Video-Driven Animation of Neural Head Avatars
No Thumbnail Available
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present a new approach for video-driven animation of high-quality neural 3D head models, addressing the challenge of person-independent animation from video input. Typically, high-quality generative models are learned for specific individuals from multi-view video footage, resulting in person-specific latent representations that drive the generation process. In order to achieve person-independent animation from video input, we introduce an LSTM-based animation network capable of translating person-independent expression features into personalized animation parameters of person-specific 3D head models. Our approach combines the advantages of personalized head models (high quality and realism) with the convenience of video-driven animation employing multi-person facial performance capture.We demonstrate the effectiveness of our approach on synthesized animations with high quality based on different source videos as well as an ablation study.
Description
CCS Concepts: Computing methodologies -> Machine learning; Computer graphics; Animation; Rendering
@inproceedings{10.2312:vmv.20231237,
booktitle = {Vision, Modeling, and Visualization},
editor = {Guthe, Michael and Grosch, Thorsten},
title = {{Video-Driven Animation of Neural Head Avatars}},
author = {Paier, Wolfgang and Hinzer, Paul and Hilsmann, Anna and Eisert, Peter},
year = {2023},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-232-5},
DOI = {10.2312/vmv.20231237}
}