InterLight: Leveraging Intrinsic Illumination Priors for Low-Light Image Enhancement

TL;DR

InterLight introduces a novel low-light image enhancement framework that leverages intrinsic illumination priors and physics-guided augmentation to improve detail, contrast, and color fidelity in dark images.

Contribution

The paper proposes a new method that systematically exploits intrinsic illumination priors and scene-aware prompts for more effective low-light image enhancement.

Findings

Achieves clearer textures and better visual coherence.

Outperforms existing methods on multiple benchmarks.

Utilizes physics-guided augmentation and illumination-aware prompts.

Abstract

Low-Light Image Enhancement (LLIE) has long been a challenging problem in low-level vision, as insufficient illumination often leads to low contrast, detail loss, and noise. Recent studies show that deep learning-based Retinex theory can effectively decouple illumination and reflectance. However, existing methods frequently suffer from over-enhancement or color distortion, and often assume uniform noise or ideal lighting. To address these limitations, we propose InterLight, a novel framework that systematically excavates and operationalizes intrinsic illumination priors for LLIE.Our core insight is that robust enhancement requires not just estimating illumination, but constructing an illumination-aware pipeline. We first inject sensor-level illumination-response priors via physics-guided augmentation, then represent the degradation through adaptive prompts conditioned on the scene's latent illumination state. This explicit representation directly guides a luminance-gated intrinsic memory mechanism to selectively compensate for information loss, prioritizing reconstruction in dark regions while preserving fidelity in bright ones. Finally, the entire process is regularized by a self-supervised consistency objective that distills illumination-invariant features. By deeply exploiting intrinsic illumination priors, our method achieves clearer textures and more visually coherent enhancement results. Extensive experiments across multiple benchmarks demonstrate the effectiveness of our approach. Code is available at: https://github.com/House-yuyu/InterLight.