualizing their feature maps and comparing them to classical optical flow techniques which are robust to these attacks. We also demonstrate that such attacks are practical by placing a printed pattern into real scenes.

Video Project Page Paper Supplementary Material link (url) DOI [BibTex]

2019

Video Project Page Paper Supplementary Material link (url) DOI [BibTex]


Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics
Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics

Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.

International Conference on Computer Vision, October 2019 (conference)

Abstract
Deep learning based 3D reconstruction techniques have recently achieved impressive results. However, while state-of-the-art methods are able to output complex 3D geometry, it is not clear how to extend these results to time-varying topologies. Approaches treating each time step individually lack continuity and exhibit slow inference, while traditional 4D reconstruction methods often utilize a template model or discretize the 4D space at fixed resolution. In this work, we present Occupancy Flow, a novel spatio-temporal representation of time-varying 3D geometry with implicit correspondences. Towards this goal, we learn a temporally and spatially continuous vector field which assigns a motion vector to every point in space and time. In order to perform dense 4D reconstruction from images or sparse point clouds, we combine our method with a continuous 3D representation. Implicitly, our model yields correspondences over time, thus enabling fast inference while providing a sound physical description of the temporal dynamics. We show that our method can be used for interpolation and reconstruction tasks, and demonstrate the accuracy of the learned correspondences. We believe that Occupancy Flow is a promising new 4D representation which will be useful for a variety of spatio-temporal reconstruction tasks.

pdf poster suppmat code Project page video blog [BibTex]


Texture Fields: Learning Texture Representations in Function Space
Texture Fields: Learning Texture Representations in Function Space

Oechsle, M., Mescheder, L., Niemeyer, M., Strauss, T., Geiger, A.

International Conference on Computer Vision, October 2019 (conference)

Abstract
In recent years, substantial progress has been achieved in learning-based reconstruction of 3D objects. At the same time, generative models were proposed that can generate highly realistic images. However, despite this success in these closely related tasks, texture reconstruction of 3D objects has received little attention from the research community and state-of-the-art methods are either limited to comparably low resolution or constrained experimental setups. A major reason for these limitations is that common representations of texture are inefficient or hard to interface for modern deep learning techniques. In this paper, we propose Texture Fields, a novel texture representation which is based on regressing a continuous 3D function parameterized with a neural network. Our approach circumvents limiting factors like shape discretization and parameterization, as the proposed texture representation is independent of the shape representation of the 3D object. We show that Texture Fields are able to represent high frequency texture and naturally blend with modern deep learning techniques. Experimentally, we find that Texture Fields compare favorably to state-of-the-art methods for conditional texture reconstruction of 3D objects and enable learning of probabilistic generative models for texturing unseen 3D models. We believe that Texture Fields will become an important building block for the next generation of generative 3D models.

pdf suppmat video poster blog Project Page [BibTex]


NoVA: Learning to See in Novel Viewpoints and Domains
NoVA: Learning to See in Novel Viewpoints and Domains

Coors, B., Condurache, A. P., Geiger, A.

In 2019 International Conference on 3D Vision (3DV), pages: 116-125, IEEE, 2019 International Conference on 3D Vision (3DV), September 2019 (inproceedings)

Abstract
Domain adaptation techniques enable the re-use and transfer of existing labeled datasets from a source to a target domain in which little or no labeled data exists. Recently, image-level domain adaptation approaches have demonstrated impressive results in adapting from synthetic to real-world environments by translating source images to the style of a target domain. However, the domain gap between source and target may not only be caused by a different style but also by a change in viewpoint. This case necessitates a semantically consistent translation of source images and labels to the style and viewpoint of the target domain. In this work, we propose the Novel Viewpoint Adaptation (NoVA) model, which enables unsupervised adaptation to a novel viewpoint in a target domain for which no labeled data is available. NoVA utilizes an explicit representation of the 3D scene geometry to translate source view images and labels to the target view. Experiments on adaptation to synthetic and real-world datasets show the benefit of NoVA compared to state-of-the-art domain adaptation approaches on the task of semantic segmentation.

pdf suppmat poster video DOI [BibTex]

pdf suppmat poster video DOI [BibTex]


