Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |