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
Book ChapterDOI
Nonparametric density estimation with adaptive, anisotropic kernels for human motion tracking
TL;DR: The concentration of human motion data on lower-dimensional manifolds, approves kernel density estimation as a transparent tool that is able to model priors on arbitrary mixtures of human motions.
Proceedings ArticleDOI
Global, Dense Multiscale Reconstruction for a Billion Points
Benjamin Ummenhofer,Thomas Brox +1 more
TL;DR: A variational approach for surface reconstruction from a set of oriented points with scale information is presented, focusing particularly on scenarios with non-uniform point densities due to images taken from different distances.
Posted Content
Learning to Generate Chairs with Convolutional Neural Networks
TL;DR: In this paper, a generative convolutional neural network is trained to generate images of objects given object type, viewpoint, and color, which can be used to find correspondences between different chairs from the dataset.
Journal ArticleDOI
Fully automated segmentation and morphometrical analysis of muscle fiber images.
TL;DR: An automated image analysis method is proposed for objective, reproducible, and time‐saving measurement of muscle fibers in routinely hematoxylin‐eosin stained cryostat sections.
Book ChapterDOI
PDE-based deconvolution with forward-backward diffusivities and diffusion tensors
TL;DR: This work addresses the problem of deblurring with a spatially invariant kernel of arbitrary shape by studying nonconvex variational functionals that lead to diffusion-reaction equations of Perona–Malik type and proposes a continuation strategy in which the diffusion weight is reduced during the process.