We are interested in computer vision and machine learning with a focus on 3D scene understanding, parsing, reconstruction, material and motion estimation for autonomous intelligent systems such as self-driving cars or household robots. In particular, we investigate how complex prior knowledge can be incorporated into computer vision algorithms for making them robust to variations in our complex 3D world. You can follow us on GoogleScholar (paper email alert) and on YouTube (video email alert).
In many applications, an accurate model of the 3D scene is required. Not only when actors needs to take decisions based on the world around them, but also for accurate measurements, industrial inspection, object modeling (and reprinting in 3D!), and so on. For this, we need algorithms that are highly accurate but are still able to y... Read More
While deep learning achieves undeniably impressive results on many different aspects of computer vision, the theoretical foundations behind the success of these methods is often not well understood. We have specifically studied generative adversial networks (GANs). These are networks that generate data (images) based on some random ... Read More
Many problems in computer vision benefit from an accurate estimate of object motion and location. This is required for everything from self-driving cars, over 3D mapping, virtual reality, graphics, to robotics. Reasoning about the 3D world and its structure is one of the core concepts of computer vision. Flow: Read More
For website questions and technical problems please contact:
© 2018 Max-Planck-Gesellschaft - Imprint | Privacy Policy
