FastTalker：实时音频驱动的三维高斯说话脸生成

IF 4.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Image and Vision Computing Pub Date : 2025-05-04 DOI:10.1016/j.imavis.2025.105573

Keliang Chen , Zongze Li , Fang Cui , Mao Ni , Shaoying Wang , Junlin Che , Feng Liu , Yonggang Qi , Fangwei Zhang , Jun Liu , Gan Guo , Rongrong Fu , Yunxia Huang

{"title":"FastTalker：实时音频驱动的三维高斯说话脸生成","authors":"Keliang Chen , Zongze Li , Fang Cui , Mao Ni , Shaoying Wang , Junlin Che , Feng Liu , Yonggang Qi , Fangwei Zhang , Jun Liu , Gan Guo , Rongrong Fu , Yunxia Huang","doi":"10.1016/j.imavis.2025.105573","DOIUrl":null,"url":null,"abstract":"<div><div>The performance of 3D talking head generation has shown significant im- provement over the past few years. Nevertheless, real-time rendering remains a challenge that needs to be overcome. To address this issue, we present the FastTalker framework, which uses 3D Gaussian Splatting (3DGS) for talking head generation. This method introduces an audio-driven Dynamic Neural Skinning (DNS) approach to facilitate flexible and high-fidelity talking head video generation. It first employs an adaptive FLAME mesh for sampling to obtain the initialized 3DGS. Then, Neural Skinning Networks (DNS) are used to account for the appearance changes of 3DGS. Finally, a pre-trained Audio Motion Net is utilized to model facial movements as the final dynamic driving facial signal. Experimental results demonstrate that FastTalker of- fers a rendering speed exceeding 100 FPS, making it the fastest audio-driven talking head generation method in terms of inference efficiency.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"159 ","pages":"Article 105573"},"PeriodicalIF":4.2000,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FastTalker: Real-time audio-driven talking face generation with 3D Gaussian\",\"authors\":\"Keliang Chen , Zongze Li , Fang Cui , Mao Ni , Shaoying Wang , Junlin Che , Feng Liu , Yonggang Qi , Fangwei Zhang , Jun Liu , Gan Guo , Rongrong Fu , Yunxia Huang\",\"doi\":\"10.1016/j.imavis.2025.105573\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The performance of 3D talking head generation has shown significant im- provement over the past few years. Nevertheless, real-time rendering remains a challenge that needs to be overcome. To address this issue, we present the FastTalker framework, which uses 3D Gaussian Splatting (3DGS) for talking head generation. This method introduces an audio-driven Dynamic Neural Skinning (DNS) approach to facilitate flexible and high-fidelity talking head video generation. It first employs an adaptive FLAME mesh for sampling to obtain the initialized 3DGS. Then, Neural Skinning Networks (DNS) are used to account for the appearance changes of 3DGS. Finally, a pre-trained Audio Motion Net is utilized to model facial movements as the final dynamic driving facial signal. Experimental results demonstrate that FastTalker of- fers a rendering speed exceeding 100 FPS, making it the fastest audio-driven talking head generation method in terms of inference efficiency.</div></div>\",\"PeriodicalId\":50374,\"journal\":{\"name\":\"Image and Vision Computing\",\"volume\":\"159 \",\"pages\":\"Article 105573\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2025-05-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Image and Vision Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0262885625001611\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Image and Vision Computing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0262885625001611","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

摘要

在过去的几年里，3D说话头一代的性能有了显著的提高。然而，实时渲染仍然是一个需要克服的挑战。为了解决这个问题，我们提出了FastTalker框架，它使用3D高斯飞溅（3DGS）来生成说话头。该方法引入了一种音频驱动的动态神经蒙皮（DNS）方法，以实现灵活、高保真的说话头视频生成。首先采用自适应FLAME网格进行采样，得到初始化的3DGS。然后，使用神经皮肤网络（DNS）来解释3DGS的外观变化。最后，利用预训练的音频运动网络对面部运动进行建模，作为最终的动态驱动面部信号。实验结果表明，FastTalker的渲染速度超过100 FPS，在推理效率方面是最快的音频驱动谈话头生成方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

FastTalker: Real-time audio-driven talking face generation with 3D Gaussian

查看原文本刊更多论文

FastTalker: Real-time audio-driven talking face generation with 3D Gaussian

The performance of 3D talking head generation has shown significant im- provement over the past few years. Nevertheless, real-time rendering remains a challenge that needs to be overcome. To address this issue, we present the FastTalker framework, which uses 3D Gaussian Splatting (3DGS) for talking head generation. This method introduces an audio-driven Dynamic Neural Skinning (DNS) approach to facilitate flexible and high-fidelity talking head video generation. It first employs an adaptive FLAME mesh for sampling to obtain the initialized 3DGS. Then, Neural Skinning Networks (DNS) are used to account for the appearance changes of 3DGS. Finally, a pre-trained Audio Motion Net is utilized to model facial movements as the final dynamic driving facial signal. Experimental results demonstrate that FastTalker of- fers a rendering speed exceeding 100 FPS, making it the fastest audio-driven talking head generation method in terms of inference efficiency.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Image and Vision Computing 工程技术-工程：电子与电气

CiteScore

8.50

自引率

8.50%

发文量

143

审稿时长

7.8 months

期刊介绍： Image and Vision Computing has as a primary aim the provision of an effective medium of interchange for the results of high quality theoretical and applied research fundamental to all aspects of image interpretation and computer vision. The journal publishes work that proposes new image interpretation and computer vision methodology or addresses the application of such methods to real world scenes. It seeks to strengthen a deeper understanding in the discipline by encouraging the quantitative comparison and performance evaluation of the proposed methodology. The coverage includes: image interpretation, scene modelling, object recognition and tracking, shape analysis, monitoring and surveillance, active vision and robotic systems, SLAM, biologically-inspired computer vision, motion analysis, stereo vision, document image understanding, character and handwritten text recognition, face and gesture recognition, biometrics, vision-based human-computer interaction, human activity and behavior understanding, data fusion from multiple sensor inputs, image databases.