8000 GitHub - wmpscc/Face_Frontalization: Simple and Efficient Practices for Profile-to-Frontal Face Synthesis and Recognition
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Simple and Efficient Practices for Profile-to-Frontal Face Synthesis and Recognition

Notifications You must be signed in to change notification settings

wmpscc/Face_Frontalization

Repository files navigation

Face Frontalization

This is official Pytorch implementation for the paper "Simple and Efficient Practices for Profile-to-frontal Face Synthesis and Recognition" by Huijiao Wang, Haijian Zhang and Xulei Yang.

The target is to provide three simple but efficient practices to CR-GAN when synthesising a frontal face image from a profile.

The following is the visual comparison results with TP-GAN.

Visual Comparison results with TP-GAN

More details please pay attention to our paper "Simple and Efficient Practices for Profile-to-frontal Face Synthesis and Recognition" which is under review at IJCNN 2021.

Acknowledgement

A large part of the code is borrowed from CR-GAN.

About

Simple and Efficient Practices for Profile-to-Frontal Face Synthesis and Recognition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0