Prof. Dr. Thomas Brox

In the Computer Vision Lab we work on transferring step by step the tremendous capabilities of the human visual system to computers. In this context we work with various techniques from optimization, signal processing and machine learning. The numerous applications of computer vision range from robotics to analysis methods in biology and medicine.
A special focus of our group is on video analysis. In contrast to a collection of static images, images in a video are strongly correlated. We work on exploiting this correlation to extract motion features and learn properties of objects. Moreover, we are working on reliable motion estimation and tracking of structures.
We are also interested in recognizing objects, or generally "patterns" in images. As the same object or object class can look quite different depending on the circumstances, this is a challenging task and currently the main topic of interest in computer vision. We work on learning those features of an object that discriminate the object well from other objects, but are stable under typical variations. In particular, we are interested in learning such features automatically from videos.

10 selected publications:

• 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.
• An objective comparison of cell-tracking algorithms.
  Ulman V, Maška M, Magnusson KEG, Ronneberger O, Haubold C, Harder N, Matula P, Matula P, Svoboda D, Radojevic M, Smal I, Rohr K, Jaldén J, Blau HM, Dzyubachyk O, Lelieveldt B, Xiao P, Li Y, Cho SY, Dufour AC, Olivo-Marin JC, Reyes-Aldasoro CC, Solis-Lemus JA, Bensch R, Brox T, Stegmaier J, Mikut R, Wolf S, Hamprecht FA, Esteves T, Quelhas P, Demirel Ö, Malmström L, Jug F, Tomancak P, Meijering E, Muñoz-Barrutia A, Kozubek M, Ortiz-de-Solorzano C (2017).
  Nat Methods 14, 1141-52.
• Learning to Generate Chairs, Tables and Cars with Convolutional Networks.
  Dosovitskiy A, Springenberg J, Tatarchenko M, Brox T (2017).
  IEEE Trans Pattern Anal Mach Intell. 39, 692-705.
• Spatiotemporal deformable prototypes for motion anomaly detection.
  Bensch R, Scherf N, Huisken J, Brox T, Ronneberger O (2017).
  International Journal of Computer Vision 122(3), 502-23.
• 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)
• 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.
• ViBE-Z: a framework for 3D virtual colocalization analysis in zebrafish larval brains.
  Ronneberger O, Liu K, Rath M, Rueβ D, Mueller T, Skibbe H, Drayer B, Schmidt T, Filippi A, Nitschke R, Brox T, Burkhardt H, Driever W (2012).
  Nat Methods 9, 735-42.
• Large displacement optical flow: descriptor matching in variational motion estimation.
  Brox T, Malik J (2011).
  IEEE Trans Pattern Anal Mach. Intell. 33, 500-13.
• Inversin relays Frizzled-8 signals to promote proximal pronephros development.
  Lienkamp S, Ganner A, Boehlke C, Schmidt T, Arnold SJ, Schäfer T, Romaker D, Schuler J, Hoff S, Powelske C, Eifler A, Krönig C, Bullerkotte A, Nitschke R, Kuehn EW, Kim E, Burkhardt H, Brox T, Ronneberger O, Gloy J, Walz G (2010).
  Proc Natl Acad Sci U S A. 107, 20388-93.