Geometry-aware Depth-guided Representation Learning for Structure-preserving Low-light Image Enhancement
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new method called DMSA-Net to make dark images look clearer while keeping their shapes and details accurate. They use information about depth (how far things are) to help improve the image, not just brighten it. Their approach combines brightness correction with depth clues through a special network that pays attention to both light and structure in the image. They also made a new dataset with dark pictures that include depth information to help others study this problem.
low-light image enhancementdepth-guided attentionRetinex decompositionmulti-scale fusionstructural preservationreflectancescene geometryencoder-decoder networkimage restorationdepth dataset
Authors
Fang Gao, Jiongkai Qin, Jiabao Wang, Jingfeng Tang, Ming Cheng, Hanbo Zheng, Qingbao Huang, Cheng Wu
Abstract
Low-light degradation reduces image visibility and weakens structural cues that are important for visual representation and scene understanding. Existing low-light image enhancement methods mainly focus on appearance restoration, while insufficiently exploiting scene geometry to preserve structural consistency. To address this limitation, this paper proposes a Depth-guided Multi-scale Attention Network (DMSA-Net) for geometry-aware low-light image enhancement. DMSA-Net introduces depth-related structural priors into low-light representation learning through reflectance-geometry interaction. A Retinex-based decomposition module is first used to obtain illumination-invariant reflectance representations, from which depth cues are inferred to characterize scene structure under degraded illumination. A multi-scale depth-guided fusion strategy is then embedded into a hierarchical encoder-decoder architecture, where depth-aware attention adaptively integrates geometric and appearance features. Experiments on several benchmark datasets show that DMSA-Net achieves effective low-light restoration while improving structural preservation. Moreover, we construct LOL-D, a depth-augmented low-light dataset, to facilitate research on geometry-aware low-light vision.