CURVE: CLIP-Utilized Reinforcement Learning for Visual Image Enhancement via Simple Image Processing

TL;DR

CURVE introduces a reinforcement learning approach utilizing CLIP for perceptually optimized low-light image enhancement, emphasizing simplicity, efficiency, and high-quality results for high-resolution images.

Contribution

The paper presents a novel reinforcement learning framework that leverages CLIP for perceptually guided image enhancement using a simple, efficient global tone adjustment method.

Findings

Outperforms traditional methods in enhancement quality.

Achieves faster processing speeds for high-resolution images.

Demonstrates effectiveness on multiple low-light datasets.

Abstract

Low-Light Image Enhancement (LLIE) is crucial for improving both human perception and computer vision tasks. This paper addresses two challenges in zero-reference LLIE: obtaining perceptually 'good' images using the Contrastive Language-Image Pre-Training (CLIP) model and maintaining computational efficiency for high-resolution images. We propose CLIP-Utilized Reinforcement learning-based Visual image Enhancement (CURVE). CURVE employs a simple image processing module which adjusts global image tone based on B\'ezier curve and estimates its processing parameters iteratively. The estimator is trained by reinforcement learning with rewards designed using CLIP text embeddings. Experiments on low-light and multi-exposure datasets demonstrate the performance of CURVE in terms of enhancement quality and processing speed compared to conventional methods.