Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Authors:
Top Cited Papers
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9458-9467
Abstract
Several recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head model, these works require training on a large dataset of images of a single person. However, in many practical scenarios, such personalized talking head models need to be learned from a few image views of a person, potentially even a single image. Here, we present a system with such few-shot capability. It performs lengthy meta-learning on a large dataset of videos, and after that is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators. Crucially, the system is able to initialize the parameters of both the generator and the discriminator in a person-specific way, so that training can be based on just a few images and done quickly, despite the need to tune tens of millions of parameters. We show that such an approach is able to learn highly realistic and personalized talking head models of new people and even portrait paintings.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Bringing portraits to lifeACM Transactions on Graphics, 2017
- VoxCeleb: A Large-Scale Speaker Identification Dataset2017
- Synthesizing ObamaACM Transactions on Graphics, 2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation2016
- Demo of Face2Face2016
- Caffe2014
- The Digital Emily Project: Achieving a Photorealistic Digital ActorIEEE Computer Graphics and Applications, 2010
- A morphable model for the synthesis of 3D faces1999
- View morphing1996