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 Article
Variational Motion Segmentation with Level Sets
TL;DR: A variational method for the joint estimation of optic flow and the segmentation of the image into regions of similar motion made use of the level set framework following the idea of motion competition, which is extended to non-parametric motion.
Journal ArticleDOI
iPiasco: Inertial Proximal Algorithm for Strongly Convex Optimization
TL;DR: This paper presents a forward–backward splitting algorithm with additional inertial term for solving a strongly convex optimization problem of a certain type and proves it to be an optimal algorithm with linear rate of convergence.
Posted Content
What Do Single-view 3D Reconstruction Networks Learn?
TL;DR: This paper showed that the current state-of-the-art in single-view object reconstruction does not actually perform reconstruction but image classification, and proposed two alternative approaches that perform image classification and retrieval respectively.
Proceedings ArticleDOI
Deep learning for human part discovery in images
TL;DR: A network architecture that assigns each pixel to one of a predefined set of human body part classes, such as head, torso, arms, legs, is presented, which achieves state-of-the-art performance on the PASCAL Parts dataset.
Proceedings ArticleDOI
Semantics-aware visual localization under challenging perceptual conditions
TL;DR: This paper proposes a novel approach for learning a discriminative holistic image representation which exploits the image content to create a dense and salient scene description and shows that the learnt image representation outperforms off-the-shelf features from the deep networks and hand-crafted features.