Low-light image enhancement using dual cross attention

Abstract

Low-light image enhancement (LLIE) aims to improve the perceptibility and interpretability of images captured in poorly illuminated environments. Existing LLIE methods often fail to capture the local self-similarity and long-range dependencies at the same time, causing the loss of complementary information between multiple modules or network layers, ultimately resulting in the loss of image details. To alleviate this issue, we design a hierarchical mutual Enhancement via a dual cross-attention transformer (ECAFormer), which introduces an architecture that enables concurrent propagation and interaction of multiple disentangling features. To capture the local self-similarity, we design a Dual Multi-head Self-Attention (DMSA), which leverages the disentangled visual and semantic features across different scales, allowing them to guide and complement each other. Further, a cross-scale DMSA block is incorporated to capture residual connections, thereby integrating cross-layer information and capturing the long-range dependencies. Experimental results show that the ECAFormer reaches competitive performance across multiple benchmarks, yielding nearly a 3.7% improvement in Peak Signal-to-Noise Ratio (PSNR) over the suboptimal method, demonstrating the effectiveness of information interaction in LLIE. For facilitating the efforts to replicate our results, our implementation is available on GitHub¹