A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution

This work is based on PFNL by Yi et al. This is the TensorFlow version, and PyTorch version will be available.

Datasets

We have selected MM522 dataset for training and collected another 20 sequences for evaluation, and in consider of copyright, the datasets should only be used for study.

The datasets can be downloaded from Google Drive and Baidu Drive, train and eval,test,checkpoint (password: pr7p).

Note that the training dataset provides Ground Truth images and Bicubic downsampling LR images, while the eval (password: pr7p) dataset provides Gaussian blur and downsampling images. Thus, please refer to ./model/base_model.py for generating Gaussian blur and downsampling images from Ground Truth images.

Unzip the training dataset to ./data/train/ and evaluation dataset to ./data/val/ .

Environment

• Python (Tested on 3.6)
• Tensorflow (Tested on 1.12.0)

Citation

If you find our code or datasets helpful, please consider citing our related works. ``` @ARTICLE{MSHPFNL, author={Yi, Peng and Wang, Zhongyuan and Jiang, Kui and Jiang, Junjun and Lu, Tao and Ma, Jiayi}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, title={A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution}, year={2020}, volume={}, number={}, pages={}, doi={10.1109/TPAMI.2020.3042298} }

@inproceedings{PFNL, title={Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations}, author={Yi, Peng and Wang, Zhongyuan and Jiang, Kui and Jiang, Junjun and Ma, Jiayi}, booktitle={IEEE International Conference on Computer Vision (ICCV)}, pages={3106-3115}, year={2019}, } ```

Contact

If you have questions or suggestions, please open an issue here or send an email to [email protected]

Issues

About PyTorch version

opened on 2022-06-28 07:01:35 by Koubunnkei

您好，想问一下大约什么时候可以公布PyTorch版本的代码。谢谢

Results in MSU Video Super Resolution Benchmark

opened on 2021-07-16 13:01:29 by Kirillova-Anastasia

Hello, MSU Graphics & Media Lab Video Group has recently launched Video Super Resolution Benchmark. We provide a comprehensive comparison of a variety of different VSR models. You can see our current results: MSU VSR Benchmark. If you are interested in participating, you can add your algorithm, following the submission steps. You can read about MSU Graphics & Media Lab Video Group here and here.

Codes for discriminator

opened on 2021-05-29 19:24:13 by pjwang317

Hello, Thanks for your great work. Can you provide the codes for the discriminator and the training process of the GAN?

from model.base_model import VSR ModuleNotFoundError: No module named 'model.base_model'

opened on 2021-03-03 05:20:03 by hiredd

from model.base_model import VSR ModuleNotFoundError: No module named 'model.base_model'