Taking a Deeper Look at the Inverse Compositional Algorithm
Taking a Deeper Look at the Inverse Compositional Algorithm

Lv, Z., Dellaert, F., Rehg, J. M., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.

pdf suppmat Video Project Page Poster [BibTex]

pdf suppmat Video Project Page Poster [BibTex]


MOTS: Multi-Object Tracking and Segmentation
MOTS: Multi-Object Tracking and Segmentation

Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B. B. G., Geiger, A., Leibe, B.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure. Our new annotations comprise 65,213 pixel masks for 977 distinct objects (cars and pedestrians) in 10,870 video frames. For evaluation, we extend existing multi-object tracking metrics to this new task. Moreover, we propose a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network. We demonstrate the value of our datasets by achieving improvements in performance when training on MOTS annotations. We believe that our datasets, metrics and baseline will become a valuable resource towards developing multi-object tracking approaches that go beyond 2D bounding boxes.

pdf suppmat Project Page Poster Video Project Page [BibTex]

pdf suppmat Project Page Poster Video Project Page [BibTex]


PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds
PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds

Behl, A., Paschalidou, D., Donne, S., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneously, these applications are often not restricted to image-based estimation: laser scanners provide a popular alternative to traditional cameras, for example in the context of self-driving cars, as they directly yield a 3D point cloud. In this paper, we propose to estimate 3D motion from such unstructured point clouds using a deep neural network. In a single forward pass, our model jointly predicts 3D scene flow as well as the 3D bounding box and rigid body motion of objects in the scene. While the prospect of estimating 3D scene flow from unstructured point clouds is promising, it is also a challenging task. We show that the traditional global representation of rigid body motion prohibits inference by CNNs, and propose a translation equivariant representation to circumvent this problem. For training our deep network, a large dataset is required. Because of this, we augment real scans from KITTI with virtual objects, realistically modeling occlusions and simulating sensor noise. A thorough comparison with classic and learning-based techniques highlights the robustness of the proposed approach.

pdf suppmat Project Page Poster Video [BibTex]

pdf suppmat Project Page Poster Video [BibTex]


Learning Non-volumetric Depth Fusion using Successive Reprojections
Learning Non-volumetric Depth Fusion using Successive Reprojections

Donne, S., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Given a set of input views, multi-view stereopsis techniques estimate depth maps to represent the 3D reconstruction of the scene; these are fused into a single, consistent, reconstruction -- most often a point cloud. In this work we propose to learn an auto-regressive depth refinement directly from data. While deep learning has improved the accuracy and speed of depth estimation significantly, learned MVS techniques remain limited to the planesweeping paradigm. We refine a set of input depth maps by successively reprojecting information from neighbouring views to leverage multi-view constraints. Compared to learning-based volumetric fusion techniques, an image-based representation allows significantly more detailed reconstructions; compared to traditional point-based techniques, our method learns noise suppression and surface completion in a data-driven fashion. Due to the limited availability of high-quality reconstruction datasets with ground truth, we introduce two novel synthetic datasets to (pre-)train our network. Our approach is able to improve both the output depth maps and the reconstructed point cloud, for both learned and traditional depth estimation front-ends, on both synthetic and real data.

pdf suppmat Project Page Video Poster blog [BibTex]

pdf suppmat Project Page Video Poster blog [BibTex]


Connecting the Dots: Learning Representations for Active Monocular Depth Estimation
Connecting the Dots: Learning Representations for Active Monocular Depth Estimation

Riegler, G., Liao, Y., Donne, S., Koltun, V., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
We propose a technique for depth estimation with a monocular structured-light camera, \ie, a calibrated stereo set-up with one camera and one laser projector. Instead of formulating the depth estimation via a correspondence search problem, we show that a simple convolutional architecture is sufficient for high-quality disparity estimates in this setting. As accurate ground-truth is hard to obtain, we train our model in a self-supervised fashion with a combination of photometric and geometric losses. Further, we demonstrate that the projected pattern of the structured light sensor can be reliably separated from the ambient information. This can then be used to improve depth boundaries in a weakly supervised fashion by modeling the joint statistics of image and depth edges. The model trained in this fashion compares favorably to the state-of-the-art on challenging synthetic and real-world datasets. In addition, we contribute a novel simulator, which allows to benchmark active depth prediction algorithms in controlled conditions.

