Visual Inference
The Visual Inference Lab at TU Darmstadt, led by Prof. Stefan Roth, conducts research in several areas of computer vision with an emphasis on statistical methods and machine learning. We develop mathematical models and algorithms for analyzing and processing digital images with the computer. For example, we work on semantic scene understanding, image motion estimation, deep learning, probabilistic methods, image restoration, and object tracking.
Moreover, we regularly offer courses, seminars and labs in computer science, particularly in computer vision and machine learning.
Recent Highlight

News & Events
-
Longuet-Higgins Prize 2020
June 16, 2020
Stefan Roth and his co-authors Deqing Sun and Michael J. Black have been awarded the Longuet-Higgins Prize for their CVPR 2010 paper “Secrets of Optical Flow and Their Principles”.
Recent Publications
-
NeurIPS 2020
J. Dong, S. Roth and B. Schiele, “Deep Wiener deconvolution: Wiener meets deep learning for image deblurring,” oral presentation. [coming soon]
-
WACV 2021
F. Saeedan, S. Roth, “Boosting Monocular Depth with Panoptic Segmentation Maps.” [coming soon]
-
IJCV
P. Dendorfer, A. Ošep, A. Milan, K. Schindler, D. Cremers, I. Reid, S. Roth, L. Leal-Taixé, “MOTChallenge: A Benchmark for Single-camera Multiple Target Tracking.” [preprint]
-
NeurIPS 2020
S. Mahajan and S. Roth, “Diverse image captioning with context-object split latent spaces.” [preprint], [code]