High Quality Underwater Image Compression with Adaptive Correction and Codebook-based Augmentation

2025-05-15

AI Summary

Existing underwater image compression methods neglect underwater-specific degradations—including wavelength-dependent light attenuation, severe color casts, and semantic redundancy—leading to suboptimal reconstruction quality. To address this, we propose the first end-to-end learnable compression framework tailored for underwater scenes. Our method comprises three key components: (1) an Adaptive Light Transmission and Compensation (ALTC) module that jointly estimates wavelength-adaptive light attenuation coefficients and global illumination; (2) a codebook-assisted branch that explicitly models structural priors of common underwater objects; and (3) a dynamic weighted multi-scale frequency-domain attention mechanism that enhances fidelity in distortion-sensitive frequency bands. Trained via rate-distortion optimization, our framework achieves significant improvements over state-of-the-art methods across multiple underwater benchmarks: +1.82 dB average PSNR and +0.023 MS-SSIM at equal bitrates, with marked gains in color fidelity and fine-detail preservation.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Data Mining & Knowledge Management: Data Compression

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

With the increasing exploration and exploitation of the underwater world, underwater images have become a critical medium for human interaction with marine environments, driving extensive research into their efficient transmission and storage. However, contemporary underwater image compression algorithms fail to fully leverage the unique characteristics distinguishing underwater scenes from terrestrial images, resulting in suboptimal performance. To address this limitation, we introduce HQUIC, designed to exploit underwater-image-specific features for enhanced compression efficiency. HQUIC employs an ALTC module to adaptively predict the attenuation coefficients and global light information of the images, which effectively mitigates the issues caused by the differences in lighting and tone existing in underwater images. Subsequently, HQUIC employs a codebook as an auxiliary branch to extract the common objects within underwater images and enhances the performance of the main branch. Furthermore, HQUIC dynamically weights multi-scale frequency components, prioritizing information critical for distortion quality while discarding redundant details. Extensive evaluations on diverse underwater datasets demonstrate that HQUIC outperforms state-of-the-art compression methods.

Problem

• Improves underwater image compression by leveraging unique underwater features
• Adaptively corrects lighting and tone issues in underwater images
• Enhances compression efficiency using codebook-based object extraction

Innovation

• ALTC module predicts underwater image attenuation coefficients
• Codebook extracts common objects for performance enhancement
• Dynamic weighting prioritizes critical multi-scale frequency components