CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

TL;DR

CodeEnhance introduces a novel codebook-driven method for low-light image enhancement, leveraging semantic embedding, adaptive codebook shifting, and interactive feature transformation to improve image quality and robustness against various degradations.

Contribution

It reframes LLIE as an image-to-code learning task using quantized priors, and introduces modules for semantic integration, codebook adaptation, and interactive refinement, which are novel contributions.

Findings

Outperforms existing methods on real-world and synthetic benchmarks.

Demonstrates robustness to noise, uneven illumination, and color distortions.

Provides controllable enhancement based on user preferences.

Abstract

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations; (2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion.