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

2025-05-29

AI Summary

This work addresses the no-reference low-light image enhancement (LLIE) task, aiming to jointly optimize perceptual quality and high-resolution real-time performance. To overcome limitations of existing methods—namely, lack of semantic guidance and excessive computational overhead—we propose CLIP-RL: a novel framework that for the first time leverages CLIP text embeddings as a perceptual reward signal to guide Proximal Policy Optimization (PPO) for global tone parameter optimization. We further design a differentiable, lightweight Bézier curve-based color adjustment module, enabling efficient, end-to-end trainable pixel-wise mapping. The method adopts a zero-reference training paradigm, eliminating reliance on GANs or CNNs. On the LOL and MEF datasets, CLIP-RL achieves state-of-the-art PSNR and SSIM scores, while attaining 120 FPS inference speed on 1080p images—demonstrating superior balance between enhancement quality and computational efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Enhancing low-light images using CLIP model
• Maintaining efficiency for high-resolution image processing
• Improving image quality with reinforcement learning

Innovation

• CLIP-Utilized Reinforcement Learning for enhancement
• Bézier curve-based global tone adjustment
• Iterative parameter estimation via reinforcement learning