Geometry-Contrastive GAN for Facial Expression Transfer.

By Fengchun Qiao, Naiming Yao, Zirui Jiao, Zhihao Li, Hui Chen, Hongan Wang. 2018

55 citations recorded by the source corpus.

In this paper, we propose a Geometry-Contrastive Generative Adversarial Network (GC-GAN) for transferring continuous emotions across different subjects. Given an input face with certain emotion and a target facial expression from another subject, GC-GAN can generate an identity-preserving face with the target expression. Geometry information is introduced into cGANs as continuous conditions to guide the generation of facial expressions. In order to handle the misalignment across different subjects or emotions, contrastive learning is used to transform geometry manifold into an embedded semantic manifold of facial expressions. Therefore, the embedded geometry is injected into the latent space of GANs and control the emotion generation effectively. Experimental results demonstrate that our proposed method can be applied in facial expression transfer even there exist big differences in facial shapes and expressions between different subjects.

Subfields: Computer Vision and Pattern Recognition, Neurology, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Neurology

In Generative Models

Citations in the corpus

Cross-Modal Contrastive Learning for Text-to-Image Generation (2021, background): “It has been explored under several adversarial training scenarios [25, 65, 9, 41].”
A survey on face data augmentation for the training of deep neural networks (2019, methodology): “On the other side, the GAN-based methods can be further divided into four categories according to the generative condition of expression generation: reference images [11, 167], emotion or expression codes [29, 152], action unit labels [109, 110] and geometry [111, 127, 144].”