Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles
Publication in refereed journal

Times Cited
Web of Science18WOS source URL (as at 16/11/2020) Click here for the latest count
Altmetrics Information

Other information
AbstractWe propose a depth and image scene flow estimation method taking the input of a binocular video. The key component is motion-depth temporal consistency preservation, making computation in long sequences reliable. We tackle a number of fundamental technical issues, including connection establishment between motion and depth, structure consistency preservation in multiple frames, and long-range temporal constraint employment for error correction. We address all of them in a unified depth and scene flow estimation framework. Our main contributions include development of motion trajectories, which robustly link frame correspondences in a voting manner, rejection of depth/motion outliers through temporal robust regression, novel edge occurrence map estimation, and introduction of anisotropic smoothing priors for proper regularization.
All Author(s) ListHung CH, Xu L, Jia JY
Journal nameInternational Journal of Computer Vision
Volume Number102
Issue Number1-3
Pages271 - 292
LanguagesEnglish-United Kingdom
KeywordsChained temporal profiles; Consistent scene flow; Stereo matching; Video depth estimation
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Last updated on 2020-17-11 at 01:58