Saved in:
Bibliographic Details
Main Authors: Li, Renda, Qi, Xiaohua, Ling, Qiang, Yu, Jun, Chen, Ziyi, Chang, Peng, Xiao, Mei HanJing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.08344
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917982540660736
author Li, Renda
Qi, Xiaohua
Ling, Qiang
Yu, Jun
Chen, Ziyi
Chang, Peng
Xiao, Mei HanJing
author_facet Li, Renda
Qi, Xiaohua
Ling, Qiang
Yu, Jun
Chen, Ziyi
Chang, Peng
Xiao, Mei HanJing
contents Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions and gestures remains challenging in gesture-to-video systems. In order to improve the generation effect, previous works adopted complex input and training strategies and required a large amount of data sets for pre-training, which brought inconvenience to practical applications. We propose a simple one-stage training method and a temporal inference method based on a diffusion model to synthesize realistic and continuous gesture videos without the need for additional training of temporal modules.The entire model makes use of existing pre-trained weights, and only a few thousand frames of data are needed for each character at a time to complete fine-tuning. Built upon the video generator, we introduce a new audio-to-video pipeline to synthesize co-speech videos, using 2D human skeleton as the intermediate motion representation. Our experiments show that our method outperforms existing GAN-based and diffusion-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08344
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion Model
Li, Renda
Qi, Xiaohua
Ling, Qiang
Yu, Jun
Chen, Ziyi
Chang, Peng
Xiao, Mei HanJing
Computer Vision and Pattern Recognition
Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions and gestures remains challenging in gesture-to-video systems. In order to improve the generation effect, previous works adopted complex input and training strategies and required a large amount of data sets for pre-training, which brought inconvenience to practical applications. We propose a simple one-stage training method and a temporal inference method based on a diffusion model to synthesize realistic and continuous gesture videos without the need for additional training of temporal modules.The entire model makes use of existing pre-trained weights, and only a few thousand frames of data are needed for each character at a time to complete fine-tuning. Built upon the video generator, we introduce a new audio-to-video pipeline to synthesize co-speech videos, using 2D human skeleton as the intermediate motion representation. Our experiments show that our method outperforms existing GAN-based and diffusion-based methods.
title EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.08344