Lishen Qu的博客
首页
News
Github
友情链接
往期整理
  •   历史归档
  •   文章分类
  •   文章标签
Lishen Qu
文章
7
分类
3
标签
4
首页
News
Github
友情链接
往期整理
历史归档
文章分类
文章标签
学术研究
📄ECCV 2024
发布于: 2024-11-19
最后更新: 2025-5-7
次查看
论文
type
status
date
slug
summary
tags
category
icon
password

Abstract

How to explore useful features from images as prompts to guide the deep image restoration models is an effective way to solve image restoration. In contrast to mining spatial relations within images as prompt, which leads to characteristics of different frequencies being neglected and further remaining subtle or undetectable artifacts in the restored image, we develop a Frequency Prompting image restoration method, dubbed FPro, which can effectively provide prompt components from a frequency perspective to guild the restoration model address these differences. Specifically, we first decompose input features into separate frequency parts via dynamically learned filters, where we introduce a gating mechanism for suppressing the less informative elements within the kernels. To propagate useful frequency information as prompt, we then propose a dual prompt block, consisting of a low-frequency prompt modulator (LPM) and a high-frequency prompt modulator (HPM), to handle signals from different bands respectively. Each modulator contains a generation process to incorporate prompting components into the extracted frequency maps, and a modulation part that modifies the prompt feature with the guidance of the decoder features. Experimental results on commonly used benchmarks have demonstrated the favorable performance of our pipeline against SOTA methods on 5 image restoration tasks, including deraining, deraindrop, demoiréing, deblurring, and dehazing.

Paper

arxiv.org
https://arxiv.org/pdf/2404.00288

Code

GitHub - joshyZhou/FPro: Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration
Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration - joshyZhou/FPro
GitHub - joshyZhou/FPro: Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration
https://github.com/joshyZhou/FPro
GitHub - joshyZhou/FPro: Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration
 
  • 作者:Lishen Qu
  • 链接:https://qulishen.top/article/FPro
  • 声明:本文采用 CC BY-NC-SA 4.0 许可协议,转载请注明出处。
相关文章
CVPR 2025 Highlight
Burst Image Restoration
Ubuntu 18.04 LTS 升级到 20.04 LTSCVPR 2025 Highlight
Loading...
目录
0%
AbstractPaperCode
Lishen Qu
Lishen Qu
代码承愿
文章
7
分类
3
标签
4
最新发布
CVPR 2025 Highlight
CVPR 2025 Highlight
2025-5-7
ECCV 2024
ECCV 2024
2025-5-7
Ubuntu 18.04 LTS 升级到 20.04 LTS
Ubuntu 18.04 LTS 升级到 20.04 LTS
2025-4-5
Burst Image Restoration
Burst Image Restoration
2024-12-17
奇异值分解
奇异值分解
2024-12-17
Leetcode-3164
Leetcode-3164
2024-11-19
公告
😀 A papers was accepted and selected as highlight in CVPR 2025.
 
目录
0%
AbstractPaperCode
2021-2025Lishen Qu.

Lishen Qu的博客 | 代码承愿

Powered byNotionNext 4.7.9.