2024-03-29T09:57:11Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/966862019-06-12T07:14:19Zcom_10261_106com_10261_4col_10261_1241
00925njm 22002777a 4500
dc
Trulls, Eduard
author
Sanfeliu, Alberto
author
Moreno-Noguer, Francesc
author
2012
This paper studies the use of temporal consistency to match appear- ance descriptors and handle complex ambiguities when computing dynamic depth maps from stereo. Previous attempts have designed 3D descriptors over the space- time 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.
Computer Vision – ECCV: 441-454 (2012)
http://hdl.handle.net/10261/96686
10.1007/978-3-642-33712-3_32
Spatiotemporal
Appearance descriptors
Stereo
Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes