Snow Removal in Video:

A New Dataset and A Novel Method

Haoyu Chen, Jingjing Ren, Jinjin Gu, Hongtao Wu, Xuequan Lu, Haoming Cai, Lei Zhu
International Conference on Computer Vision (ICCV), 2023
Left Image Right Image


Snowfall is a common weather phenomenon that can severely affect computer vision tasks by obscuring objects and scenes. However, existing deep learning-based snow removal methods are designed for single images only. In this paper, we target a more complex task – video snow removal, which aims to restore the clear video from the snowy video. To facilitate this task, we propose the first high-quality video dataset, which simulates realistic physical characteristics of snow and haze using a rendering engine and augmentation techniques. We also develop a deep learning framework for video snow removal. Specifically, we propose a snow-query temporal aggregation module and a snow-aware contrastive learning loss function. The module aggregates features between video frames and removes snow effectively, while the loss function helps identify and eliminate snow features. We conduct extensive experiments and demonstrate that our proposed dataset is more realistic than previous datasets, and the models trained on it achieve better performance in real-world snowing images. Our proposed method outperforms state-of-the-art video and image-based methods on both synthetic and real snowy videos.

Realistic Video DeSnowing Dataset

RVSD Download

Train (80 videos)

[Google Drive] [Baidu Netdisk (password: uvmu)]

Test (30 videos)

[Google Drive] [Baidu Netdisk (password: d82f)]

Left Image


    title={Snow Removal in Video: A New Dataset and A Novel Method}, 
    author={Chen, Haoyu and Ren, Jingjing and Gu, Jinjin and Wu, Hongtao and Lu, Xuequan and Cai, Haoming and Zhu, Lei}, 
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},