C
Christoph Vogel
Researcher at Graz University of Technology
Publications - 28
Citations - 1247
Christoph Vogel is an academic researcher from Graz University of Technology. The author has contributed to research in topics: Motion estimation & Motion field. The author has an hindex of 10, co-authored 27 publications receiving 886 citations. Previous affiliations of Christoph Vogel include ETH Zurich & RWTH Aachen University.
Papers
More filters
Proceedings ArticleDOI
Piecewise Rigid Scene Flow
TL;DR: A novel model that represents the dynamic 3D scene by a collection of planar, rigidly moving, local segments is introduced that achieves leading performance levels, exceeding competing3D scene flow methods, and even yielding better 2D motion estimates than all tested dedicated optical flow techniques.
Journal ArticleDOI
3D Scene Flow Estimation with a Piecewise Rigid Scene Model
TL;DR: This work proposes to represent the dynamic scene as a collection of rigidly moving planes, into which the input images are segmented, and shows that a view-consistent multi-frame scheme significantly improves accuracy, especially in the presence of occlusions, and increases robustness against adverse imaging conditions.
Proceedings ArticleDOI
3D scene flow estimation with a rigid motion prior
TL;DR: This work derives a local rigidity constraint of the 3D scene flow and defines a smoothness term that penalizes deviations from that constraint, thus favoring solutions that consist largely of rigidly moving parts.
Proceedings ArticleDOI
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling
TL;DR: An adaptive multi-resolution formulation of semantic 3D reconstruction which refines the reconstruction only in regions that are likely to contain a surface, exploiting the fact that both high spatial resolution and high numerical precision are only required in those regions.
Posted Content
PatchmatchNet: Learned Multi-View Patchmatch Stereo
TL;DR: For the first time, an iterative multi-scale Patchmatch in an end-to-end trainable architecture is introduced and the Patchmatch core algorithm is improved with a novel and learned adaptive propagation and evaluation scheme for each iteration.