pdf suppmat Poster Project Page [BibTex]

pdf suppmat Poster Project Page [BibTex]


Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids
Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids

Paschalidou, D., Ulusoy, A. O., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting superquadrics as atomic elements. We demonstrate that superquadrics lead to more expressive 3D scene parses while being easier to learn than 3D cuboid representations. Moreover, we provide an analytical solution to the Chamfer loss which avoids the need for computational expensive reinforcement learning or iterative prediction. Our model learns to parse 3D objects into consistent superquadric representations without supervision. Results on various ShapeNet categories as well as the SURREAL human body dataset demonstrate the flexibility of our model in capturing fine details and complex poses that could not have been modelled using cuboids.

Project Page Poster suppmat pdf Video blog handout [BibTex]

Project Page Poster suppmat pdf Video blog handout [BibTex]


Real-Time Dense Mapping for Self-Driving Vehicles using Fisheye Cameras
Real-Time Dense Mapping for Self-Driving Vehicles using Fisheye Cameras

Cui, Z., Heng, L., Yeo, Y. C., Geiger, A., Pollefeys, M., Sattler, T.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings)

Abstract
We present a real-time dense geometric mapping algorithm for large-scale environments. Unlike existing methods which use pinhole cameras, our implementation is based on fisheye cameras which have larger field of view and benefit some other tasks including Visual-Inertial Odometry, localization and object detection around vehicles. Our algorithm runs on in-vehicle PCs at 15 Hz approximately, enabling vision-only 3D scene perception for self-driving vehicles. For each synchronized set of images captured by multiple cameras, we first compute a depth map for a reference camera using plane-sweeping stereo. To maintain both accuracy and efficiency, while accounting for the fact that fisheye images have a rather low resolution, we recover the depths using multiple image resolutions. We adopt the fast object detection framework YOLOv3 to remove potentially dynamic objects. At the end of the pipeline, we fuse the fisheye depth images into the truncated signed distance function (TSDF) volume to obtain a 3D map. We evaluate our method on large-scale urban datasets, and results show that our method works well even in complex environments.

pdf video poster Project Page [BibTex]

pdf video poster Project Page [BibTex]


Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System
Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System

Heng, L., Choi, B., Cui, Z., Geppert, M., Hu, S., Kuan, B., Liu, P., Nguyen, R. M. H., Yeo, Y. C., Geiger, A., Lee, G. H., Pollefeys, M., Sattler, T.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings)

Abstract
Project AutoVision aims to develop localization and 3D scene perception capabilities for a self-driving vehicle. Such capabilities will enable autonomous navigation in urban and rural environments, in day and night, and with cameras as the only exteroceptive sensors. The sensor suite employs many cameras for both 360-degree coverage and accurate multi-view stereo; the use of low-cost cameras keeps the cost of this sensor suite to a minimum. In addition, the project seeks to extend the operating envelope to include GNSS-less conditions which are typical for environments with tall buildings, foliage, and tunnels. Emphasis is placed on leveraging multi-view geometry and deep learning to enable the vehicle to localize and perceive in 3D space. This paper presents an overview of the project, and describes the sensor suite and current progress in the areas of calibration, localization, and perception.

pdf [BibTex]

pdf [BibTex]


no image
Geometric Image Synthesis

Abu Alhaija, H., Mustikovela, S. K., Geiger, A., Rother, C.

Computer Vision – ACCV 2018, 11366, pages: 85-100, Lecture Notes in Computer Science, (Editors: Jawahar, C. and Li, H. and Mori, G. and Schindler, K. ), Asian Conference on Computer Vision, 2019 (conference)

DOI Project Page [BibTex]

DOI Project Page [BibTex]


Occupancy Networks: Learning 3D Reconstruction in Function Space
Occupancy Networks: Learning 3D Reconstruction in Function Space

Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, 2019 (inproceedings)

Abstract
With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learning-based 3D reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose Occupancy Networks, a new representation for learning-based 3D reconstruction methods. Occupancy networks implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier. In contrast to existing approaches, our representation encodes a description of the 3D output at infinite resolution without excessive memory footprint. We validate that our representation can efficiently encode 3D structure and can be inferred from various kinds of input. Our experiments demonstrate competitive results, both qualitatively and quantitatively, for the challenging tasks of 3D reconstruction from single images, noisy point clouds and coarse discrete voxel grids. We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.

