tencentarc / animesr

Real-World Super-Resolution Models for Animation Videos

  • Public
  • 10K runs
  • GitHub
  • Paper
  • License

Input

Output

Run time and cost

This model costs approximately $0.057 to run on Replicate, or 17 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 5 minutes. The predict time for this model varies significantly based on the inputs.

Readme

AnimeSR (NeurIPS 2022)

AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos

arXiv
Yanze Wu, Xintao Wang, Gen Li, Ying Shan
Tencent ARC Lab; Platform Technologies, Tencent Online Video

Acknowledgement

This project is build based on BasicSR.

Citation

If you find this project useful for your research, please consider citing our paper:

@InProceedings{wu2022animesr,
  author={Wu, Yanze and Wang, Xintao and Li, Gen and Shan, Ying},
  title={AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos},
  booktitle={Advances in Neural Information Processing Systems},
  year={2022}
}

:e-mail: Contact

If you have any question, please email yanzewu@tencent.com.