Temporally Coherent Disparity Maps Using CRFs with Fast 4D Filtering
| Data(s) |
2015
|
|---|---|
| Resumo |
State of the art methods for disparity estimation achieve good results for single stereo frames, but temporal coherence in stereo videos is often neglected. In this paper we present a method to compute temporally coherent disparity maps. We define an energy over whole stereo sequences and optimize their Conditional Random Field (CRF) distributions using mean-field approximation. We introduce novel terms for smoothness and consistency between the left and right views, and perform CRF optimization by fast, iterative spatio-temporal filtering with linear complexity in the total number of pixels. Our results rank among the state of the art while having significantly less flickering artifacts in stereo sequences. |
| Formato |
application/pdf |
| Identificador |
http://boris.unibe.ch/81126/1/PID3903707.pdf Arjomand, Siavash; Budweiser, Gregor; Zwicker, Matthias (2015). Temporally Coherent Disparity Maps Using CRFs with Fast 4D Filtering (Unpublished). In: Asian Conference on Pattern Recognition (ACPR). Kuala Lumpur. 03-06.11.2015. 10.1109/ACPR.2015.7486514 <http://dx.doi.org/10.1109/ACPR.2015.7486514> doi:10.7892/boris.81126 info:doi:10.1109/ACPR.2015.7486514 |
| Idioma(s) |
eng |
| Relação |
http://boris.unibe.ch/81126/ http://dx.doi.org/10.1109/ACPR.2015.7486514 |
| Direitos |
info:eu-repo/semantics/openAccess |
| Fonte |
Arjomand, Siavash; Budweiser, Gregor; Zwicker, Matthias (2015). Temporally Coherent Disparity Maps Using CRFs with Fast 4D Filtering (Unpublished). In: Asian Conference on Pattern Recognition (ACPR). Kuala Lumpur. 03-06.11.2015. 10.1109/ACPR.2015.7486514 <http://dx.doi.org/10.1109/ACPR.2015.7486514> |
| Palavras-Chave | #000 Computer science, knowledge & systems #510 Mathematics |
| Tipo |
info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/draft PeerReviewed |
