Match stereo videos via bidirectional alignment
File(s)
Accepted version
Author(s)
Jing, Junpeng
Mao, Ye
Qiu, Anlan
Mikolajczyk, Krystian
Type
Journal Article
Abstract
Video stereo matching is the task of estimating consistent disparity maps from rectified stereo videos. There is considerable scope for improvement in both datasets and methods within this area. Recent learning-based methods often focus on optimizing performance for independent stereo pairs, leading to temporal inconsistencies in videos. Existing video methods typically employ sliding window operation over time dimension, which can result in low-frequency oscillations corresponding to the window size. To address these challenges, we propose a bidirectional alignment mechanism for adjacent frames as a fundamental operation. Building on this, we introduce a novel video processing framework, BiDAStereo, and a plugin stabilizer network, BiDAStabilizer, compatible with general image-based methods. Regarding datasets, current synthetic object-based and indoor datasets are commonly used for training and benchmarking, with a lack of outdoor nature scenarios. To bridge this gap, we present a realistic synthetic dataset and benchmark focused on natural scenes, along with a real-world dataset captured by a stereo camera in diverse urban scenes for qualitative evaluation. Extensive experiments on in-domain, out-of-domain, and robustness evaluation demonstrate the contribution of our methods and datasets, showcasing improvements in prediction quality and achieving state-of-the-art results on various commonly used benchmarks.
Date Issued
2026-08-01
Date Acceptance
2026-03-27
Citation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026, 48 (8), pp.9337-9353
ISSN
0162-8828
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Start Page
9337
End Page
9353
Journal / Book Title
IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume
48
Issue
8
Copyright Statement
Copyright © 2026 IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/41915511
Publication Status
Published
Coverage Spatial
United States
Date Publish Online
2026-03-31