Journal of Frontiers of Computer Science and Technology ›› 2024, Vol. 18 ›› Issue (3): 718-730.DOI: 10.3778/j.issn.1673-9418.2301050

• Graphics·Image • Previous Articles     Next Articles

Lightweight Cross-Gating Transformer for Image Restoration and Enhancement#br# #br#

XUE Jinqiang, WU Qin   

  1. 1. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, China
    2. Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Wuxi, Jiangsu 214122, China
  • Online:2024-03-01 Published:2024-03-01

面向图像复原和增强的轻量级交叉门控Transformer

薛金强,吴秦   

  1. 1. 江南大学 人工智能与计算机学院,江苏 无锡 214122
    2. 江苏省模式识别与计算智能工程实验室,江苏 无锡 214122

Abstract: Recent image restoration and image enhancement methods are difficult to balance the robustness of multiple subtasks with the small number of parameters and computational costs. To solve this problem, this paper proposes a lightweight cross-gating transformer (CGT) for efficient image restoration task. On the one hand, this paper summarizes the limitations of traditional global self-attention mechanism to capture global dependencies, and improves the global self-attention mechanism to a cross-level cross-gating self-attention mechanism. Meanwhile, a lightweight feed-forward neural network is proposed to learn cross-level local dependencies at a very small computational cost and reconstruct clear features in the adjacent locality. On the other hand, in view of the defect that the traditional method of adding or concatenating encoder and decoder equally leads to information interference, a long-distance reset update module is proposed to suppress and update useless information and clear features respectively. This paper conducts extensive quantitative experiments and is compared with 25 state-of-the-art methods on 9 datasets for image denoising, image deraining and low-light image enhancement, respectively. Experimental results prove that the proposed lightweight cross-gating transformer achieves high peak signal-to-noise ratio and structural similarity in image restoration and image enhancement tasks with a small number of parameters and computation, and reconstructs clear images close to real-world scenes, achieving state-of-the-art image restoration performance.

Key words: image restoration, image enhancement, deep learning, Transformer, lightweight, feature fusion

摘要: 现有的图像复原和图像增强方法难以同时兼顾在多个子任务上的鲁棒性和维持较小的参数量与计算代价。针对这一问题,提出轻量级交叉门控转换算法(CGT)。一方面,总结了传统全局自注意力机制捕获全局依赖关系的局限性,将全局自注意力机制改进为跨层次交叉门控自注意力机制。同时提出轻量化的前馈神经网络,从而以极小的计算代价学习到跨层次局部依赖关系,在局部邻域内重构清晰特征。另一方面,针对传统方法对编码器和解码器平等地进行加法或拼接的操作易导致信息干扰这一缺陷,提出长距离重置更新模块,分别对无用信息与清晰特征加以抑制和更新。在图像去噪、图像去雨和低亮度图像增强3个不同任务的9个公开数据集上,与最新的25个方法进行的对比实验结果表明,所提出的轻量级交叉门控转换模型以较少的参数量和计算代价,在图像复原和图像增强领域中均取得较高的峰值信噪比和结构相似度,重构出接近真实世界场景的清晰图像,达到了先进的图像复原性能。

关键词: 图像复原, 图像增强, 深度学习, Transformer, 轻量化, 特征融合