EUVIMEDEUVIMED entdecken
Crossref

Self-Supervised Pretraining for Stereoscopic Image Super-Resolution With Parallax-Aware Masking

Zhe Zhang, Jianjun Lei, Bo Peng, Jie Zhu, Qingming Huang

IEEE Transactions on Broadcasting · 2024-06 · 70 (2) · 482-491

DOI: 10.1109/tbc.2024.3382960 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Broadcasting, 2024-06. Verfasst von Zhe Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Science and Technology Major Project of Tibetan Autonomous Region of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most existing learning-based methods for stereoscopic image super-resolution rely on a great number of high-resolution stereoscopic images as labels. To alleviate the problem of data dependency, this paper proposes a self-supervised pretraining-based method for stereoscopic image super-resolution (SelfSSR). Specifically, to develop a self-supervised pretext task for stereoscopic images, a parallax-aware masking strategy (PAMS) is designed to adaptively mask matching areas of the left and right views. With PAMS, the network is encouraged to effectively predict missing information of input images. Besides, a cross-view Transformer module (CVTM) is presented to aggregate the intra-view and inter-view information simultaneously for stereoscopic image reconstruction. Meanwhile, the cross-attention map learned by CVTM is utilized to guide the masking process in PAMS. Comparative results on four datasets show that the proposed SelfSSR achieves state-of-the-art performance by using only 10% of labeled training data.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Science and Technology Major Project of Tibetan Autonomous Region of China

Zitieren

APA

Zhang, Z., Lei, J., Peng, B., Zhu, J., & Huang, Q. (2024). Self-Supervised Pretraining for Stereoscopic Image Super-Resolution With Parallax-Aware Masking. IEEE Transactions on Broadcasting, 70(2), 482-491. https://doi.org/10.1109/tbc.2024.3382960

Vancouver

Zhang Z, Lei J, Peng B, Zhu J, Huang Q. Self-Supervised Pretraining for Stereoscopic Image Super-Resolution With Parallax-Aware Masking. IEEE Transactions on Broadcasting. 2024;70(2):482-491. doi:10.1109/tbc.2024.3382960

BibTeX
@article{Zhang2024,
  author = {Zhang, Zhe and Lei, Jianjun and Peng, Bo and Zhu, Jie and Huang, Qingming},
  title = {Self-Supervised Pretraining for Stereoscopic Image Super-Resolution With Parallax-Aware Masking},
  journal = {IEEE Transactions on Broadcasting},
  year = {2024},
  volume = {70},
  number = {2},
  pages = {482--491},
  doi = {10.1109/tbc.2024.3382960}
}
Kostenlos starten →