Temporally coherent disparity maps using CRFs with fast 4D filtering
Options
BORIS DOI
Date of Publication
December 2016
Publication Type
Article
Division/Institute
Series
IPSJ Transactions on Computer Vision and Applications
ISSN or ISBN (if monograph)
1882-6695
Publisher
Springer
Language
English
Publisher DOI
Description
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 the mean-field approximation. In addition, we introduce novel terms for smoothness and consistency between the left and right views. We perform CRF optimization by fast, iterative spatio-temporal filtering with linear complexity in the total number of pixels. We propose two CRF optimization techniques, using parallel and sequential updates, and compare them in detail. While parallel updates are not guaranteed to converge, we show that, in practice with appropriate initialization, they provide the same quality as sequential updates and they also lead to faster implementations. Finally, we demonstrate that the results of our approach rank among the state of the art while having significantly less flickering artifacts in stereo sequences.
File(s)
File | File Type | Format | Size | License | Publisher/Copright statement | Content | |
---|---|---|---|---|---|---|---|
art%3A10.1186%2Fs41074-016-0011-2.pdf | text | Adobe PDF | 1.19 MB | Attribution (CC BY 4.0) | published |