Diffusion-based Human Motion Style Transfer with Semantic Guidance
文献类型：期刊论文
| 作者 | Hu, Lei1,2; Zhang, Zihao1; Ye, Yongjing1; Xu, Yiwen1,2; Xia, Shihong1,2 |
| 刊名 | COMPUTER GRAPHICS FORUM
 |
| 出版日期 | 2024-10-09 |
| 页码 | 12 |
| 关键词 | |
| ISSN号 | 0167-7055 |
| DOI | 10.1111/cgf.15169 |
| 英文摘要 | 3D Human motion style transfer is a fundamental problem in computer graphic and animation processing. Existing AdaIN-based methods necessitate datasets with balanced style distribution and content/style labels to train the clustered latent space. However, we may encounter a single unseen style example in practical scenarios, but not in sufficient quantity to constitute a style cluster for AdaIN-based methods. Therefore, in this paper, we propose a novel two-stage framework for few-shot style transfer learning based on the diffusion model. Specifically, in the first stage, we pre-train a diffusion-based text-to-motion model as a generative prior so that it can cope with various content motion inputs. In the second stage, based on the single style example, we fine-tune the pre-trained diffusion model in a few-shot manner to make it capable of style transfer. The key idea is regarding the reverse process of diffusion as a motion-style translation process since the motion styles can be viewed as special motion variations. During the fine-tuning for style transfer, a simple yet effective semantic-guided style transfer loss coordinated with style example reconstruction loss is introduced to supervise the style transfer in CLIP semantic space. The qualitative and quantitative evaluations demonstrate that our method can achieve state-of-the-art performance and has practical applications. The source code is available at https://github.com/hlcdyy/diffusion-based-motion-style-transfer. |
| 资助项目 | National Key R&D Program of China[2022YFB3303202] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001331462300001 |
| 出版者 | WILEY |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/39523]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Xia, Shihong |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Hu, Lei,Zhang, Zihao,Ye, Yongjing,et al. Diffusion-based Human Motion Style Transfer with Semantic Guidance[J]. COMPUTER GRAPHICS FORUM,2024:12. |
| APA | Hu, Lei,Zhang, Zihao,Ye, Yongjing,Xu, Yiwen,&Xia, Shihong.(2024).Diffusion-based Human Motion Style Transfer with Semantic Guidance.COMPUTER GRAPHICS FORUM,12. |
| MLA | Hu, Lei,et al."Diffusion-based Human Motion Style Transfer with Semantic Guidance".COMPUTER GRAPHICS FORUM (2024):12. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。