Shape from Contours and Multiple Stereo " A Hierarchical, Mesh-Based Approach

Authors:
Affiliations:
Venue:
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Year:
2004

Citing 13
Cited 0

Fast computation of the Euclidian distance maps for binary images: Fast computations of the Euclidean distance maps for binary images

Information Processing Letters
Numerical recipes in C (2nd ed.): the art of scientific computing

Numerical recipes in C (2nd ed.): the art of scientific computing
Photorealistic Scene Reconstruction by Voxel Coloring

International Journal of Computer Vision
√3-subdivision

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Feature sensitive surface extraction from volume data

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
A Theory of Shape by Space Carving

International Journal of Computer Vision - Special issue on Genomic Signal Processing
Spatio-Temporal Stereo Using Multi-Resolution Subdivision Surfaces

International Journal of Computer Vision
The Visual Hull Concept for Silhouette-Based Image Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence
Polyhedral Visual Hulls for Real-Time Rendering

Proceedings of the 12th Eurographics Workshop on Rendering Techniques
Real-Time Generation and High-Fidelity Visualization of 3D Video

ICCIMA '03 Proceedings of the 5th International Conference on Computational Intelligence and Multimedia Applications
Stochastic Refinement of the Visual Hull to Satisfy Photometric and Silhouette Consistency Constraints

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Variational principles, surface evolution, PDEs, level set methods, and the stereo problem

IEEE Transactions on Image Processing
A survey of methods for volumetric scene reconstruction from photographs

VG'01 Proceedings of the 2001 Eurographics conference on Volume Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel method for 3D shape recoverybased on a combination of visual hull informationand multi image stereo. We start from a coarse trianglemesh extracted from visual hull information. Themesh is then hierarchically refined and its vertex positionsare optimized based on multi image stereo information.This optimization procedure utilizes 3Dgraphics hardware to evaluate the quality of vertexpositions, and takes both color consistency, and occlusioneffects as well as silhouette information into account.By directly working on a triangle mesh we areable to obtain more spatial coherence than algorithmsbased entirely on point information, such asvoxel-based methods. This allows us to deal with objectsthat have very little structure in some places,as well as small specular patches.