Name
Abstract | ||
|---|---|---|
In this paper, we propose an algorithm that recovers binocu- lar disparities in accordance with the surface properties of the scene under consideration. To do so, we estimate the dispar- ity as well as the normals in the disparity space, by setting the two tasks in a unified framework. A novel joint probabilistic model is defined through two random fields to favor both in- tra field (within neighboring disparities and neighboring nor- mals) and inter field (between disparities and normals) consis- tency. Geometric contextual information is introduced in the models for both normals and disparities, which is optimized using an appropriate alternating maximization procedure. We illustrate the performance of our approach on synthetic and real data. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ICIP.2010.5653453 | ICIP |
Keywords | Field | DocType |
optimisation,probability,stereo image processing,alternating maximization procedure,disparity estimation,geometric contextual information,normal estimation,probabilistic model,Alternating Maximization,CRF,MRF,Stereo Vision | Computer vision,Contextual information,Random field,Pattern recognition,Stereopsis,Computer science,Statistical model,Pixel,Artificial intelligence,Normal estimation,Maximization,Belief propagation | Conference |
ISSN | Citations | PageRank |
1522-4880 | 0 | 0.34 |
References | Authors | |
10 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ramya Narasimha | 1 | 7 | 0.97 |
| Elise Arnaud | 2 | 126 | 10.05 |
| Florence Forbes | 3 | 115 | 9.87 |
| Radu Horaud | 4 | 2776 | 261.99 |