Abstract | ||
---|---|---|
We cast the problem of iriferring the 3D shape of a scene from a collection of defocused images in the framework of anisotropic diffusion. We propose a novel algorithm that can estimate the shape of a scene by iriferring the diffusion coefficient of a heat equation. The method is optimal, as we pose it as the minimization of a cenain cost functional based on the input images, and fast. Furthermore, we also extend our algorithm to the case of multiple images, and derive a 3D scene segmentation algorithm that can work in the presence of pictorial camouflage. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/CVPR.2003.1211352 | CVPR (1) |
Keywords | Field | DocType |
defocused image,diffusion coefficient,multiple image,cenain cost,input image,pictorial camouflage,anisotropic diffusion,scene segmentation algorithm,heat equation,novel algorithm,pattern recognition,partial differential equations,cost function,image segmentation,minimisation,computer vision,shape | Anisotropic diffusion,Computer vision,Computer science,Image segmentation,Camouflage,Minimisation (psychology),Minification,Artificial intelligence,Heat equation,Partial differential equation,Scene segmentation | Conference |
ISSN | ISBN | Citations |
1063-6919 | 0-7695-1900-8 | 12 |
PageRank | References | Authors |
1.21 | 11 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paolo Favaro | 1 | 127 | 11.23 |
Stanley Osher | 2 | 7973 | 514.62 |
Stefano Soatto | 3 | 4967 | 350.34 |
Luminita A. Vese | 4 | 5389 | 302.64 |