D
Daniel Cremers
Researcher at Technische Universität München
Publications - 702
Citations - 55592
Daniel Cremers is an academic researcher from Technische Universität München. The author has contributed to research in topics: Image segmentation & Computer science. The author has an hindex of 99, co-authored 655 publications receiving 44957 citations. Previous affiliations of Daniel Cremers include Siemens & University of Mannheim.
Papers
More filters
Book ChapterDOI
Low Rank Priors for Color Image Regularization
TL;DR: This work proposes a novel scheme of minimizing the rank of the image Jacobian and extends this idea to second derivatives in the framework of total generalized variation and introduces a novel algorithm for efficiently evaluating the proximal mapping of the l q norm appearing during optimization.
Proceedings ArticleDOI
Nonlinear Dynamical Shape Priors for Level Set Segmentation
TL;DR: This paper proposes to approximate the temporal evolution of the eigenmodes of the level set function by means of a mixture of autoregressive models and details how such shape priors "with memory" can be integrated into a variational framework for level set segmentation.
Journal ArticleDOI
Motion Field Estimation from Alternate Exposure Images
TL;DR: This work makes use of an additional long-exposed image for motion field estimation and describes a practical variational algorithm to estimate the motion field not only for visible image regions but also for regions getting occluded.
Book ChapterDOI
Robust variational segmentation of 3d objects from multiple views
TL;DR: A probabilistic formulation of 3D segmentation given a series of images from calibrated cameras, which can reconstruct the mean intensity and variance of the extracted object and background and cope with noisy data.
Book ChapterDOI
A Superresolution Framework for High-Accuracy Multiview Reconstruction
Bastian Goldlücke,Daniel Cremers +1 more
TL;DR: A variational approach to jointly estimate a displacement map and a superresolution texture for a 3D model from multiple calibrated views allows to obtain fine details in the texture map which surpass individual input image resolution.