Visual Inference

Headerbild Scene Flow Faded

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

Teaser ICCV15 I2G Registration
Registering an untextured 3D geometry to a photograph (ICCV 2015)

News & Events

  • IV 2016 Best Paper Award

    Marius Cordts, Timo Rehfeld and Stefan Roth have won the Best Paper Award (First Prize) at the IEEE Intelligent Vehicles Symposium 2016for the paper “Semantic stixels: Depth is not enough”.

  • MOT16 Challenge

    The 2016 challenge of the Multiple Object Tracking Benchmark (MOT16) has been released. Please visit for data, instructions & results.

  • Cityscapes Dataset Released

    The Cityscapes Dataset for sematic urban scene understanding has been officially released: Please visit for data, instructions & results

Recent Publications

  • CVPR 2016

    J. Gast, A. Sellent, and S. Roth, “Parametric object motion from blur,” to appear. [preprint], [supplemental]

  • CVPR 2016

    M. Cordts, M. Omran, S. Ramos, T. Scharwächter, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” to appear, spotlight presentation. [preprint], [supplemental], [benchmark]

  • IV 2016

    L. Schneider, M. Cordts, T. Rehfeld, D. Pfeiffer, M. Enzweiler, U. Franke, M. Pollefeys, and S. Roth, “Semantic stixels: Depth is not enough,” oral presentation, best paper award. [preprint]

  • arXiv 2016

    L. Leal-Taixé, A. Milan, I. Reid, S. Roth, and K. Schindler, “MOT16: A benchmark for multi object tracking”. [benchmark]

  • PAMI

    A. Milan, K. Schindler, S. Roth, “Multi-target tracking by discrete-continuous energy minimization,” to appear. [preprint]

  • ICCV 2015

    T. Plötz and S. Roth, Registering Images to Untextured Geometry using Average Shading Gradients,” oral presentation, [open access], [supplemental], [video]

  • PAMI

    U. Schmidt, J. Jancsary, S. Nowozin, S. Roth, and C. Rother, “Cascades of regression tree fields for image restoration” [open access]