用深度信息提升暗光图像结构保真度，避免修复后失真。
Geometry-aware Depth-guided Representation Learning for Structure-preserving Low-light Image Enhancement
- 通过反射-几何交互引入深度先验，指导暗光图像表征学习。
- 在多个基准数据集上同时实现亮化与结构保留，优于现有方法。
- 构建了含深度标注的LOL-D数据集，推动几何感知暗光视觉研究。
暗光退化降低图像可见性，并削弱对视觉表征和场景理解至关重要的结构线索。现有暗光图像增强方法主要关注外观恢复，却未能充分利用场景几何以保持结构一致性。为此，本文提出深度引导多尺度注意力网络（DMSA-Net），通过反射-几何交互将深度相关的结构先验融入暗光表征学习。首先采用基于Retinex的分解模块获取光照无关的反射表示，并从中推断深度线索以刻画退化光照下的场景结构。随后，在分层编码器-解码器架构中嵌入多尺度深度引导融合策略，使深度感知注意力自适应融合几何与外观特征。在多个基准数据集上的实验表明，DMSA-Net在实现有效暗光恢复的同时显著提升了结构保真度。此外，我们构建了含深度标注的低光图像数据集LOL-D，以促进几何感知暗光视觉的研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。