【图像去噪】论文精读:CVPR 2025 | DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables

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 works
    • 2.1. Color Image denoising
    • 2.2. Replacing CNN with LUT
  • 3. Method
    • 3.1. Preliminary
    • 3.2. Overview
    • 3.3. Pairwise Channel Mixer
    • 3.4. Rotation Non-overlapping Kernel
    • 3.5. PCM Plug-in Module
  • 4. Experiments
    • 4.1. Implementation details
    • 4.2. Gaussian Color Image denoising
    • 4.3. Real-world Color Image denoising
    • 4.4. Quantitative results
    • 4.5. Qualitative results
    • 4.6. Efficiency Evaluation
    • 4.7. Effectiveness of Plug-in PCM
    • 4.8. Ablation study
      • 4.8.1. Channel-spatial-wise convolution
      • 4.8.2. L-shaped convolution
  • 5. Conclusion


前言

论文题目:DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables —— DnLUT:基于通道感知查找表的超高效彩色图像去噪

论文地址:DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables

论文源码:https://github.com/Stephen0808/DnLUT

CVPR 2025!

Abstra

你可能感兴趣的:(图像去噪,深度学习,计算机视觉,人工智能,图像处理,论文阅读,论文笔记)