Code Video pdf suppmat Project Page blog [BibTex]

Code Video pdf suppmat Project Page blog [BibTex]

2018


On the Integration of Optical Flow and Action Recognition
On the Integration of Optical Flow and Action Recognition

Sevilla-Lara, L., Liao, Y., Güney, F., Jampani, V., Geiger, A., Black, M. J.

In German Conference on Pattern Recognition (GCPR), LNCS 11269, pages: 281-297, Springer, Cham, October 2018 (inproceedings)

Abstract
Most of the top performing action recognition methods use optical flow as a "black box" input. Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow method good for action recognition, and how we can make it better. In particular, we investigate the impact of different flow algorithms and input transformations to better understand how these affect a state-of-the-art action recognition method. Furthermore, we fine tune two neural-network flow methods end-to-end on the most widely used action recognition dataset (UCF101). Based on these experiments, we make the following five observations: 1) optical flow is useful for action recognition because it is invariant to appearance, 2) optical flow methods are optimized to minimize end-point-error (EPE), but the EPE of current methods is not well correlated with action recognition performance, 3) for the flow methods tested, accuracy at boundaries and at small displacements is most correlated with action recognition performance, 4) training optical flow to minimize classification error instead of minimizing EPE improves recognition performance, and 5) optical flow learned for the task of action recognition differs from traditional optical flow especially inside the human body and at the boundary of the body. These observations may encourage optical flow researchers to look beyond EPE as a goal and guide action recognition researchers to seek better motion cues, leading to a tighter integration of the optical flow and action recognition communities.

arXiv DOI [BibTex]

2018

arXiv DOI [BibTex]


Towards Robust Visual Odometry with a Multi-Camera System
Towards Robust Visual Odometry with a Multi-Camera System

Liu, P., Geppert, M., Heng, L., Sattler, T., Geiger, A., Pollefeys, M.

In International Conference on Intelligent Robots and Systems (IROS) 2018, International Conference on Intelligent Robots and Systems, October 2018 (inproceedings)

Abstract
We present a visual odometry (VO) algorithm for a multi-camera system and robust operation in challenging environments. Our algorithm consists of a pose tracker and a local mapper. The tracker estimates the current pose by minimizing photometric errors between the most recent keyframe and the current frame. The mapper initializes the depths of all sampled feature points using plane-sweeping stereo. To reduce pose drift, a sliding window optimizer is used to refine poses and structure jointly. Our formulation is flexible enough to support an arbitrary number of stereo cameras. We evaluate our algorithm thoroughly on five datasets. The datasets were captured in different conditions: daytime, night-time with near-infrared (NIR) illumination and night-time without NIR illumination. Experimental results show that a multi-camera setup makes the VO more robust to challenging environments, especially night-time conditions, in which a single stereo configuration fails easily due to the lack of features.

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Learning Priors for Semantic 3D Reconstruction
Learning Priors for Semantic 3D Reconstruction

Cherabier, I., Schönberger, J., Oswald, M., Pollefeys, M., Geiger, A.

In Computer Vision – ECCV 2018, Springer International Publishing, Cham, September 2018 (inproceedings)

Abstract
We present a novel semantic 3D reconstruction framework which embeds variational regularization into a neural network. Our network performs a fixed number of unrolled multi-scale optimization iterations with shared interaction weights. In contrast to existing variational methods for semantic 3D reconstruction, our model is end-to-end trainable and captures more complex dependencies between the semantic labels and the 3D geometry. Compared to previous learning-based approaches to 3D reconstruction, we integrate powerful long-range dependencies using variational coarse-to-fine optimization. As a result, our network architecture requires only a moderate number of parameters while keeping a high level of expressiveness which enables learning from very little data. Experiments on real and synthetic datasets demonstrate that our network achieves higher accuracy compared to a purely variational approach while at the same time requiring two orders of magnitude less iterations to converge. Moreover, our approach handles ten times more semantic class labels using the same computational resources.

pdf suppmat Project Page Video DOI Project Page [BibTex]

pdf suppmat Project Page Video DOI Project Page [BibTex]


Unsupervised Learning of Multi-Frame Optical Flow with Occlusions
Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

Janai, J., Güney, F., Ranjan, A., Black, M. J., Geiger, A.

