EUVIMEDEUVIMED entdecken
Crossref

Stereo Image Restoration via Attention-Guided Correspondence Learning

Shengping Zhang, Wei Yu, Feng Jiang, Liqiang Nie, Hongxun Yao, Qingming Huang, Dacheng Tao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-07 · 46 (7) · 4850-4865

DOI: 10.1109/tpami.2024.3357709 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-07. Verfasst von Shengping Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Shenzhen Colleges and Universities Stable Support Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although stereo image restoration has been extensively studied, most existing work focuses on restoring stereo images with limited horizontal parallax due to the binocular symmetry constraint. Stereo images with unlimited parallax (e.g., large ranges and asymmetrical types) are more challenging in real-world applications and have rarely been explored so far. To restore high-quality stereo images with unlimited parallax, this paper proposes an attention-guided correspondence learning method, which learns both self- and cross-views feature correspondence guided by parallax and omnidirectional attention. To learn cross-view feature correspondence, a Selective Parallax Attention Module (SPAM) is proposed to interact with cross-view features under the guidance of parallax attention that adaptively selects receptive fields for different parallax ranges. Furthermore, to handle asymmetrical parallax, we propose a Non-local Omnidirectional Attention Module (NOAM) to learn the non-local correlation of both self- and cross-view contexts, which guides the aggregation of global contextual features. Finally, we propose an Attention-guided Correspondence Learning Restoration Network (ACLRNet) upon SPAMs and NOAMs to restore stereo images by associating the features of two views based on the learned correspondence. Extensive experiments on five benchmark datasets demonstrate the effectiveness and generalization of the proposed method on three stereo image restoration tasks including super-resolution, denoising, and compression artifact reduction.

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China
  • Shenzhen Colleges and Universities Stable Support Program

Zitieren

APA

Zhang, S., Yu, W., Jiang, F., Nie, L., Yao, H., Huang, Q., & Tao, D. (2024). Stereo Image Restoration via Attention-Guided Correspondence Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7), 4850-4865. https://doi.org/10.1109/tpami.2024.3357709

Vancouver

Zhang S, Yu W, Jiang F, Nie L, Yao H, Huang Q, et al. Stereo Image Restoration via Attention-Guided Correspondence Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(7):4850-4865. doi:10.1109/tpami.2024.3357709

BibTeX
@article{Zhang2024,
  author = {Zhang, Shengping and Yu, Wei and Jiang, Feng and Nie, Liqiang and Yao, Hongxun and Huang, Qingming and Tao, Dacheng},
  title = {Stereo Image Restoration via Attention-Guided Correspondence Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {7},
  pages = {4850--4865},
  doi = {10.1109/tpami.2024.3357709}
}
Kostenlos starten →