Joint Face Completion and Super-resolution using Multi-scale Feature Relation Learning

no code implementations • 29 Feb 2020 • Zhilei Liu, Yunpeng Wu, Le Li, Cuicui Zhang, Baoyuan Wu

This paper proposes a multi-scale feature graph generative adversarial network (MFG-GAN) to implement the face restoration of images in which both degradation modes coexist, and also to repair images with a single type of degradation.

Facial Inpainting Generative Adversarial Network +2

Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection

no code implementations • 23 Oct 2019 • Zhilei Liu, Jiahui Dong, Cuicui Zhang, Longbiao Wang, Jianwu Dang

Most existing AU detection works considering AU relationships are relying on probabilistic graphical models with manually extracted features.

Action Unit Detection Facial Action Unit Detection +1

Facial Expression Restoration Based on Improved Graph Convolutional Networks

no code implementations • 23 Oct 2019 • Zhilei Liu, Le Li, Yunpeng Wu, Cuicui Zhang

Facial expression analysis in the wild is challenging when the facial image is with low resolution or partial occlusion.

Generative Adversarial Network Super-Resolution