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
Book ChapterDOI
An Anisotropic Selection Scheme for Variational Optical Flow Methods with Order-Adaptive Regularisation
TL;DR: In this paper, the authors propose a generalised order-adaptive approach that allows to select the local regularisation order for each direction individually, which is applicable to scenes with both fronto-parallel and ego motion.
Posted Content
Technical Report on Visual Quality Assessment for Frame Interpolation
TL;DR: A subjective quality assessment study by crowdsourcing for the interpolated images provided in one of the optical flow benchmarks, the Middlebury benchmark, gives rise to a re-ranking of 141 participating algorithms and shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks.
Book ChapterDOI
A Comparison of Isotropic and Anisotropic Second Order Regularisers for Optical Flow
TL;DR: This work juxtapose general concepts for isotropic and anisotropic second order regularization based on direct second order methods, infimal convolution techniques, and indirect coupling models and shows that modelling anisotrop second order smoothness terms gives an additional degree of freedom when penalising deviations from smoothness.
Posted Content
Direct Variational Perspective Shape from Shading with Cartesian Depth Parametrisation
TL;DR: A novel variational model that operates directly on the Cartesian depth and a novel coarse-to-fine minimisation framework based on an alternating explicit scheme to avoid local minima during the minimisation and thus to improve the accuracy of the reconstruction.
Book ChapterDOI
Variational Large Displacement Optical Flow Without Feature Matches
TL;DR: A novel variational method is proposed for the simultaneous estimation and fusion of flow candidates and is able to capture different motion patterns and hence to estimate large displacements even without additional feature matches by jointly using multiple smoothness weights within a single energy functional.