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11220, pages: 713-731, Springer, Cham, September 2018 (inproceedings)

pdf suppmat Video Project Page DOI Project Page [BibTex]

pdf suppmat Video Project Page DOI Project Page [BibTex]


SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images
SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images

Coors, B., Condurache, A. P., Geiger, A.

European Conference on Computer Vision (ECCV), September 2018 (conference)

Abstract
Omnidirectional cameras offer great benefits over classical cameras wherever a wide field of view is essential, such as in virtual reality applications or in autonomous robots. Unfortunately, standard convolutional neural networks are not well suited for this scenario as the natural projection surface is a sphere which cannot be unwrapped to a plane without introducing significant distortions, particularly in the polar regions. In this work, we present SphereNet, a novel deep learning framework which encodes invariance against such distortions explicitly into convolutional neural networks. Towards this goal, SphereNet adapts the sampling locations of the convolutional filters, effectively reversing distortions, and wraps the filters around the sphere. By building on regular convolutions, SphereNet enables the transfer of existing perspective convolutional neural network models to the omnidirectional case. We demonstrate the effectiveness of our method on the tasks of image classification and object detection, exploiting two newly created semi-synthetic and real-world omnidirectional datasets.

pdf suppmat Project Page [BibTex]


Robust Dense Mapping for Large-Scale Dynamic Environments
Robust Dense Mapping for Large-Scale Dynamic Environments

Barsan, I. A., Liu, P., Pollefeys, M., Geiger, A.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2018, IEEE, International Conference on Robotics and Automation, May 2018 (inproceedings)

Abstract
We present a stereo-based dense mapping algorithm for large-scale dynamic urban environments. In contrast to other existing methods, we simultaneously reconstruct the static background, the moving objects, and the potentially moving but currently stationary objects separately, which is desirable for high-level mobile robotic tasks such as path planning in crowded environments. We use both instance-aware semantic segmentation and sparse scene flow to classify objects as either background, moving, or potentially moving, thereby ensuring that the system is able to model objects with the potential to transition from static to dynamic, such as parked cars. Given camera poses estimated from visual odometry, both the background and the (potentially) moving objects are reconstructed separately by fusing the depth maps computed from the stereo input. In addition to visual odometry, sparse scene flow is also used to estimate the 3D motions of the detected moving objects, in order to reconstruct them accurately. A map pruning technique is further developed to improve reconstruction accuracy and reduce memory consumption, leading to increased scalability. We evaluate our system thoroughly on the well-known KITTI dataset. Our system is capable of running on a PC at approximately 2.5Hz, with the primary bottleneck being the instance-aware semantic segmentation, which is a limitation we hope to address in future work.

pdf Video Project Page Project Page [BibTex]

pdf Video Project Page Project Page [BibTex]


Learning 3D Shape Completion under Weak Supervision
Learning 3D Shape Completion under Weak Supervision

Stutz, D., Geiger, A.

Arxiv, May 2018 (article)

Abstract
We address the problem of 3D shape completion from sparse and noisy point clouds, a fundamental problem in computer vision and robotics. Recent approaches are either data-driven or learning-based: Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations; Learning-based approaches, in contrast, avoid the expensive optimization step by learning to directly predict complete shapes from incomplete observations in a fully-supervised setting. However, full supervision is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, i.e., learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. On synthetic benchmarks based on ShapeNet and ModelNet as well as on real robotics data from KITTI and Kinect, we demonstrate that the proposed amortized maximum likelihood approach is able to compete with fully supervised baselines and outperforms data-driven approaches, while requiring less supervision and being significantly faster.

