Computer Vision - ECCV 2002

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.

Inhalt

Surface Geometry.- A Variational Approach to Recovering a Manifold from Sample Points.- A Variational Approach to Shape from Defocus.- Shadow Graphs and Surface Reconstruction.- Specularities Reduce Ambiguity of Uncalibrated Photometric Stereo.- Grouping and Segmentation.- Pairwise Clustering with Matrix Factorisation and the EM Algorithm.- Shape Priors for Level Set Representations.- Nonlinear Shape Statistics in Mumford-Shah Based Segmentation.- Class-Specific, Top-Down Segmentation.- Structure from Motion / Stereoscopic Vision / Surface Geometry / Shape.- Quasi-Dense Reconstruction from Image Sequence.- Properties of the Catadioptric Fundamental Matrix.- Building Architectural Models from Many Views Using Map Constraints.- Motion - Stereo Integration for Depth Estimation.- Lens Distortion Recovery for Accurate Sequential Structure and Motion Recovery.- Generalized Rank Conditions in Multiple View Geometry with Applications to Dynamical Scenes.- Dense Structure-from-Motion: An Approach Based on Segment Matching.- Maximizing Rigidity: Optimal Matching under Scaled-Orthography.- Dramatic Improvements to Feature Based Stereo.- Motion Curves for Parametric Shape and Motion Estimation.- Bayesian Self-Calibration of a Moving Camera.- Balanced Recovery of 3D Structure and Camera Motion from Uncalibrated Image Sequences.- Linear Multi View Reconstruction with Missing Data.- Model-Based Silhouette Extraction for Accurate People Tracking.- On the Non-linear Optimization of Projective Motion Using Minimal Parameters.- Structure from Many Perspective Images with Occlusions.- Sequence-to-Sequence Self Calibration.- Structure from Planar Motions with Small Baselines.- Revisiting Single-View Shape Tensors: Theory and Applications.- Tracking and Rendering Using Dynamic Textures on Geometric Structure from Motion.- Sensitivity of Calibration to Principal Point Position.- Critical Curves and Surfaces for Euclidean Reconstruction.- View Synthesis with Occlusion Reasoning Using Quasi-Sparse Feature Correspondences.- Eye Gaze Correction with Stereovision for Video-Teleconferencing.- Wavelet-Based Correlation for Stereopsis.- Stereo Matching Using Belief Propagation.- Symmetric Sub-pixel Stereo Matching.- New Techniques for Automated Architectural Reconstruction from Photographs.- Stereo Matching with Segmentation-Based Cooperation.- Coarse Registration of Surface Patches with Local Symmetries.- Multiview Registration of 3D Scenes by Minimizing Error between Coordinate Frames.- Recovering Surfaces from the Restoring Force.- Interpolating Sporadic Data.- Highlight Removal Using Shape-from-Shading.- A Reflective Symmetry Descriptor.- Gait Sequence Analysis Using Frieze Patterns.- Feature-Preserving Medial Axis Noise Removal.- Hierarchical Shape Modeling for Automatic Face Localization.- Using Dirichlet Free Form Deformation to Fit Deformable Models to Noisy 3-D Data.- Transitions of the 3D Medial Axis under a One-Parameter Family of Deformations.- Learning Shape from Defocus.- A Rectilinearity Measurement for Polygons.- Local Analysis for 3D Reconstruction of Specular Surfaces - Part II.- Matching Distance Functions: A Shape-to-Area Variational Approach for Global-to-Local Registration.- Shape from Shading and Viscosity Solutions.- Model Acquisition by Registration of Multiple Acoustic Range Views.- Structure from Motion.- General Trajectory Triangulation.- Surviving Dominant Planes in Uncalibrated Structure and Motion Recovery.- A Bayesian Estimation of Building Shape Using MCMC.- Structure and Motion for Dynamic Scenes - The Case of Points Moving in Planes.- What Does the Scene Look Like from a Scene Point?.