MCATD: Multi-Scale Contextual Attention Transformer Diffusion for Unsupervised Low-Light Image Enhancement

作者：Cheng Da, Yongsheng Qian, Junwei Zeng, Xuting Wei, Futao Zhang · 发表于：IEEE Access · 年份：2025 · DOI：10.1109/access.2025.3573171 · 被引用次数：7 · 研究领域：Computer Science

Low-light image enhancement (LLIE) remains a challenging task due to the complex degradation patterns in images captured under insufficient illumination, including non-linear intensity mappings, spatially-varying noise distributions, and content-dependent color distortions. Despite significant advances, existing methods struggle with three fundamental challenges: 1) difficulty in simultaneously preserving structural details while reducing noise, 2) limited generalization across diverse lighting conditions and scene types, and 3) computational inefficiency when processing complex natural scenes. While recent diffusion-based methods have shown promise, they often struggle with generalization and require paired training data. We propose MCATD, a novel unsupervised framework that integrates adaptive sampling, multi-scale feature extraction, and dynamic enhancement capabilities into diffusion models for LLIE. The framework consists of three key components: 1) a Dynamic Adaptive Diffusion Sampling (DADS) strategy that adjusts sampling steps based on image complexity, 2) a Multi-scale Contextual Attention Transformer (MCAT) network that captures features at different scales with attention mechanisms, and 3) a Multi-scale Dynamic Structure-Preserving (MDSP) loss that preserves image structure while optimizing perceptual quality. Experimental results on multiple benchmarks demonstrate that our method outperforms state-of-the-art unsupervised approaches and achieves comparable performa...