[Project Page]
Learning To Have An Ear For Face Super-ResolutionThis repository contains demo code of our CVPR2020 paper.
Training and evaluation on VoxCeleb is coming soon!
Requirements
The code is based on Python 3.7 and tensorflow 1.13.
How to use it
1. Setup
- Download the checkpoints from https://drive.google.com/drive/folders/1YSXktBv0xZxdo41H_cNV8fzku2CdBZBK?usp=sharing
- Run test.py to test the method on images and audio tracks from test_data directory.