Physics-inspired Learning for Structure-Aware Texture-Sensitive Underwater Image Enhancement

Xinwei Xue, Zexuan Li, Long Ma, Risheng Liu, Xin Fan
Proceedings of The 13th Asian Conference on Machine Learning, PMLR 157:1224-1236, 2021.

Abstract

Recently, improving the visual quality of underwater images using deep learning-based methods has drawn considerable attention. Unfortunately, diverse environmental factors (e.g., blue/green color distortion) severely limit their performance in real-world environments. Therefore, strengthening the superiority of the underwater image enhancement method is critical. In this paper, we devote ourselves to develop a new architecture with strong superiority and adaptability. Inspired by the underwater imaging principle, we establish a novel physics-inspired learning model that is easy to realize. A Structure-Aware Texture-Sensitive Network (SATS-Net) is further developed to portray the model. The structure-aware module is responsible for structural information, and the texture-sensitive module is responsible for textural information. Thus, SATS-Net successfully incorporates robust characterization absorbed from the physical principle to achieve strong robustness and adaptability. We conduct extensive experiments to demonstrate that SATS-Net outperforms existing advanced techniques in various real-world underwater environments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v157-xue21a, title = {Physics-inspired Learning for Structure-Aware Texture-Sensitive Underwater Image Enhancement}, author = {Xue, Xinwei and Li, Zexuan and Ma, Long and Liu, Risheng and Fan, Xin}, booktitle = {Proceedings of The 13th Asian Conference on Machine Learning}, pages = {1224--1236}, year = {2021}, editor = {Balasubramanian, Vineeth N. and Tsang, Ivor}, volume = {157}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v157/xue21a/xue21a.pdf}, url = {https://proceedings.mlr.press/v157/xue21a.html}, abstract = {Recently, improving the visual quality of underwater images using deep learning-based methods has drawn considerable attention. Unfortunately, diverse environmental factors (e.g., blue/green color distortion) severely limit their performance in real-world environments. Therefore, strengthening the superiority of the underwater image enhancement method is critical. In this paper, we devote ourselves to develop a new architecture with strong superiority and adaptability. Inspired by the underwater imaging principle, we establish a novel physics-inspired learning model that is easy to realize. A Structure-Aware Texture-Sensitive Network (SATS-Net) is further developed to portray the model. The structure-aware module is responsible for structural information, and the texture-sensitive module is responsible for textural information. Thus, SATS-Net successfully incorporates robust characterization absorbed from the physical principle to achieve strong robustness and adaptability. We conduct extensive experiments to demonstrate that SATS-Net outperforms existing advanced techniques in various real-world underwater environments.} }
Endnote
%0 Conference Paper %T Physics-inspired Learning for Structure-Aware Texture-Sensitive Underwater Image Enhancement %A Xinwei Xue %A Zexuan Li %A Long Ma %A Risheng Liu %A Xin Fan %B Proceedings of The 13th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Vineeth N. Balasubramanian %E Ivor Tsang %F pmlr-v157-xue21a %I PMLR %P 1224--1236 %U https://proceedings.mlr.press/v157/xue21a.html %V 157 %X Recently, improving the visual quality of underwater images using deep learning-based methods has drawn considerable attention. Unfortunately, diverse environmental factors (e.g., blue/green color distortion) severely limit their performance in real-world environments. Therefore, strengthening the superiority of the underwater image enhancement method is critical. In this paper, we devote ourselves to develop a new architecture with strong superiority and adaptability. Inspired by the underwater imaging principle, we establish a novel physics-inspired learning model that is easy to realize. A Structure-Aware Texture-Sensitive Network (SATS-Net) is further developed to portray the model. The structure-aware module is responsible for structural information, and the texture-sensitive module is responsible for textural information. Thus, SATS-Net successfully incorporates robust characterization absorbed from the physical principle to achieve strong robustness and adaptability. We conduct extensive experiments to demonstrate that SATS-Net outperforms existing advanced techniques in various real-world underwater environments.
APA
Xue, X., Li, Z., Ma, L., Liu, R. & Fan, X.. (2021). Physics-inspired Learning for Structure-Aware Texture-Sensitive Underwater Image Enhancement. Proceedings of The 13th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 157:1224-1236 Available from https://proceedings.mlr.press/v157/xue21a.html.

Related Material