ShanghaiTech University Knowledge Management System
| LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation | |
| 2023-10-06 | |
| Source Publication | 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
 |
| ISSN | 1550-5499 |
| Status | 已发表 |
| DOI | 10.1109/ICCV51070.2023.01902 |
| Abstract | Gestures are non-verbal but important behaviors accompanying people’s speech. While previous methods are able to generate speech rhythm-synchronized gestures, the semantic context of the speech is generally lacking in the gesticulations. Although semantic gestures do not occur very regularly in human speech, they are indeed the key for the audience to understand the speech context in a more immersive environment. Hence, we introduce LivelySpeaker, a framework that realizes semantics-aware co-speech gesture generation and offers several control handles. In particular, our method decouples the task into two stages: script-based gesture generation and audio-guided rhythm refinement. Specifically, the script-based gesture generation leverages the pre-trained CLIP text embeddings as the guidance for generating gestures that are highly semantically aligned with the script. Then, we devise a simple but effective diffusion-based gesture generation backbone simply using pure MLPs, that is conditioned on only audio signals and learns to gesticulate with realistic motions. We utilize such powerful prior to rhyme the script-guided gestures with the audio signals, notably in a zero-shot setting. Our novel two-stage generation framework also enables several applications, such as changing the gesticulation style, editing the co-speech gestures via textual prompting, and controlling the semantic awareness and rhythm alignment with guided diffusion. Extensive experiments demonstrate the advantages of the proposed framework over competing methods. In addition, our core diffusion-based generative model also achieves state-of-the-art performance on two benchmarks. The code and model will be released to facilitate future research. |
| Keyword | Interpolation Computer vision Codes Semantics Benchmark testing Rhythm Generators |
| Conference Place | Paris, France |
| Conference Date | 1-6 Oct. 2023 |
| URL | 查看原文 |
| Source Data | IEEE |
| Citation statistics | |
| Document Type | 会议论文 |
| Identifier | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354918 |
| Collection | 信息科学与技术学院_硕士生 信息科学与技术学院_PI研究组_高盛华组 |
| Affiliation | 1.ShanghaiTech University 2.Tencent AI Lab 3.Intellindust 4.INRIA |
| First Author Affilication | ShanghaiTech University |
| First Signature Affilication | ShanghaiTech University |
| Recommended Citation GB/T 7714 | Yihao Zhi,Xiaodong Cun,Xuelin Chen,et al. LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation[C],2023. |
| Files in This Item: | Download All | |||||
| File Name/Size | DocType | Version | Access | License | ||
Edit Comment
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.