T
Thomas Brox
Researcher at University of Freiburg
Publications - 353
Citations - 127470
Thomas Brox is an academic researcher from University of Freiburg. The author has contributed to research in topics: Segmentation & Optical flow. The author has an hindex of 99, co-authored 329 publications receiving 94431 citations. Previous affiliations of Thomas Brox include Dresden University of Technology & University of California, Berkeley.
Papers
More filters
Journal ArticleDOI
On the Equivalence of Soft Wavelet Shrinkage, Total Variation Diffusion, Total Variation Regularization, and SIDEs
TL;DR: It is proved that Haar wavelet shrinkage on a single scale is equivalent to a single step of space-discrete TV diffusion or regularization of two-pixel pairs, and it is shown that waveletshrinkage on multiple scales can be regarded as asingle step diffusion filtering orregularization of the Laplacian pyramid of the signal.
Journal ArticleDOI
Optimization and Filtering for Human Motion Capture
TL;DR: A multi-layer framework that combines stochastic optimization, filtering, and local optimization is introduced and quantitative 3D pose tracking results for the complete HumanEva-II dataset are provided.
Proceedings ArticleDOI
Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions
Peter Ochs,Thomas Brox +1 more
TL;DR: A variational method to obtain dense segmentations from sparse trajectory clusters by propagating information with a hierarchical, nonlinear diffusion process that runs in the continuous domain but takes superpixels into account.
Journal ArticleDOI
Efficient Nonlocal Means for Denoising of Textural Patterns
TL;DR: An iterative version of the nonlocal means filter that is derived from a variational principle and is designed to yield nontrivial steady states is suggested to be particularly useful in order to restore regular, textured patterns.
Proceedings Article
Understanding and Robustifying Differentiable Architecture Search
TL;DR: It is shown that by adding one of various types of regularization to DARTS, one can robustify DARTS to find solutions with less curvature and better generalization properties, and proposes several simple variations of DARTS that perform substantially more robustly in practice.