A
Andrés Bruhn
Researcher at University of Stuttgart
Publications - 95
Citations - 9062
Andrés Bruhn is an academic researcher from University of Stuttgart. The author has contributed to research in topics: Optical flow & Motion estimation. The author has an hindex of 36, co-authored 95 publications receiving 8474 citations. Previous affiliations of Andrés Bruhn include Saarland University.
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.
Book ChapterDOI
Variational motion segmentation with level sets
TL;DR: In this paper, a variational method for the joint estimation of optic flow and segmentation of the image into regions of similar motion is proposed, which makes use of the level set framework following the idea of motion competition.
Book ChapterDOI
From box filtering to fast explicit diffusion
TL;DR: A novel class of algorithms that combine the advantages of both worlds are presented: They are based on simple explicit schemes, while being more efficient than semi-implicit approaches.
Book ChapterDOI
On robust estimation and smoothing with spatial and tonal kernels
TL;DR: In this paper, a unified framework of functional minimisation combining nonlocal data and nonlocal smoothness terms is presented, which can be used for combining the advantages of known filters.
Book ChapterDOI
A survey on variational optic flow methods for small displacements
TL;DR: In this article, the authors present a survey on different model assumptions for each of these terms and illustrate their impact by experiments on rotationally invariant convex functionals with a linearised data term.