论文标题
线性阵列网络用于低光图像增强
Linear Array Network for Low-light Image Enhancement
论文作者
论文摘要
基于卷积神经网络（CNN）方法由于其出色的性能而占据了低光图像增强任务。但是，卷积操作基于局部滑动窗口机构，该机构很难构建特征图的远程依赖关系。同时，基于自我注意力的全球关系聚集方法已被广泛用于计算机视觉中，但是由于高计算复杂性，这些方法很难处理高分辨率图像。为了解决这个问题，本文提出了线性阵列自我注意（LASA）机制，该机制仅使用两个2-D特征编码来构建3-D全局权重，然后优化卷积层生成的特征图。基于LASA，提出了线性阵列网络（LAN），它优于RGB和RAW基于RAW的低光增强任务中现有的最新方法（SOTA）方法，具有较小的参数。该代码在https://github.com/cuiziteng/lasa_enhancement中发布。
Convolution neural networks (CNNs) based methods have dominated the low-light image enhancement tasks due to their outstanding performance. However, the convolution operation is based on a local sliding window mechanism, which is difficult to construct the long-range dependencies of the feature maps. Meanwhile, the self-attention based global relationship aggregation methods have been widely used in computer vision, but these methods are difficult to handle high-resolution images because of the high computational complexity. To solve this problem, this paper proposes a Linear Array Self-attention (LASA) mechanism, which uses only two 2-D feature encodings to construct 3-D global weights and then refines feature maps generated by convolution layers. Based on LASA, Linear Array Network (LAN) is proposed, which is superior to the existing state-of-the-art (SOTA) methods in both RGB and RAW based low-light enhancement tasks with a smaller amount of parameters. The code is released in https://github.com/cuiziteng/LASA_enhancement.
