CodeFormer

Preview：

Introduce：

CodeFormer is a Transformer based predictive network for picture Mosaic recovery. By learning discrete codebooks and decoders, it can reduce the uncertainty of recovery mapping and generate high-quality faces. It has excellent anti-degradation robustness and is suitable for both synthetic and real data sets.

Stakeholders:
Picture Mosaic removal
The features of the tool:

• Learn discrete codebooks and decoders
• Global face composition modeling
• Controllable feature transformation

Tool’s Tabs: Face recovery, discrete codebook