Visual Inference

Visual Inference

The Visual Inference group 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 image restoration, image motion estimation, object recognition & tracking, and semantic scene understanding.

Moreover, we regularly offer courses, seminars and labs in computer science, particularly in computer vision and machine learning.

Recent Highlight

Obtaining ground truth data for computer vision using games

News & Events

Recent Publications

  • CVPR 2017

    T. Plötz and S. Roth, “Benchmarking denoising algorithms with real photographs.” [coming soon]

  • CVPR 2017

    M. Jin, S. Roth, and P. Favaro, “Noise-blind image deblurring.” [preprint], [supplemental]

  • ECCV 2016

    S. R. Richter, V. Vineet, S. Roth, and V. Koltun, “Playing for data: Ground truth from computer games.” [preprint] [video] [dataset] [code]

  • ECCV 2016

    A. Sellent, C. Rother, and S. Roth, “Stereo video deblurring.” [preprint] [supplemental]

  • ECCV 2016 Workshop

    J. Hur and S. Roth, “Joint optical flow and temporally consistent semantic segmentation,” best paper award. [preprint]


    M. Cordts, T. Rehfeld, M. Enzweiler, U. Franke, and S. Roth, “Tree-structured models for efficient multi-cue scene labeling,” to appear. [preprint]