Home

Awesome

<div align="center"> <h1> SemiVDN </h1> <h2>Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization</h2> </div> <p align="center">Hongtao Wu, Yijun Yang, Angelica Aviles-Rivero, Jingjing Ren, Sixiang Chen, Haoyu Chen, Lei Zhu<sup>:email:</sup></p> <p align="center"> <!-- <a href="https://github.com/TonyHongtaoWu/SemiVDN">ArXivPreprint</a> --> </p>

Realsnow85 Dataset

https://private-user-images.githubusercontent.com/141260395/366072004-ebbf91e4-80bb-48d3-9184-21521d81763e.mp4

Our Realsnow85 dataset can be downloaded here. Wait a few seconds for loading videos.

Our Results

<div align="center"> <img src="./figures/Img1.png" > </div>

Synthetic visual results

https://private-user-images.githubusercontent.com/141260395/366064880-4222f10a-1a39-4a45-9a4a-b5e5def10aa9.mp4

MethodsVDNSemiVDN
Synthetic DatasetLinkLink

Real-world visual results

image

https://private-user-images.githubusercontent.com/141260395/366066317-bc897d7e-eb6d-46a0-b49f-7fa7b79cafdc.mp4