Computer Vision - ECCV 2002

1. Front Matter

   Pages I-XXIV

   PDF

2. Shape

   1. 3D Statistical Shape Models Using Direct Optimisation of Description Length

      • Rhodri H. Davies, Carole J. Twining, Tim F. Cootes, John C. Waterton, Chris J. Taylor

      Pages 3-20

   2. Approximate Thin Plate Spline Mappings

      • Gianluca Donato, Serge Belongie

      Pages 21-31

   3. DEFORMOTION Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images

      • Stefano Soatto, Anthony J. Yezzi

      Pages 32-47

   4. Region Matching with Missing Parts

      • Alessandro Duci, Anthony J. Yezzi, Sanjoy Mitter, Stefano Soatto

      Pages 48-62

3. Stereoscopic Vision I

   1. What Energy Functions Can Be Minimized via Graph Cuts?

      • Vladimir Kolmogorov, Ramin Zabih

      Pages 65-81

   2. Multi-camera Scene Reconstruction via Graph Cuts

      • Vladimir Kolmogorov, Ramin Zabih

      Pages 82-96

   3. A Markov Chain Monte Carlo Approach to Stereovision

      • Julien Sénégas

      Pages 97-111

   4. A Probabilistic Theory of Occupancy and Emptiness

      • Rahul Bhotika, David J. Fleet, Kiriakos N. Kutulakos

      Pages 112-130

4. Texture Shading and Colour / Grouping and Segmentation / Object Recognition

   1. Texture Similarity Measure Using Kullback-Leibler Divergence between Gamma Distributions

      • John Reidar Mathiassen, Amund Skavhaug, Ketil Bø

      Pages 133-147

   2. All the Images of an Outdoor Scene

      • Srinivasa G. Narasimhan, Chi Wang, Shree K. Nayar

      Pages 148-162

   3. Recovery of Reflectances and Varying Illuminants from Multiple Views

      • Q.-Tuan Luong, Pascal Fua, Yvan Leclerc

      Pages 163-179

   4. Composite Texture Descriptions

      • Alexey Zalesny, Vittorio Ferrari, Geert Caenen, Dominik Auf der Maur, Luc Van Gool

      Pages 180-194

   5. Constructing Illumination Image Basis from Object Motion

      • Akiko Nakashima, Atsuto Maki, Kazuhiro Fukui

      Pages 195-209

   6. Diffuse-Specular Separation and Depth Recovery from Image Sequences

      • Stephen Lin, Yuanzhen Li, Sing Bing Kang, Xin Tong, Heung-Yeung Shum

      Pages 210-224

   7. Shape from Texture without Boundaries

      • D. A. Forsyth

      Pages 225-239

   8. Statistical Modeling of Texture Sketch

      • Ying Nian Wu, Song Chun Zhu, Cheng-en Guo

      Pages 240-254

   9. Classifying Images of Materials: Achieving Viewpoint and Illumination Independence

      • Manik Varma, Andrew Zisserman

      Pages 255-271

   10. Estimation of Multiple Illuminants from a Single Image of Arbitrary Known Geometry

       • Yang Wang, Dimitris Samaras

       Pages 272-288

   11. The Effect of Illuminant Rotation on Texture Filters: Lissajous’s Ellipses

       • M. Chantler, M. Schmidt, M. Petrou, G. McGunnigle

       Pages 289-303

Premiering in 1990 in Antibes, France, the European Conference on Computer Vision, ECCV, has been held biennially at venues all around Europe. These conferences have been very successful, making ECCV a major event to the computer vision community. ECCV 2002 was the seventh in the series. The privilege of organizing it was shared by three universities: The IT University of Copenhagen, the University of Copenhagen, and Lund University, with the conference venue in Copenhagen. These universities lie ¨ geographically close in the vivid Oresund region, which lies partly in Denmark and partly in Sweden, with the newly built bridge (opened summer 2000) crossing the sound that formerly divided the countries. We are very happy to report that this year’s conference attracted more papers than ever before, with around 600 submissions. Still, together with the conference board, we decided to keep the tradition of holding ECCV as a single track conference. Each paper was anonymously refereed by three different reviewers. For the nal selection, for the rst time for ECCV, a system with area chairs was used. These met with the program chairsinLundfortwodaysinFebruary2002toselectwhatbecame45oralpresentations and 181 posters.Also at this meeting the selection was made without knowledge of the authors’identity.

• 3D
• 3D reconstruction
• Fuzzy
• Image segmentation
• Shading
• algortihmic learning
• camera calibration
• classifiers
• cognition
• computer vision
• learning
• multiple images
• object recognition
• robot vision
• shape reconstru

• Centre for Mathematical Sciences, Lund University, Lund, Sweden

  Anders Heyden, Gunnar Sparr

• The IT University of Copenhagen, Copenhagen, Denmark

  Mads Nielsen

• University of Copenhagen, Copenhagen, Denmark

  Peter Johansen

Policies and ethics