8000 GitHub - xianggkl/VLU-Net: Official repository of the CVPR 2025 paper: Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Official repository of the CVPR 2025 paper: Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks.

Notifications You must be signed in to change notification settings

xianggkl/VLU-Net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 

Repository files navigation

Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks

Haijin Zeng*, Xiangming Wang*, Yongyong Chen, Jingyong Su, Jie Liu

Code for CVPR 2025 paper "Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks".

News

Our work has been accepted by CVPR 2025, codes and results are coming soon!

Update: We release the three-task, five-task and single restoration results.

Update: We release the paper in Arxiv: https://arxiv.org/pdf/2503.16930.

Results

For one-by-one IR results

https://drive.google.com/file/d/1Xbq3g15SYGCisPA2TZsx_WEUzhC7MCjL/view?usp=sharing

For all-in-one IR results

NHRBL (five-task): https://drive.google.com/file/d/1vR7PrXGCJTZcAwWQePihcEuozvc8Ggpt/view?usp=sharing

NHR (three-task): https://drive.google.com/file/d/1p9yP80KXmK7kk_6cTINdbqFfrrCcyrZt/view?usp=sharing

About

Official repository of the CVPR 2025 paper: Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0