EUVIMEDEUVIMED entdecken
Crossref

UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching

Qingxuan Lv, Junyu Dong, Yuezun Li, Sheng Chen, Hui Yu, Shu Zhang, Wenhan Wang

IEEE Transactions on Circuits and Systems for Video Technology · 2025-11 · 35 (11) · 11216-11228

DOI: 10.1109/tcsvt.2025.3572044 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-11. Verfasst von Qingxuan Lv und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Sanya Science and Technology Special Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite recent advances in stereo matching, the extension to intricate underwater settings remains unexplored, primarily owing to: 1) the reduced visibility, low contrast, and other adverse effects of underwater images; 2) the difficulty in obtaining ground truth data for training deep learning models, i.e. simultaneously capturing an image and estimating its corresponding pixel-wise depth information in underwater environments. To enable further advance in underwater stereo matching, we introduce a large synthetic dataset called UWStereo. Our dataset includes 29,568 synthetic stereo image pairs with dense and accurate disparity annotations for left view. We design four distinct underwater scenes filled with diverse objects such as corals, ships and robots. We also induce additional variations in camera model, lighting, and environmental effects. In comparison with existing underwater datasets, UWStereo is superior in terms of scale, variation, annotation, and photo-realistic image quality. To substantiate the efficacy of the UWStereo dataset, we undertake a comprehensive evaluation compared with eleven state-of-the-art algorithms as benchmarks. The results indicate that current models still struggle to generalize to new domains. Hence, we design a new strategy that learns to reconstruct cross domain masked images before stereo matching training and integrate a cross view attention enhancement module that aggregates long-range content information to enhance the generalization ability.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Sanya Science and Technology Special Fund
  • Leverhulme Trust

Zitieren

APA

Lv, Q., Dong, J., Li, Y., Chen, S., Yu, H., Zhang, S., & Wang, W. (2025). UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching. IEEE Transactions on Circuits and Systems for Video Technology, 35(11), 11216-11228. https://doi.org/10.1109/tcsvt.2025.3572044

Vancouver

Lv Q, Dong J, Li Y, Chen S, Yu H, Zhang S, et al. UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(11):11216-11228. doi:10.1109/tcsvt.2025.3572044

BibTeX
@article{Lv2025,
  author = {Lv, Qingxuan and Dong, Junyu and Li, Yuezun and Chen, Sheng and Yu, Hui and Zhang, Shu and Wang, Wenhan},
  title = {UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {11},
  pages = {11216--11228},
  doi = {10.1109/tcsvt.2025.3572044}
}
Kostenlos starten →