HCLR-Net: Hybrid Contrastive Learning Regularization with Locally Randomized Perturbation for Underwater Image Enhancement
-
Published:2024-02-04
Issue:
Volume:
Page:
-
ISSN:0920-5691
-
Container-title:International Journal of Computer Vision
-
language:en
-
Short-container-title:Int J Comput Vis
Author:
Zhou JingchunORCID, Sun Jiaming, Li Chongyi, Jiang Qiuping, Zhou Man, Lam Kin-Man, Zhang Weishi, Fu Xianping
Abstract
AbstractUnderwater image enhancement presents a significant challenge due to the complex and diverse underwater environments that result in severe degradation phenomena such as light absorption, scattering, and color distortion. More importantly, obtaining paired training data for these scenarios is a challenging task, which further hinders the generalization performance of enhancement models. To address these issues, we propose a novel approach, the Hybrid Contrastive Learning Regularization (HCLR-Net). Our method is built upon a distinctive hybrid contrastive learning regularization strategy that incorporates a unique methodology for constructing negative samples. This approach enables the network to develop a more robust sample distribution. Notably, we utilize non-paired data for both positive and negative samples, with negative samples are innovatively reconstructed using local patch perturbations. This strategy overcomes the constraints of relying solely on paired data, boosting the model’s potential for generalization. The HCLR-Net also incorporates an Adaptive Hybrid Attention module and a Detail Repair Branch for effective feature extraction and texture detail restoration, respectively. Comprehensive experiments demonstrate the superiority of our method, which shows substantial improvements over several state-of-the-art methods in terms of quantitative metrics, significantly enhances the visual quality of underwater images, establishing its innovative and practical applicability. Our code is available at: https://github.com/zhoujingchun03/HCLR-Net.
Funder
National Natural Science Foundation of China Liaoning Provincial Natural Science Foundation of China Fundamental Research Funds for the Central Universities Natural Science Foundation of China Natural Science Foundation of Zhejiang Natural Science Foundation of Ningbo
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Software
Reference72 articles.
1. Chen, R., Cai, Z., & Yuan, J. (2023). UIESC: An underwater image enhancement framework via self-attention and contrastive learning. IEEE Transactions on Industrial Informatics. 2. Chen, L., Chu, X., Zhang, X., & Sun, J. (2022). Simple baselines for image restoration. In European conference on computer vision (pp. 17–33). Springer. 3. Chen, X., Fan, Z., Li, P., Dai, L., Kong, C., Zheng, Z., Huang, Y., & Li, Y. (2022). Unpaired deep image dehazing using contrastive disentanglement learning. In European conference on computer vision (pp. 632–648). Springer. 4. Chen, X., Pan, J., Jiang, K., Li, Y., Huang, Y., Kong, C., Dai, L., & Fan, Z. (2022). Unpaired deep image deraining using dual contrastive learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 2017–2026). 5. Chen, R., Cai, Z., & Cao, W. (2021). MFFN: An underwater sensing scene image enhancement method based on multiscale feature fusion network. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–12.
|
|