One Shot, One Talk: Whole-body Talking Avatar from a Single Image

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiang, Jun, Guo, Yudong, Hu, Leipeng, Guo, Boyang, Yuan, Yancheng, Zhang, Juyong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929610360356864
author Xiang, Jun
Guo, Yudong
Hu, Leipeng
Guo, Boyang
Yuan, Yancheng
Zhang, Juyong
author_facet Xiang, Jun
Guo, Yudong
Hu, Leipeng
Guo, Boyang
Yuan, Yancheng
Zhang, Juyong
contents Building realistic and animatable avatars still requires minutes of multi-view or monocular self-rotating videos, and most methods lack precise control over gestures and expressions. To push this boundary, we address the challenge of constructing a whole-body talking avatar from a single image. We propose a novel pipeline that tackles two critical issues: 1) complex dynamic modeling and 2) generalization to novel gestures and expressions. To achieve seamless generalization, we leverage recent pose-guided image-to-video diffusion models to generate imperfect video frames as pseudo-labels. To overcome the dynamic modeling challenge posed by inconsistent and noisy pseudo-videos, we introduce a tightly coupled 3DGS-mesh hybrid avatar representation and apply several key regularizations to mitigate inconsistencies caused by imperfect labels. Extensive experiments on diverse subjects demonstrate that our method enables the creation of a photorealistic, precisely animatable, and expressive whole-body talking avatar from just a single image.
format Preprint
id arxiv_https___arxiv_org_abs_2412_01106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle One Shot, One Talk: Whole-body Talking Avatar from a Single Image
Xiang, Jun
Guo, Yudong
Hu, Leipeng
Guo, Boyang
Yuan, Yancheng
Zhang, Juyong
Computer Vision and Pattern Recognition
Graphics
Building realistic and animatable avatars still requires minutes of multi-view or monocular self-rotating videos, and most methods lack precise control over gestures and expressions. To push this boundary, we address the challenge of constructing a whole-body talking avatar from a single image. We propose a novel pipeline that tackles two critical issues: 1) complex dynamic modeling and 2) generalization to novel gestures and expressions. To achieve seamless generalization, we leverage recent pose-guided image-to-video diffusion models to generate imperfect video frames as pseudo-labels. To overcome the dynamic modeling challenge posed by inconsistent and noisy pseudo-videos, we introduce a tightly coupled 3DGS-mesh hybrid avatar representation and apply several key regularizations to mitigate inconsistencies caused by imperfect labels. Extensive experiments on diverse subjects demonstrate that our method enables the creation of a photorealistic, precisely animatable, and expressive whole-body talking avatar from just a single image.
title One Shot, One Talk: Whole-body Talking Avatar from a Single Image
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.01106