EUVIMEDEUVIMED entdecken
Crossref

Correlation Matching Transformation Transformers for UHD Image Restoration

Cong Wang, Jinshan Pan, Wei Wang, Gang Fu, Siyuan Liang, Mengzhu Wang, Xiao-Ming Wu, Jun Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5336-5344

DOI: 10.1609/aaai.v38i6.28341 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Cong Wang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 76-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high features and reconstructs the residual images, while the latter explores more representative features learning from the high-resolution ones to facilitate better restoration. To better improve feature representation in low-resolution space, we propose to build feature transformation from the high-resolution space to the low-resolution one. To that end, we propose two new modules: Dual-path Correlation Matching Transformation module (DualCMT) and Adaptive Channel Modulator (ACM). The DualCMT selects top C/r (r is greater or equal to 1 which controls the squeezing level) correlation channels from the max-pooling/mean-pooling high-resolution features to replace low-resolution ones in Transformers, which can effectively squeeze useless content to improve the feature representation in low-resolution space to facilitate better recovery. The ACM is exploited to adaptively modulate multi-level high-resolution features, enabling to provide more useful features to low-resolution space for better learning. Experimental results show that our UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods while significantly improving performance under different training sets on 3 UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring. The source codes will be made available at https://github.com/supersupercong/UHDformer.

Zitieren

APA

Wang, C., Pan, J., Wang, W., Fu, G., Liang, S., Wang, M., Wu, X., & Liu, J. (2024). Correlation Matching Transformation Transformers for UHD Image Restoration. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5336-5344. https://doi.org/10.1609/aaai.v38i6.28341

Vancouver

Wang C, Pan J, Wang W, Fu G, Liang S, Wang M, et al. Correlation Matching Transformation Transformers for UHD Image Restoration. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5336-5344. doi:10.1609/aaai.v38i6.28341

BibTeX
@article{Wang2024,
  author = {Wang, Cong and Pan, Jinshan and Wang, Wei and Fu, Gang and Liang, Siyuan and Wang, Mengzhu and Wu, Xiao-Ming and Liu, Jun},
  title = {Correlation Matching Transformation Transformers for UHD Image Restoration},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {6},
  pages = {5336--5344},
  doi = {10.1609/aaai.v38i6.28341}
}
Kostenlos starten →