Anchor then Polish for Low-light Enhancement

TL;DR

This paper introduces an anchor-then-polish framework for low-light image enhancement that decouples global luminance and color correction from local detail refinement, achieving state-of-the-art results.

Contribution

The novel ATP framework separates global energy alignment from local detail polishing, using a simple linear projection for stabilization and wavelet-based refinement for detail enhancement.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Produces visually natural and quantitatively superior enhancements.

Uses a simple scene-adaptive projection matrix with only 12 degrees of freedom.

Abstract

Low-light image enhancement is challenging due to entangled degradations, mainly including poor illumination, color shifts, and texture interference. Existing methods often rely on complex architectures to address these issues jointly but may overfit simple physical constraints, leading to global distortions. This work proposes a novel anchor-then-polish (ATP) framework to fundamentally decouple global energy alignment from local detail refinement. First, macro anchoring is customized to (greatly) stabilize luminance distribution and correct color by learning a scene-adaptive projection matrix with merely 12 degrees of freedom, revealing that a simple linear operator can effectively align global energy. The macro anchoring then reduces the task to micro polishing, which further refines details in the wavelet domain and chrominance space under matrix guidance. A constrained luminance update strategy is designed to ensure global consistency while directing the network to concentrate on fine-grained polishing. Extensive experiments on multiple benchmarks show that our method achieves state-of-the-art performance, producing visually natural and quantitatively superior low-light enhancements.