DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume

Miao, Xingyu; Bai, Yang; Duan, Haoran; Huang, Yawen; Wan, Fan; Xu, Xinxing; Long, Yang; Zheng, Yefeng

Abstract

Self-supervised monocular depth estimation methods typically rely on the reprojection error to capture geometric relationships between successive frames in static environments. However, this assumption does not hold in dynamic objects in scenarios, leading to errors during the view synthesis stage, such as feature mismatch and occlusion, which can significantly reduce the accuracy of the generated depth maps. To address this problem, we propose a novel dynamic cost volume that exploits residual optical flow to describe moving objects, improving incorrectly occluded regions in static cost volumes used in previous work. Nevertheless, the dynamic cost volume inevitably generates extra occlusions and noise, thus we alleviate this by designing a fusion module that makes static and dynamic cost volumes compensate for each other. In other words, occlusion from the static volume is refined by the dynamic volume, and incorrect information from the dynamic volume is eliminated by the static volume. Furthermore, we propose a pyramid distillation loss to reduce photometric error inaccuracy at low resolutions and an adaptive photometric error loss to alleviate the flow direction of the large gradient in the occlusion regions. We conducted extensive experiments on the KITTI and Cityscapes datasets, and the results demonstrate that our model outperforms previously published baselines for self-supervised monocular depth estimation.

Citation

Miao, X., Bai, Y., Duan, H., Huang, Y., Wan, F., Xu, X., …Zheng, Y. (2023). DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume. IEEE Transactions on Circuits and Systems for Video Technology, https://doi.org/10.1109/tcsvt.2023.3305776

• Journal Article Type: Article
• Acceptance Date: Aug 15, 2023
• Online Publication Date: Aug 15, 2023
• Publication Date: 2023
• Deposit Date: Oct 6, 2023
• Publicly Available Date: Oct 6, 2023
• Journal: IEEE Transactions on Circuits and Systems for Video Technology
• Print ISSN: 1051-8215
• Electronic ISSN: 1558-2205
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/tcsvt.2023.3305776
• Public URL: https://durham-repository.worktribe.com/output/1758337