Mathematical methods has been a dominant research path in computational vision leading to a number of areas like ?ltering, segmentation, motion analysis and stereo reconstruction. Within such a branch visual perception tasks can either be addressed through the introduction of application-driven geometric ?ows or through the minimization of problem-driven cost functions where their lowest potential corresponds to image understanding. The 3rd IEEE Workshop on Variational, Geometric and Level Set Methods focused on these novel mathematical techniques and their applications to c- puter vision problems. To this end, from a substantial number of submissions, 30 high-quality papers were selected after a fully blind review process covering a large spectrum of computer-aided visual understanding of the environment. The papers are organized into four thematic areas: (i) Image Filtering and Reconstruction, (ii) Segmentation and Grouping, (iii) Registration and Motion Analysis and (iiii) 3D and Reconstruction. In the ?rst area solutions to image enhancement, inpainting and compression are presented, while more advanced applications like model-free and model-based segmentation are presented in the segmentation area. Registration of curves and images as well as multi-frame segmentation and tracking are part of the motion understanding track, while - troducing computationalprocessesinmanifolds,shapefromshading,calibration and stereo reconstruction are part of the 3D track. We hope that the material presented in the proceedings exceeds your exp- tations and will in?uence your research directions in the future. We would like to acknowledge the support of the Imaging and Visualization Department of Siemens Corporate Research for sponsoring the Best Student Paper Award.
Author(s): Jing Yuan, Christoph Schnörr (auth.), Nikos Paragios, Olivier Faugeras, Tony Chan, Christoph Schnörr (eds.)
Series: Lecture Notes in Computer Science 3752
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2005
Language: English
Pages: 372
Tags: Computer Imaging, Vision, Pattern Recognition and Graphics; Pattern Recognition; Image Processing and Computer Vision; Artificial Intelligence (incl. Robotics); Algorithm Analysis and Problem Complexity; Computer Graphics
Front Matter....Pages -
A Study of Non-smooth Convex Flow Decomposition....Pages 1-12
Denoising Tensors via Lie Group Flows....Pages 13-24
Nonlinear Inverse Scale Space Methods for Image Restoration....Pages 25-36
Towards PDE-Based Image Compression....Pages 37-48
Color Image Deblurring with Impulsive Noise....Pages 49-60
Using an Oriented PDE to Repair Image Textures....Pages 61-72
Image Cartoon-Texture Decomposition and Feature Selection Using the Total Variation Regularized L 1 Functional....Pages 73-84
Structure-Texture Decomposition by a TV-Gabor Model....Pages 85-96
From Inpainting to Active Contours....Pages 97-108
Sobolev Active Contours....Pages 109-120
Advances in Variational Image Segmentation Using AM-FM Models: Regularized Demodulation and Probabilistic Cue Integration....Pages 121-136
Entropy Controlled Gauss-Markov Random Measure Field Models for Early Vision....Pages 137-148
Global Minimization of the Active Contour Model with TV-Inpainting and Two-Phase Denoising....Pages 149-160
Combined Geometric-Texture Image Classification....Pages 161-172
Heuristically Driven Front Propagation for Geodesic Paths Extraction....Pages 173-185
Trimap Segmentation for Fast and User-Friendly Alpha Matting....Pages 186-197
Uncertainty-Driven Non-parametric Knowledge-Based Segmentation: The Corpus Callosum Case....Pages 198-209
Dynamical Statistical Shape Priors for Level Set Based Sequence Segmentation....Pages 210-221
Non-rigid Shape Comparison of Implicitly-Defined Curves....Pages 222-234
Incorporating Rigid Structures in Non-rigid Registration Using Triangular B-Splines....Pages 235-246
Geodesic Image Interpolation: Parameterizing and Interpolating Spatiotemporal Images....Pages 247-258
A Variational Approach for Object Contour Tracking....Pages 259-270
Implicit Free-Form-Deformations for Multi-frame Segmentation and Tracking....Pages 271-282
A Surface Reconstruction Method for Highly Noisy Point Clouds....Pages 283-294
A C 1 Globally Interpolatory Spline of Arbitrary Topology....Pages 295-306
Solving PDEs on Manifolds with Global Conformal Parametriazation....Pages 307-319
Fast Marching Method for Generic Shape from Shading....Pages 320-331
A Gradient Descent Procedure for Variational Dynamic Surface Problems with Constraints....Pages 332-343
Regularization of Mappings Between Implicit Manifolds of Arbitrary Dimension and Codimension....Pages 344-355
Lens Distortion Calibration Using Level Sets....Pages 356-367
Back Matter....Pages -