Large Foundation Model Empowered Discriminative Underwater Image Enhancement
Authors:
Top Cited Papers
- 3 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-17
Abstract
The underwater color disparity is an important cue for enhancing an underwater image. Applying the underwater color disparity indiscriminately to the entire underwater image tends to give rise to foreground-background crosstalk with either excessive foreground or insufficient background enhancement. To address the discriminativeness between underwater color disparities in foreground and background regions, we develop a discriminative underwater image enhancement method empowered by large foundation model technology. We first utilize the Segment Anything Model to generate segmentation masks, dividing the underwater image into foreground and background regions. This enables accurate foreground-background separation. Then, we conduct adaptive color compensation and fusion to improve the color histogram similarity for foreground and background regions separately. This corrects color deviations and improves contrasts in a discriminative manner that avoids the foreground-background crosstalk. Finally, we propose high-frequency edge fusion to extract high-frequency components from both the original underwater image and the fused image, and then fuse these components to obtain the final enhanced image. This eliminates blurred details arising from the discriminative processing of foreground and background regions. Our method represents the pioneering application of large foundation model technology to empower underwater image enhancement. Experimental results indicate that our method outperforms nine state-of-the-art underwater image enhancement methods in visual quality, achieves superior results across five underwater image quality evaluation metrics on three underwater image datasets, and is beneficial for practical applications such as underwater feature matching. We release our code at https://gitee.com/wanghaoupc/UIE SAM.Keywords
Funding Information
- Taishan Scholar Project of Shandong Province
- Chinese Scholarship Council
This publication has 66 references indexed in Scilit:
- HCLR-Net: Hybrid Contrastive Learning Regularization with Locally Randomized Perturbation for Underwater Image EnhancementInternational Journal of Computer Vision, 2024
- Underwater image enhancement via histogram similarity-oriented color compensation complemented by multiple attribute adjustmentIntelligent Marine Technology and Systems, 2023
- Underwater Camera: Improving Visual Perception Via Adaptive Dark Pixel Prior and Color CorrectionInternational Journal of Computer Vision, 2023
- Enhancing underwater image via adaptive color and contrast enhancement, and denoisingEngineering Applications of Artificial Intelligence, 2022
- An imaging-inspired no-reference underwater color image quality assessment metricComputers and Electrical Engineering, 2018
- Pixelwise View Selection for Unstructured Multi-View Stereo2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Microsoft COCO: Common Objects in Context2014
- Indoor Segmentation and Support Inference from RGBD Images2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009