请先看【专栏介绍文章】：【图像去噪（Image Denoising）】关于【图像去噪】专栏的相关说明，包含适配人群、专栏简介、专栏亮点、阅读方法、定价理由、品质承诺、关于更新、去噪概述、文章目录、资料汇总、问题汇总（更新中）
文章目录
- 前言
- Abstract
- 1 Introduction
- 2 Related Work
- 2.1 Traditional Methods
- 2.2 CNNs for Image Restoration
- 2.3 Transformers for Image Restoration
- 3 Method
- 3.1 Kernel Basis Attention Module
- 3.2 Multi-axis Feature Fusion Block
- 3.3 Intergration of MFF Block into U-Net
- 4 Results
- 4.1 Implementation Details
- 4.2 Gaussian Denoising Results
- 4.3 Raw Image Denoising Results
- 4.4 Deraining and Defocus results
- 4.5 Ablation Studies
- 5 Conclusion
前言
论文题目：KBNet: Kernel Basis Network for Image Restoration —— KBNet:图像恢复的核基础网络
论文地址：KBNet: Kernel Basis Network for Image Restoration
论文源码：https://github.com/zhangyi-3/kbnet
基于kernel的图像恢复网络KBNet！SIDD数据集上PSNR/SSIM：40.35/0.972！
Abstract
如何聚合空
