LUMEN: Low-light Unified Multi-stage Enhancement Network using depth-guided flash, clustering, and attention-based Transformers

TL;DR

LUMEN is a multi-stage low-light image enhancement framework that uses depth estimation, clustering, and attention-based transformers to improve visual quality and detail preservation.

Contribution

It introduces a novel depth-guided multi-stage enhancement method combining virtual flash simulation and transformer-based feature fusion.

Findings

Achieves state-of-the-art performance on LOL-v1 and LOL-v2 benchmarks.

Produces visually natural and detailed enhanced images.

Effectively preserves structural and color fidelity in low-light conditions.

Abstract

Low-light image enhancement remains a challenging problem due to severe noise, color distortion, contrast degradation, and loss of structural details under insufficient illumination. Existing methods typically apply uniform enhancement without considering the depth-dependent nature of light attenuation and sensor noise in real-world scenes. To address this limitation, we propose LUMEN, a multi-stage enhancement framework that integrates virtual flash simulation with transformer-based feature fusion. The proposed framework first estimates scene depth from low-light inputs using a dedicated encoder-decoder network, after which a soft clustering module partitions pixels into depth-aware regions, enabling depth-dependent flash simulation. The simulated flash features, together with depth representations, are fused with image features through efficient attention-based fusion blocks to enhance global context while preserving fine details. A composite loss function combining reconstruction, perceptual, structural, color, edge, and depth consistency objectives ensures both visual fidelity and perceptual quality. Extensive experiments on LOL-v1 and LOL-v2 benchmarks demonstrate that LUMEN achieves state-of-the-art performance and produces visually natural results compared with several state-of-the-art methods.