/MMNet

video denoising

Primary LanguagePython

Multiframe to Multiframe Network for Video Denoising

This project is implemented using Pytorch and tested on V1.4.0

dataset:

download from: Vimeo-90K (https://github.com/anchen1011/toflow) and CVRD( https://mega.nz/file/Hx8TgLQY#0MoZSqdrQ_HgIc4OP6_jmwAwupNctPc7ZilXLV_FAQ0 )

Testing:

Test with a list of video: python test.py

Test with a single video: python test_on_one_sequence.py

Undated Training and Pretrained model:

https://pan.baidu.com/s/1Fkf4-XVtRn9VLNViEg73aQ?pwd=uswu key: uswu ===> python train.py

References:

[1] T. Xue, B. Chen, J. Wu, D. Wei, and W. T. Freeman, “Video enhancement with task-oriented flow,” Int. J. Comput. Vis., vol. 127, no. 8, pp.1106–1125, 2019.

[2] H. Yue, C. Cao, L. Liao, R. Chu, and J. Yang, “Supervised raw video denoising with a benchmark dataset on dynamic scenes,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., June 2020, pp. 2298–2307.