/RestoreFormer

[CVPR 2022] RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs

Primary LanguagePythonApache License 2.0Apache-2.0

We have merged the code of RestoreFormer into our journal version, RestoreFormer++. Please feel free to access the resources from https://github.com/wzhouxiff/RestoreFormerPlusPlus

Updating

  • 20230915 Update an online demo Huggingface Gradio
  • 20230915 A more user-friendly and comprehensive inference method refer to our RestoreFormer++
  • 20230116 For convenience, we further upload the test datasets, including CelebA (both HQ and LQ data), LFW-Test, CelebChild-Test, and Webphoto-Test, to OneDrive and BaiduYun.
  • 20221003 We provide the link of the test datasets.
  • 20220924 We add the code for metrics in scripts/metrics.