Scale Space, Flow, Restoration -- A l 1-Unified Variational Framework for Image Restoration -- Support Blob Machines -- High Accuracy Optical Flow Estimation Based on a Theory for Warping -- Model-Based Approach to Tomographic Reconstruction Including Projection Deblurring. Sensitivity of Parameter Model to Noise on Data -- 2D Shape Detection and Recognition -- Unlevel-Sets: Geometry and Prior-Based Segmentation -- Learning and Bayesian Shape Extraction for Object Recognition -- Multiphase Dynamic Labeling for Variational Recognition-Driven Image Segmentation -- Posters IV -- Integral Invariant Signatures -- Detecting Keypoints with Stable Position, Orientation, and Scale under Illumination Changes -- Spectral Simplification of Graphs -- Inferring White Matter Geometry from Diffusion Tensor MRI: Application to Connectivity Mapping -- Unifying Approaches and Removing Unrealistic Assumptions in Shape from Shading: Mathematics Can Help -- Morphological Operations on Matrix-Valued Images -- Constraints on Coplanar Moving Points -- A PDE Solution of Brownian Warping -- Stereovision-Based Head Tracking Using Color and Ellipse Fitting in a Particle Filter -- Parallel Variational Motion Estimation by Domain Decomposition and Cluster Computing -- Whitening for Photometric Comparison of Smooth Surfaces under Varying Illumination -- Structure from Motion of Parallel Lines -- A Bayesian Framework for Multi-cue 3D Object Tracking -- On the Significance of Real-World Conditions for Material Classification -- Toward Accurate Segmentation of the LV Myocardium and Chamber for Volumes Estimation in Gated SPECT Sequences -- An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets -- Human Pose Estimation Using Learnt Probabilistic Region Similarities and Partial Configurations -- Tensor Field Segmentation Using Region Based Active Contour Model -- Groupwise Diffeomorphic Non-rigid Registration for Automatic Model Building -- Separating Transparent Layers through Layer Information Exchange -- Multiple Classifier System Approach to Model Pruning in Object Recognition -- Coaxial Omnidirectional Stereopsis -- Classifying Materials from Their Reflectance Properties -- Seamless Image Stitching in the Gradient Domain -- Spectral Clustering for Robust Motion Segmentation -- Learning Outdoor Color Classification from Just One Training Image -- A Polynomial-Time Metric for Attributed Trees -- Probabilistic Multi-view Correspondence in a Distributed Setting with No Central Server -- Monocular 3D Reconstruction of Human Motion in Long Action Sequences -- Fusion of Infrared and Visible Images for Face Recognition -- Reliable Fiducial Detection in Natural Scenes -- Light Field Appearance Manifolds -- Galilean Differential Geometry of Moving Images -- Tracking People with a Sparse Network of Bearing Sensors -- Transformation-Invariant Embedding for Image Analysis -- The Least-Squares Error for Structure from Infinitesimal Motion -- Stereo Based 3D Tracking and Scene Learning, Employing Particle Filtering within EM -- 3D Shape Representation and Reconstruction -- The Isophotic Metric and Its Application to Feature Sensitive Morphology on Surfaces -- A Closed-Form Solution to Non-rigid Shape and Motion Recovery -- Stereo Using Monocular Cues within the Tensor Voting Framework -- Shape and View Independent Reflectance Map from Multiple Views.

Welcome to the proceedings of the 8th European Conference on Computer - sion! Following a very successful ECCV 2002, the response to our call for papers was almost equally strong – 555 papers were submitted. We accepted 41 papers for oral and 149 papers for poster presentation. Several innovations were introduced into the review process. First, the n- ber of program committee members was increased to reduce their review load. We managed to assign to program committee members no more than 12 papers. Second, we adopted a paper ranking system. Program committee members were asked to rank all the papers assigned to them, even those that were reviewed by additional reviewers. Third, we allowed authors to respond to the reviews consolidated in a discussion involving the area chair and the reviewers. Fourth, thereports,thereviews,andtheresponsesweremadeavailabletotheauthorsas well as to the program committee members. Our aim was to provide the authors with maximal feedback and to let the program committee members know how authors reacted to their reviews and how their reviews were or were not re?ected in the ?nal decision. Finally, we reduced the length of reviewed papers from 15 to 12 pages. ThepreparationofECCV2004wentsmoothlythankstothee?ortsofthe- ganizing committee, the area chairs, the program committee, and the reviewers. We are indebted to Anders Heyden, Mads Nielsen, and Henrik J. Nielsen for passing on ECCV traditions and to Dominique Asselineau from ENST/TSI who kindly provided his GestRFIA conference software. We thank Jan-Olof Eklundh and Andrew Zisserman for encouraging us to organize ECCV 2004 in Prague.