ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement

2026-05-25

AI Summary

Existing low-light image enhancement methods are often constrained by limited training data and narrow optimization objectives, struggling to achieve both controllability and generalization in real-world scenarios. To address this, this work introduces the first large-scale real-world low-light image dataset annotated with continuous illumination intensity levels and proposes a continuously adjustable enhancement framework. By leveraging continuous illumination supervision and a misalignment-aware weighted flow-matching loss, the method enables flexible user control over enhancement intensity while preserving structural consistency and visual realism. Extensive experiments demonstrate that the proposed approach significantly outperforms state-of-the-art techniques across multiple metrics, exhibiting superior continuous controllability and robust generalization in complex real-world conditions.

Abstract

Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome these limitations, we propose ControlLight, a controllable, consistent, and generalizable framework for low-light enhancement. We first construct a large-scale dataset of real-world degraded images with continuous illumination-strength supervision. To further ensure consistent outputs under different control strengths, we introduce a misalignment-aware weighted flow matching loss that preserves image structure across continuous enhancement strengths. ControlLight allows users to edit real-world degraded low-light images toward satisfactory enhancement results by flexibly controlling the strength while preserving visual consistency and realism. Extensive experiments show that ControlLight achieves state-of-the-art performance against existing low-light enhancement approaches while demonstrating strong continuous controllability and generalization to real-world scenarios.

Problem

• low-light enhancement
• controllability
• generalization
• real-world applications

Innovation

• controllable enhancement
• continuous illumination supervision
• misalignment-aware loss
• low-light image enhancement
• generalizable framework