Energy Minimization Methods in Computer Vision and Pattern Recognition

1. Front Matter

   PDF

2. Discrete and Continuous Optimization

   1. Convex Envelopes for Low Rank Approximation

      • Viktor Larsson, Carl Olsson

      Pages 1-14

   2. Maximizing Flows with Message-Passing: Computing Spatially Continuous Min-Cuts

      • Egil Bae, Xue-Cheng Tai, Jing Yuan

      Pages 15-28

   3. A Compact Linear Programming Relaxation for Binary Sub-modular MRF

      • Junyan Wang, Sai-Kit Yeung

      Pages 29-42

   4. On the Link between Gaussian Homotopy Continuation and Convex Envelopes

      • Hossein Mobahi, John W. Fisher III

      Pages 43-56

   5. How Hard Is the LP Relaxation of the Potts Min-Sum Labeling Problem?

      • Daniel Průša, Tomáš Werner

      Pages 57-70

   6. Coarse-to-Fine Minimization of Some Common Nonconvexities

      • Hossein Mobahi, John W. Fisher III

      Pages 71-84

3. Image Restoration and Inpainting

   1. Why Does Non-binary Mask Optimisation Work for Diffusion-Based Image Compression?

      • Laurent Hoeltgen, Joachim Weickert

      Pages 85-98

   2. Expected Patch Log Likelihood with a Sparse Prior

      • Jeremias Sulam, Michael Elad

      Pages 99-111

   3. Blind Deconvolution via Lower-Bounded Logarithmic Image Priors

      • Daniele Perrone, Remo Diethelm, Paolo Favaro

      Pages 112-125

   4. Low Rank Priors for Color Image Regularization

      • Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Moeller, Daniel Cremers

      Pages 126-140

   5. A Novel Framework for Nonlocal Vectorial Total Variation Based on ℓ^p,q,r −norms

      • Joan Duran, Michael Moeller, Catalina Sbert, Daniel Cremers

      Pages 141-154

   6. Inpainting of Cyclic Data Using First and Second Order Differences

      • Ronny Bergmann, Andreas Weinmann

      Pages 155-168

   7. Discrete Green’s Functions for Harmonic and Biharmonic Inpainting with Sparse Atoms

      • Sebastian Hoffmann, Gerlind Plonka, Joachim Weickert

      Pages 169-182

4. Segmentation

   1. A Fast Projection Method for Connectivity Constraints in Image Segmentation

      • Jan Stühmer, Daniel Cremers

      Pages 183-196

   2. Two-Dimensional Variational Mode Decomposition

      • Konstantin Dragomiretskiy, Dominique Zosso

      Pages 197-208

   3. Multi-class Graph Mumford-Shah Model for Plume Detection Using the MBO scheme

      • Huiyi Hu, Justin Sunu, Andrea L. Bertozzi

      Pages 209-222

   4. A Novel Active Contour Model for Texture Segmentation

      • Aditya Tatu, Sumukh Bansal

      Pages 223-236

   5. Segmentation Using SubMarkov Random Walk

      • Xingping Dong, Jianbing Shen, Luc Van Gool

      Pages 237-248

   6. Automatic Shape Constraint Selection Based Object Segmentation

      • Kunqian Li, Wenbing Tao, Xiangli Liao, Liman Liu

      Pages 249-262

This volume constitutes the refereed proceedings of the 10th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR 2015, held in Hong Kong, China, in January 2015. The 36 revised full papers were carefully reviewed and selected from 45 submissions. The papers are organized in topical sections on discrete and continuous optimization; image restoration and inpainting; segmentation; PDE and variational methods; motion, tracking and multiview reconstruction; statistical methods and learning; and medical image analysis.

• clustering algorithm
• computer vision
• convex optimization
• image processing
• iterative methods
• machine learning
• multi-view stereo
• numerical analysis
• optic disk
• optimization
• pattern recognition
• semantic image segmentation
• statistical methods
• total variation
• variational methods
• algorithm analysis and problem complexity

• Department of Mathematics, University of Bergen, Bergen, Norway

  Xue-Cheng Tai

• Department of Mathematics, University of California, Los Angeles, USA

  Egil Bae

• The Hong Kong University of Science and Technology, Kowloon, Hong Kong, S.A.R.

  Tony F. Chan

• Telemark University College, Porsgrunn, Norway

  Marius Lysaker

Policies and ethics