EUVIMEDEUVIMED entdecken
Crossref

Underwater Depth Estimation via Stereo Adaptation Networks

Xinchen Ye, Jinyi Zhang, Yazhi Yuan, Rui Xu, Zhihui Wang, Haojie Li

IEEE Transactions on Circuits and Systems for Video Technology · 2023-09 · 33 (9) · 5089-5101

DOI: 10.1109/tcsvt.2023.3249223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-09. Verfasst von Xinchen Ye und 5 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Dalian High-Level Talents Innovation Support Plan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the fast development and wide application of stereo depth estimation, adequate high-quality stereo training data with groundtruth depth information plays an important role, but is not easily acquired in underwater environments. Therefore, satisfactory performance of depth estimation is difficult to achieve in underwater environments. In addition, the domain gap also leads to the failure of directly applying existing models of terrestrial scene to underwater scene. Therefore, this paper proposes a novel underwater depth estimation network which can infer depth maps from real underwater stereo images in an adaptation manner. The proposed learning pipeline mainly contains three different adaptation modules, i.e., style adaptation, semantic adaptation and disparity range adaptation, to progressively adapt a terrestrial depth estimation model to the underwater domain. Specifically, due to the lack of underwater training data, we first propose a depth-aware stereo image translation network to synthesize stylized underwater stereo images from terrestrial dataset, thus benefiting the effective training of depth estimation network. Then, considering the weak generalization to the real underwater data when only trained on the above synthetic data, we present a self-ensembling semantic adaptation for depth estimation network to minimize the semantic domain discrepancy between synthetic and real underwater data. Meanwhile, we design a disparity range adaptation module to address the problem of disparity range miss-match between both data, thus obtaining more accurate depth predictions for large-disparity-span underwater images. Experimental results show that by integrating the proposed adaptation modules into the off-the-shelf depth estimation backbones, our method successfully achieves superior performance of underwater depth estimation compared to other state-of-the-art methods.

Förderung

  • National Natural Science Foundation of China
  • Dalian High-Level Talents Innovation Support Plan

Zitieren

APA

Ye, X., Zhang, J., Yuan, Y., Xu, R., Wang, Z., & Li, H. (2023). Underwater Depth Estimation via Stereo Adaptation Networks. IEEE Transactions on Circuits and Systems for Video Technology, 33(9), 5089-5101. https://doi.org/10.1109/tcsvt.2023.3249223

Vancouver

Ye X, Zhang J, Yuan Y, Xu R, Wang Z, Li H. Underwater Depth Estimation via Stereo Adaptation Networks. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(9):5089-5101. doi:10.1109/tcsvt.2023.3249223

BibTeX
@article{Ye2023,
  author = {Ye, Xinchen and Zhang, Jinyi and Yuan, Yazhi and Xu, Rui and Wang, Zhihui and Li, Haojie},
  title = {Underwater Depth Estimation via Stereo Adaptation Networks},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {9},
  pages = {5089--5101},
  doi = {10.1109/tcsvt.2023.3249223}
}
Kostenlos starten →