Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancement

TL;DR

This paper introduces a zero-reference low-light image enhancement method that leverages CLIP's visual-linguistic prior and prompt learning to improve image quality and task performance without requiring paired normal-light data.

Contribution

It proposes a novel approach combining prompt learning and CLIP semantic guidance for zero-reference low-light enhancement, enhancing image quality and downstream task performance.

Findings

Improves image contrast and reduces over-enhancement.

Enhances task-based performance across multiple datasets.

Outperforms state-of-the-art low-light enhancement methods.

Abstract

Currently, low-light conditions present a significant challenge for machine cognition. In this paper, rather than optimizing models by assuming that human and machine cognition are correlated, we use zero-reference low-light enhancement to improve the performance of downstream task models. We propose to improve the zero-reference low-light enhancement method by leveraging the rich visual-linguistic CLIP prior without any need for paired or unpaired normal-light data, which is laborious and difficult to collect. We propose a simple but effective strategy to learn prompts that help guide the enhancement method and experimentally show that the prompts learned without any need for normal-light data improve image contrast, reduce over-enhancement, and reduce noise over-amplification. Next, we propose to reuse the CLIP model for semantic guidance via zero-shot open vocabulary classification to optimize low-light enhancement for task-based performance rather than human visual perception. We conduct extensive experimental results showing that the proposed method leads to consistent improvements across various datasets regarding task-based performance and compare our method against state-of-the-art methods, showing favorable results across various low-light datasets.