Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Samsung’s research center at Moscow has developed a new AI that can create talking avatars of photos and paintings without using any 3D modeling.
Paper 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.
Discover, Learn and Evaluate AI Companies and Solutions
Save content to your library
Save case studies, articles, blog posts and more. Curate your research library with content directly from AI companies.
Login with LinkedIn Login with Twitter
LATEST | POPULAR
JEDAI PRODUCT SUITE
Anagog provides a solution suite that offers to mobile app owners the most cost-effective, end-to-end, customer engagement solution.
DEMAND FORECASTING
Experience the leading AI demand forecasting platform.
SPELL - HYPERPARAMETER SEARCHES
Optimize hyperparameters to improve the accuracy of your model with the Spell Hyper command
SPELL - JUPYTER NOTEBOOK SERVER - GPU POWERED
Collaborative Jupyter Notebook or JupyterLab workspace server with powerful GPUs
SPELL - DEEP LEARNING PLATFORM
The fastest and most powerful end-to-end platform for machine learning and deep learning.
1 Comment
rosdi ab latiff Organization Identity ROSDIABLATIFF01 Personal program system, organization Identity
Leave A Comment