Temporally coherent disparity maps using CRFs with fast 4D filtering

Arjomand, Siavash; Budweiser, Gregor; Zwicker, Matthias (2016). Temporally coherent disparity maps using CRFs with fast 4D filtering. IPSJ Transactions on Computer Vision and Applications, 8(1) Springer 10.1186/s41074-016-0011-2

Preview

Text art%3A10.1186%2Fs41074-016-0011-2.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (1MB) | Preview

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.

Interest & Impact

Downloads

203 since deposited on 14 Feb 2017
28 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item