Underwater Image Enhancement by Diffusion Model with Customized CLIP-Classifier

TL;DR

This paper introduces CLIP-UIE, a novel underwater image enhancement framework leveraging diffusion models and CLIP to improve visual quality without relying on real reference images, achieving more natural results.

Contribution

The paper proposes a new framework combining diffusion models and CLIP for underwater image enhancement, with a novel high-frequency targeted fine-tuning strategy that accelerates training.

Findings

Achieves more natural and visually appealing underwater images.

Faster fine-tuning process, up to 10 times quicker than traditional methods.

Effectively leverages synthetic data and CLIP guidance for improved enhancement.

Abstract

Underwater Image Enhancement (UIE) aims to improve the visual quality from a low-quality input. Unlike other image enhancement tasks, underwater images suffer from the unavailability of real reference images. Although existing works exploit synthetic images and manually select well-enhanced images as reference images to train enhancement networks, their upper performance bound is limited by the reference domain. To address this challenge, we propose CLIP-UIE, a novel framework that leverages the potential of Contrastive Language-Image Pretraining (CLIP) for the UIE task. Specifically, we propose employing color transfer to yield synthetic images by degrading in-air natural images into corresponding underwater images, guided by the real underwater domain. This approach enables the diffusion model to capture the prior knowledge of mapping transitions from the underwater degradation domain to the real in-air natural domain. Still, fine-tuning the diffusion model for specific downstream tasks is inevitable and may result in the loss of this prior knowledge. To migrate this drawback, we combine the prior knowledge of the in-air natural domain with CLIP to train a CLIP-Classifier. Subsequently, we integrate this CLIP-Classifier with UIE benchmark datasets to jointly fine-tune the diffusion model, guiding the enhancement results towards the in-air natural domain. Additionally, for image enhancement tasks, we observe that both the image-to-image diffusion model and CLIP-Classifier primarily focus on the high-frequency region during fine-tuning. Therefore, we propose a new fine-tuning strategy that specifically targets the high-frequency region, which can be up to 10 times faster than traditional strategies. Extensive experiments demonstrate that our method exhibits a more natural appearance.