EUVIMEDEUVIMED entdecken
Crossref

Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching

Zhelun Shen, Xibin Song, Yuchao Dai, Dingfu Zhou, Zhibo Rao, Liangjun Zhang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 14301-14320

DOI: 10.1109/tpami.2023.3300976 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Zhelun Shen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Jiangxi Natural Science Foundations, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the domain differences and unbalanced disparity distribution across multiple datasets, current stereo matching approaches are commonly limited to a specific dataset and generalize poorly to others. Such domain shift issue is usually addressed by substantial adaptation on costly target-domain ground-truth data, which cannot be easily obtained in practical settings. In this paper, we propose to dig into uncertainty estimation for robust stereo matching. Specifically, to balance the disparity distribution, we employ a pixel-level uncertainty estimation to adaptively adjust the next stage disparity searching space, in this way driving the network progressively prune out the space of unlikely correspondences. Then, to solve the limited ground truth data, an uncertainty-based pseudo-label is proposed to adapt the pre-trained model to the new domain, where pixel-level and area-level uncertainty estimation are proposed to filter out the high-uncertainty pixels of predicted disparity maps and generate sparse while reliable pseudo-labels to align the domain gap. Experimentally, our method shows strong cross-domain, adapt, and joint generalization and obtains 1st place on the stereo task of Robust Vision Challenge 2020. Additionally, our uncertainty-based pseudo-labels can be extended to train monocular depth estimation networks in an unsupervised way and even achieves comparable performance with the supervised methods.

Förderung

  • National Natural Science Foundation of China
  • Jiangxi Natural Science Foundations
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Shen, Z., Song, X., Dai, Y., Zhou, D., Rao, Z., & Zhang, L. (2023). Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 14301-14320. https://doi.org/10.1109/tpami.2023.3300976

Vancouver

Shen Z, Song X, Dai Y, Zhou D, Rao Z, Zhang L. Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):14301-14320. doi:10.1109/tpami.2023.3300976

BibTeX
@article{Shen2023,
  author = {Shen, Zhelun and Song, Xibin and Dai, Yuchao and Zhou, Dingfu and Rao, Zhibo and Zhang, Liangjun},
  title = {Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {12},
  pages = {14301--14320},
  doi = {10.1109/tpami.2023.3300976}
}
Kostenlos starten →