Abstract
Recently, there have been significant advancements in Image Restoration based on CNN and transformer. However, the inherent characteristics of the Image Restoration task are often overlooked in many works. These works often focus on the basic block design and stack numerous basic blocks to the model, leading to redundant parameters and unnecessary computations and hindering the efficiency of the image restoration. In this paper, we propose a Lightweight Image Restoration network called LIR to efficiently remove degradation (blur, rain, noise, haze, etc.). A key component in LIR is the Efficient Adaptive Attention (EAA) Block, which is mainly composed of Adaptive Filters and Attention Blocks. It is capable of adaptively sharpening contours, removing degradation, and capturing global information in various image restoration scenes in an efficient and computation-friendly manner. In addition, through a simple structural design, LIR addresses the degradations existing in the local and global residual connections that are ignored by modern networks. Extensive experiments demonstrate that our LIR achieves comparable performance to state-of-the-art networks on most benchmarks with fewer parameters and computations. It is worth noting that our LIR produces better visual results than state-of-the-art networks that are more in line with the human aesthetic.
Abstract (translated)
近年来，基于CNN和Transformer的图像修复取得了显著的进展。然而，在许多工作中，图像修复任务的固有特点常常被忽视。这些工作通常关注基本组件设计，并将许多基本组件堆叠到模型中，导致冗余参数和不必要的计算，从而降低了图像修复的效率。在本文中，我们提出了一个轻量级的图像修复网络LIR，以有效地去除降解（模糊，雨，噪声，雾等）。LIR的关键组件是Efficient Adaptive Attention（EAA）块，它主要由自适应滤波器和注意力块组成。它能够动态地锐化轮廓，消除降解，并以有效且计算友好的方式捕捉各种图像修复场景中的全局信息。此外，通过简单的结构设计，LIR解决了现代网络中局部和全局残差连接中存在的降解问题。大量实验证明，我们的LIR在参数和计算量更少的情况下，与最先进的网络在大多数基准测试上的性能相当。值得注意的是，我们的LIR产生的视觉效果优于与人类美学更加贴近的先进网络。
URL
https://arxiv.org/abs/2402.01368
