Loading...
Loading...

Go to the content (press return)

Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes

Author
Trulls, E.; Sanfeliu, A.; Moreno-Noguer, F.
Type of activity
Presentation of work at congresses
Name of edition
12th European Conference on Computer Vision
Date of publication
2012
Presentation's date
2012
Book of congress proceedings
Computer vision - ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012: proceedings
First page
441
Last page
454
Publisher
Springer
DOI
https://doi.org/10.1007/978-3-642-33712-3_32 Open in new window
Repository
http://hdl.handle.net/2117/19254 Open in new window
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-b...
Citation
Trulls, E.; Sanfeliu, A.; Moreno-Noguer, F. Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes. A: European Conference on Computer Vision. "Computer Vision – ECCV 2012. Workshops and Demonstrations". Florència: Springer, 2012, p. 441-454.
Keywords
appearance descriptors, spatiotemporal, stereo
Group of research
VIS - Artificial Vision and Intelligent Systems

Participants