The team of Thomas Brox is working on computer vision and deep learning with focus on visual representation learning, video analysis, and learned 3D representations. In particular, they explore ways to train deep networks with less data and less human supervision, which is today the bottleneck for most application domains. They are also investigating the robustness of learned models to data variation

Keywords:

computer vision, machine learning, deep learning, motion estimation

10 selected publications:

• DeepTAM: Deep tracking and mapping with convolutional networks.
  Zhou H, Ummenhofer B and Brox T (2020)
  International Journal of Computer Vision 128:756-69
• U-Net: deep learning for cell counting, detection, and morphometry.
  Falk T, Mai D, Bensch R, Çiçek Ö, Abdulkadir A, Marrakchi Y, Böhm A, Deubner J, Jäckel Z, Seiwald K, Dovzhenko A, Tietz O, Dal Bosco C, Walsh S, Saltukoglu D, Tay TL, Prinz M, Palme K, Simons M, Diester I, Brox T, Ronneberger O (2019).
  Nat Methods. 16(1):67-70.
• FlowNet 2.0: evolution of optical flow estimation with deep networks
  Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A and Brox T (2017)
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
• Discriminative unsupervised feature learning with exemplar convolutional neural networks.
  Dosovitskiy A, Fischer P, Springenberg JT, Riedmiller M, Brox T (2016).
  IEEE Trans. Pattern. Anal. Mach. Intell. 38, 1734-47.
• FlowNet: learning optical flow with convolutional networks.
  Dosovitskiy A, Fischer P, Ilg E, Häusser P, Hazirbas C, Golkov V, Smagt P, Cremers D, Brox T (2015).
  IEEE International Conference on Computer Vision (ICCV)
• U-Net: convolutional networks for biomedical image segmentation, Medical Image Computing and Computer-Assisted Intervention (MICCAI)
  Ronneberger O, Fischer P and Brox T (2015)
  Springer LNCS Vol. 9351, 234-41.
• Learning to generate chairs with convolutional neural networks
  Dosovitskiy A, Springenberg J and Brox T (2015)
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
• Segmentation of Moving Objects by Long Term Video Analysis.
  Ochs P, Malik J, Brox T (2014).
  IEEE Trans Pattern Anal Mach Intell. 36, 1187-200.
• Large displacement optical flow: descriptor matching in variational motion estimation.
  Brox T, Malik J (2011).
  IEEE Trans Pattern Anal Mach. Intell. 33, 500-13.
• High accuracy optical flow estimation based on a theory for warping.
  Brox T, Bruhn A, Papenberg N and Weickert J (2004)
  European Conference on Computer Vision, volume 3024 of Lecture Notes in Computer Science 25-36.