Photorealistic Scene Reconstruction by Voxel Coloring
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A portable three-dimensional digitizer
NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Removal of Specular Reflection Component Using Multi-view Images and 3D Object Model
PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
Shape from Silhouette Consensus
Pattern Recognition
Passive reconstruction of high quality textured 3D models of works of art
VAST'05 Proceedings of the 6th International conference on Virtual Reality, Archaeology and Intelligent Cultural Heritage
| Hi-index | 0.01 |
A novel three-dimensional reconstruction algorithm "Shape-from-Silhouette/Stereo (SFS2)" is presented in this paper. This algorithm combines Shape-from-Silhouette with stereo based on simple voting-localizing operations in a voxel space. In this algorithm, Shape-from-Silhouette roughly estimates the shape of the target object first, and then multi-eye stereo is applied within the estimated area to refine the shape. This algorithm overcomes the shortcomings of each algorithm and offers the following: 1) More precise shape reconstruction than simple Shape-from-Silhouette; 2) Quicker processing than simple stereo-based reconstruction; and 3) Better noise reduction than multi-eye stereo. Our experiments showed that SFS2 is highly practical for generating 3D models of real objects.