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

Darmstadt Noise Dataset: Ground truth data for image denoising with real image noise
Darmstadt Noise Dataset: Ground truth data for image denoising with real image noise

News & Events

  • PhD Defense

    October 17, 2017

    Marius Cordts has successfully defended his PhD thesis “Understanding Cityscapes: Efficient Urban Semantic Scene Understanding”. Congratulations!

  • PhD Defense

    September 26, 2017

    Timo Rehfeld has successfully defended his PhD thesis “Combining Appearance, Depth and Motion for Efficient Semantic Scene Understanding”. Congratulations!

  • PhD Defense

    August 22, 2017

    Kevin Schelten has successfully defended his PhD thesis “Foundations, Inference, and Deconvolution in Image Restoration”. Congratulations!

  • #1 on KITTI 2015 Optical Flow

    June 23, 2017

    Our MirrorFlow optical flow method [preprint] took the #1 spot among all two-frame optical flow methods on the KITTI 2015 benchmark.

  • Best PhD Thesis Award

    May 3, 2017

    Uwe Schmidt received the prize for outstanding scientific contributions in the category best PhD thesis in computer science by the Association of Friends of TU Darmstadt. Congratulations!

  • PhD Defense

    Dec. 16, 2016

    Uwe Schmidt has successfully defended his PhD thesis “Half-quadratic Inference and Learning for Natural Images”. Congratulations!

Recent Publications

  • AAAI 2018

    S. Meister, J. Hur, and S. Roth, “UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss”, [preprint], [code]

  • ICCV 2017

    J. Hur and S. Roth, “MirrorFlow: Exploiting symmetries in joint optical flow and occlusion estimation”, [preprint], [supplemental], [code]

  • ICCV 2017

    A. S. Wannenwetsch, M. Keuper, and S. Roth, “ProbFlow: Joint optical flow and uncertainty estimation”, [preprint], [supplemental], [code]

  • GCPR 2017

    F. Lang, T. Plötz and S. Roth, “Robust multi-image HDR reconstruction for the modulo camera”, [preprint], [supplemental]

  • IJCV

    T. Plötz and S. Roth, “Automatic registration of images to untextured geometry using average shading gradients”, [open access]

  • CVPR 2017

    T. Plötz and S. Roth, “Benchmarking denoising algorithms with real photographs.” [preprint], [supplemental], [benchmark website], [data]

  • CVPR 2017

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