CLIP Guided Image-perceptive Prompt Learning for Image Enhancement

TL;DR

This paper introduces CLIP-LUT, a novel image enhancement method that leverages CLIP-guided prompts to improve image quality by effectively discerning degraded images and guiding LUT-based enhancement.

Contribution

It proposes a simple CLIP-guided prompt learning framework for image enhancement, integrating CLIP's prior knowledge with LUT-based methods for improved performance.

Findings

CLIP-LUT effectively discerns image quality differences.

The method improves image enhancement results.

Simple integration of CLIP prompts enhances LUT-based models.

Abstract

Image enhancement is a significant research area in the fields of computer vision and image processing. In recent years, many learning-based methods for image enhancement have been developed, where the Look-up-table (LUT) has proven to be an effective tool. In this paper, we delve into the potential of Contrastive Language-Image Pre-Training (CLIP) Guided Prompt Learning, proposing a simple structure called CLIP-LUT for image enhancement. We found that the prior knowledge of CLIP can effectively discern the quality of degraded images, which can provide reliable guidance. To be specific, We initially learn image-perceptive prompts to distinguish between original and target images using CLIP model, in the meanwhile, we introduce a very simple network by incorporating a simple baseline to predict the weights of three different LUT as enhancement network. The obtained prompts are used to steer the enhancement network like a loss function and improve the performance of model. We demonstrate that by simply combining a straightforward method with CLIP, we can obtain satisfactory results.