Title | ||
---|---|---|
Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes |
Abstract | ||
---|---|---|
This paper studies the use of temporal consistency to match appearance descriptors and handle complex ambiguities when computing dynamic depth maps from stereo. Previous attempts have designed 3D descriptors over the spacetime volume and have been mostly used for monocular action recognition, as they cannot deal with perspective changes. Our approach is based on a state-of-the-art 2D dense appearance descriptor which we extend in time by means of optical flow priors, and can be applied to wide-baseline stereo setups. The basic idea behind our approach is to capture the changes around a feature point in time instead of trying to describe the spatiotemporal volume. We demonstrate its effectiveness on very ambiguous synthetic video sequences with ground truth data, as well as real sequences. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33712-3_32 | ECCV (3) |
Keywords | Field | DocType |
spatiotemporal descriptor,dense appearance descriptor,basic idea,ambiguous synthetic video sequence,appearance descriptors,feature point,wide-baseline stereo reconstruction,complex ambiguity,ambiguous scene,spatiotemporal volume,dynamic depth map,spacetime volume,stereo setup,stereo,spatiotemporal | Computer vision,Computer science,Spacetime,Action recognition,Ground truth,Stereo reconstruction,Artificial intelligence,Monocular,Prior probability,Optical flow,Temporal consistency | Conference |
Volume | ISSN | Citations |
7574 | 0302-9743 | 2 |
PageRank | References | Authors |
0.36 | 21 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eduard Trulls | 1 | 318 | 11.07 |
Alberto Sanfeliu | 2 | 1757 | 162.98 |
Francesc Moreno-Noguer | 3 | 1647 | 93.46 |