EUVIMEDEUVIMED entdecken
Crossref

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

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

IEEE Transactions on Circuits and Systems for Video Technology · 2024-04 · 34 (4) · 2564-2576

DOI: 10.1109/tcsvt.2023.3305776 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-04. Verfasst von Xingyu Miao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: Securing the Energy/Transport Interface, U.K. Medical Research Council (MRC) Innovation Fellowship, International Exchanges 2022.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Securing the Energy/Transport Interface
  • U.K. Medical Research Council (MRC) Innovation Fellowship
  • International Exchanges 2022

Zitieren

APA

Miao, X., Bai, Y., Duan, H., Huang, Y., Wan, F., Xu, X., Long, Y., & Zheng, Y. (2024). DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume. IEEE Transactions on Circuits and Systems for Video Technology, 34(4), 2564-2576. https://doi.org/10.1109/tcsvt.2023.3305776

Vancouver

Miao X, Bai Y, Duan H, Huang Y, Wan F, Xu X, et al. DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(4):2564-2576. doi:10.1109/tcsvt.2023.3305776

BibTeX
@article{Miao2024,
  author = {Miao, Xingyu and Bai, Yang and Duan, Haoran and Huang, Yawen and Wan, Fan and Xu, Xinxing and Long, Yang and Zheng, Yefeng},
  title = {DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {4},
  pages = {2564--2576},
  doi = {10.1109/tcsvt.2023.3305776}
}
Kostenlos starten →