PDF Project Page Project Page [BibTex]


RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials

Paschalidou, D., Ulusoy, A. O., Schmitt, C., Gool, L., Geiger, A.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.

pdf suppmat Video Project Page code Poster Project Page [BibTex]

pdf suppmat Video Project Page code Poster Project Page [BibTex]


Deep Marching Cubes: Learning Explicit Surface Representations
Deep Marching Cubes: Learning Explicit Surface Representations

Liao, Y., Donne, S., Geiger, A.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
Existing learning based solutions to 3D surface prediction cannot be trained end-to-end as they operate on intermediate representations (eg, TSDF) from which 3D surface meshes must be extracted in a post-processing step (eg, via the marching cubes algorithm). In this paper, we investigate the problem of end-to-end 3D surface prediction. We first demonstrate that the marching cubes algorithm is not differentiable and propose an alternative differentiable formulation which we insert as a final layer into a 3D convolutional neural network. We further propose a set of loss functions which allow for training our model with sparse point supervision. Our experiments demonstrate that the model allows for predicting sub-voxel accurate 3D shapes of arbitrary topology. Additionally, it learns to complete shapes and to separate an object's inside from its outside even in the presence of sparse and incomplete ground truth. We investigate the benefits of our approach on the task of inferring shapes from 3D point clouds. Our model is flexible and can be combined with a variety of shape encoder and shape inference techniques.

pdf suppmat Video Project Page Poster Project Page [BibTex]

pdf suppmat Video Project Page Poster Project Page [BibTex]


Semantic Visual Localization
Semantic Visual Localization

Schönberger, J., Pollefeys, M., Geiger, A., Sattler, T.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, eg, in the context of life-long localization for augmented reality or autonomous robots. In this paper, we propose a novel approach based on a joint 3D geometric and semantic understanding of the world, enabling it to succeed under conditions where previous approaches failed. Our method leverages a novel generative model for descriptor learning, trained on semantic scene completion as an auxiliary task. The resulting 3D descriptors are robust to missing observations by encoding high-level 3D geometric and semantic information. Experiments on several challenging large-scale localization datasets demonstrate reliable localization under extreme viewpoint, illumination, and geometry changes.

pdf suppmat Poster Project Page [BibTex]

pdf suppmat Poster Project Page [BibTex]


Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes
Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes

Alhaija, H., Mustikovela, S., Mescheder, L., Geiger, A., Rother, C.

International Journal of Computer Vision (IJCV), 2018, 2018 (article)

Abstract
The success of deep learning in computer vision is based on the availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Unfortunately, creating realistic 3D content is challenging on its own and requires significant human effort. In this work, we propose an alternative paradigm which combines real and synthetic data for learning semantic instance segmentation and object detection models. Exploiting the fact that not all aspects of the scene are equally important for this task, we propose to augment real-world imagery with virtual objects of the target category. Capturing real-world images at large scale is easy and cheap, and directly provides real background appearances without the need for creating complex 3D models of the environment. We present an efficient procedure to augment these images with virtual objects. In contrast to modeling complete 3D environments, our data augmentation approach requires only a few user interactions in combination with 3D models of the target object category. Leveraging our approach, we introduce a novel dataset of augmented urban driving scenes with 360 degree images that are used as environment maps to create realistic lighting and reflections on rendered objects. We analyze the significance of realistic object placement by comparing manual placement by humans to automatic methods based on semantic scene analysis. This allows us to create composite images which exhibit both realistic background appearance as well as a large number of complex object arrangements. Through an extensive set of experiments, we conclude the right set of parameters to produce augmented data which can maximally enhance the performance of instance segmentation models. Further, we demonstrate the utility of the proposed approach on training standard deep models for semantic instance segmentation and object detection of cars in outdoor driving scenarios. We test the models trained on our augmented data on the KITTI 2015 dataset, which we have annotated with pixel-accurate ground truth, and on the Cityscapes dataset. Our experiments demonstrate that the models trained on augmented imagery generalize better than those trained on fully synthetic data or models trained on limited amounts of annotated real data.

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Which Training Methods for GANs do actually Converge?
Which Training Methods for GANs do actually Converge?

Mescheder, L., Geiger, A., Nowozin, S.

