Anchor then Polish for Low-light Enhancement

2026-03-16

AI Summary

This work addresses the challenge of global distortion and detail recovery in low-light image enhancement, where insufficient illumination, color shift, and texture interference are intricately coupled. To tackle this, we propose the Anchor-then-Polish (ATP) framework, which decouples the task into two stages: macro-level anchoring followed by micro-level refinement. First, a 12-degree-of-freedom scene-adaptive linear projection matrix stabilizes global brightness and corrects color globally. Subsequently, local detail enhancement is performed in the wavelet domain and chrominance space. A constrained brightness update strategy is introduced to preserve global consistency throughout the process. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance across multiple benchmarks, delivering both visually natural results and superior quantitative metrics.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Local Search
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Privacy-enhancing technologies
• Responsible Web: Data and user privacy-enhancing technologies for the Web

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.

Problem

• low-light enhancement
• illumination
• color shifts
• texture interference
• image degradation

Innovation

• anchor-then-polish
• global energy alignment
• scene-adaptive projection
• wavelet domain refinement
• low-light enhancement