Name
Abstract | ||
|---|---|---|
Given a set of low resolution camera images, it is possible to reconstruct high resolution luminance and depth information, specially if the relative displace- ments of the image frames are known. We have pro- posed iterative algorithms for recovering high resolu- tion albedo and depth maps that require no a priori knowledge of the scene, and therefore do not depend on other methods, as regards boundary and initial condi- tions. The problem of surface reconstruction has been formulated as one of Expectation Maximization (EM) and has been tackled in a probabilistic framework as- ing Markov Random Fields (MRF) (1)(3). As for the depth map, our method is directly recovering surface heights without refering to surface orientations, whale increasing the resolution by camera jittering (2). Con- ventional statistical models have been coupled with ge- ometrical techniques to construct a general model of t.he world and the imaging process. |
Year | DOI | Venue |
|---|---|---|
1994 | 10.1109/CVPR.1994.323784 | CVPR |
Keywords | Field | DocType |
Markov processes,image reconstruction,statistical models,Markov random fields,depth information,expectation maximization,high resolution 3D visual information reconstruction,low resolution camera images,luminance,relative displacements,statistical models,surface reconstruction | Iterative reconstruction,Computer vision,Surface reconstruction,Pattern recognition,Computer science,Expectation–maximization algorithm,A priori and a posteriori,Artificial intelligence,Hash function,Statistical model,Depth map,Image resolution | Conference |
Volume | Issue | ISSN |
1994 | 1 | 1063-6919 |
Citations | PageRank | References |
15 | 8.63 | 6 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| M. Berthod | 1 | 385 | 46.54 |
| H. Shekarforoush | 2 | 43 | 12.81 |
| M. Werman | 3 | 343 | 112.04 |
| Josiane Zerubia | 4 | 2032 | 232.91 |