International Conference on Machine learning (ICML), 2018 (conference)

Abstract
Recent work has shown local convergence of GAN training for absolutely continuous data and generator distributions. In this paper, we show that the requirement of absolute continuity is necessary: we describe a simple yet prototypical counterexample showing that in the more realistic case of distributions that are not absolutely continuous, unregularized GAN training is not always convergent. Furthermore, we discuss regularization strategies that were recently proposed to stabilize GAN training. Our analysis shows that GAN training with instance noise or zero-centered gradient penalties converges. On the other hand, we show that Wasserstein-GANs and WGAN-GP with a finite number of discriminator updates per generator update do not always converge to the equilibrium point. We discuss these results, leading us to a new explanation for the stability problems of GAN training. Based on our analysis, we extend our convergence results to more general GANs and prove local convergence for simplified gradient penalties even if the generator and data distributions lie on lower dimensional manifolds. We find these penalties to work well in practice and use them to learn high-resolution generative image models for a variety of datasets with little hyperparameter tuning.

code video paper supplement slides poster Project Page [BibTex]


Learning 3D Shape Completion from Laser Scan Data with Weak Supervision
Learning 3D Shape Completion from Laser Scan Data with Weak Supervision

Stutz, D., Geiger, A.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
3D shape completion from partial point clouds is a fundamental problem in computer vision and computer graphics. Recent approaches can be characterized as either data-driven or learning-based. Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations. Learning-based approaches, in contrast, avoid the expensive optimization step and instead directly predict the complete shape from the incomplete observations using deep neural networks. However, full supervision is required which is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, ie, learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. Tackling 3D shape completion of cars on ShapeNet and KITTI, we demonstrate that the proposed amortized maximum likelihood approach is able to compete with a fully supervised baseline and a state-of-the-art data-driven approach while being significantly faster. On ModelNet, we additionally show that the approach is able to generalize to other object categories as well.

pdf suppmat Project Page Poster Project Page [BibTex]

pdf suppmat Project Page Poster Project Page [BibTex]


Learning 3D Shape Completion under Weak Supervision
Learning 3D Shape Completion under Weak Supervision

Stutz, D., Geiger, A.

International Journal of Computer Vision (IJCV), 2018, 2018 (article)

Abstract
We address the problem of 3D shape completion from sparse and noisy point clouds, a fundamental problem in computer vision and robotics. Recent approaches are either data-driven or learning-based: Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations; Learning-based approaches, in contrast, avoid the expensive optimization step by learning to directly predict complete shapes from incomplete observations in a fully-supervised setting. However, full supervision is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, i.e., learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. On synthetic benchmarks based on ShapeNet and ModelNet as well as on real robotics data from KITTI and Kinect, we demonstrate that the proposed amortized maximum likelihood approach is able to compete with a fully supervised baseline and outperforms the data-driven approach of Engelmann et al., while requiring less supervision and being significantly faster.

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Learning Transformation Invariant Representations with Weak Supervision
Learning Transformation Invariant Representations with Weak Supervision

Coors, B., Condurache, A., Mertins, A., Geiger, A.

In International Conference on Computer Vision Theory and Applications, International Conference on Computer Vision Theory and Applications, 2018 (inproceedings)

Abstract
Deep convolutional neural networks are the current state-of-the-art solution to many computer vision tasks. However, their ability to handle large global and local image transformations is limited. Consequently, extensive data augmentation is often utilized to incorporate prior knowledge about desired invariances to geometric transformations such as rotations or scale changes. In this work, we combine data augmentation with an unsupervised loss which enforces similarity between the predictions of augmented copies of an input sample. Our loss acts as an effective regularizer which facilitates the learning of transformation invariant representations. We investigate the effectiveness of the proposed similarity loss on rotated MNIST and the German Traffic Sign Recognition Benchmark (GTSRB) in the context of different classification models including ladder networks. Our experiments demonstrate improvements with respect to the standard data augmentation approach for supervised and semi-supervised learning tasks, in particular in the presence of little annotated data. In addition, we analyze the performance of the proposed approach with respect to its hyperparameters, including the strength of the regularization as well as the layer where representation similarity is enforced.

pdf [BibTex]

pdf [BibTex]


Object Scene Flow
Object Scene Flow

Menze, M., Heipke, C., Geiger, A.

ISPRS Journal of Photogrammetry and Remote Sensing, 2018 (article)

Abstract
This work investigates the estimation of dense three-dimensional motion fields, commonly referred to as scene flow. While great progress has been made in recent years, large displacements and adverse imaging conditions as observed in natural outdoor environments are still very challenging for current approaches to reconstruction and motion estimation. In this paper, we propose a unified random field model which reasons jointly about 3D scene flow as well as the location, shape and motion of vehicles in the observed scene. We formulate the problem as the task of decomposing the scene into a small number of rigidly moving objects sharing the same motion parameters. Thus, our formulation effectively introduces long-range spatial dependencies which commonly employed local rigidity priors are lacking. Our inference algorithm then estimates the association of image segments and object hypotheses together with their three-dimensional shape and motion. We demonstrate the potential of the proposed approach by introducing a novel challenging scene flow benchmark which allows for a thorough comparison of the proposed scene flow approach with respect to various baseline models. In contrast to previous benchmarks, our evaluation is the first to provide stereo and optical flow ground truth for dynamic real-world urban scenes at large scale. Our experiments reveal that rigid motion segmentation can be utilized as an effective regularizer for the scene flow problem, improving upon existing two-frame scene flow methods. At the same time, our method yields plausible object segmentations without requiring an explicitly trained recognition model for a specific object class.

Project Page [BibTex]

Project Page [BibTex]

2017


The Numerics of GANs
The Numerics of GANs

Mescheder, L., Nowozin, S., Geiger, A.

In Proceedings from the conference "Neural Information Processing Systems 2017., (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., Advances in Neural Information Processing Systems 30 (NIPS), December 2017 (inproceedings)

Abstract
In this paper, we analyze the numerics of common algorithms for training Generative Adversarial Networks (GANs). Using the formalism of smooth two-player games we analyze the associated gradient vector field of GAN training objectives. Our findings suggest that the convergence of current algorithms suffers due to two factors: i) presence of eigenvalues of the Jacobian of the gradient vector field with zero real-part, and ii) eigenvalues with big imaginary part. Using these findings, we design a new algorithm that overcomes some of these limitations and has better convergence properties. Experimentally, we demonstrate its superiority on training common GAN architectures and show convergence on GAN architectures that are known to be notoriously hard to train.

pdf Project Page [BibTex]

2017

pdf Project Page [BibTex]


Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?
Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?

Behl, A., Jafari, O. H., Mustikovela, S. K., Alhaija, H. A., Rother, C., Geiger, A.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computer Vision (ICCV), October 2017 (inproceedings)

Abstract
Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome these 3D motion estimation problems by exploiting recognition. In particular, we investigate the importance of recognition granularity, from coarse 2D bounding box estimates over 2D instance segmentations to fine-grained 3D object part predictions. We compute these cues using CNNs trained on a newly annotated dataset of stereo images and integrate them into a CRF-based model for robust 3D scene flow estimation - an approach we term Instance Scene Flow. We analyze the importance of each recognition cue in an ablation study and observe that the instance segmentation cue is by far strongest, in our setting. We demonstrate the effectiveness of our method on the challenging KITTI 2015 scene flow benchmark where we achieve state-of-the-art performance at the time of submission.

pdf suppmat Poster Project Page [BibTex]

pdf suppmat Poster Project Page [BibTex]


Sparsity Invariant CNNs
Sparsity Invariant CNNs

Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.

International Conference on 3D Vision (3DV) 2017, International Conference on 3D Vision (3DV), October 2017 (conference)

Abstract
In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth upsampling from sparse laser scan data. First, we show that traditional convolutional networks perform poorly when applied to sparse data even when the location of missing data is provided to the network. To overcome this problem, we propose a simple yet effective sparse convolution layer which explicitly considers the location of missing data during the convolution operation. We demonstrate the benefits of the proposed network architecture in synthetic and real experiments \wrt various baseline approaches. Compared to dense baselines, the proposed sparse convolution network generalizes well to novel datasets and is invariant to the level of sparsity in the data. For our evaluation, we derive a novel dataset from the KITTI benchmark, comprising 93k depth annotated RGB images. Our dataset allows for training and evaluating depth upsampling and depth prediction techniques in challenging real-world settings.

pdf suppmat Project Page Project Page [BibTex]

pdf suppmat Project Page Project Page [BibTex]