中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Latent inversion for consistent identity preservation in character animation

文献类型：期刊论文

作者Li, Haochen1,2; Tang, Sheng1,2; Wan, Zhang1,2; Cao, Juan1,2; Li, Jintao1,2
刊名VISUAL COMPUTER
出版日期2025-05-22
页码14
关键词Diffusion model Character animation Human dance generation DDIM inversion
ISSN号0178-2789
DOI10.1007/s00371-025-03956-z
英文摘要This paper presents InvLatents, a novel framework for character animation that leverages latent inversion diffusion models to ensure consistent identity preservation across frames. Existing diffusion-based character animation methods often struggle with maintaining identity consistency due to the inherent randomness in the generation process. To address this issue, InvLatents introduces a latent inversion technique that incorporates target identity and pose guidance into the inference stage. By controlling different injection ratios in different branches, the method obtains richer identity information from the reference image. Additionally, a lightweight pose integration module is introduced to compensate for potential missing pose guidance. Experimental results on the TikTok dataset demonstrate that InvLatents achieves competitive performance compared to state-of-the-art approaches, effectively maintaining both identity and pose consistency without requiring additional training. The proposed method can be integrated as a plugin into other diffusion models, offering a promising solution for generating temporally coherent motion videos with consistent identity. Project page: https://github.com/SodaLee/InvLatents.
资助项目Beijing Science and Technology Plan Project[Z231100005923033]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001492947600001
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/42405]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Tang, Sheng
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Li, Haochen,Tang, Sheng,Wan, Zhang,et al. Latent inversion for consistent identity preservation in character animation[J]. VISUAL COMPUTER,2025:14.
APA Li, Haochen,Tang, Sheng,Wan, Zhang,Cao, Juan,&Li, Jintao.(2025).Latent inversion for consistent identity preservation in character animation.VISUAL COMPUTER,14.
MLA Li, Haochen,et al."Latent inversion for consistent identity preservation in character animation".VISUAL COMPUTER (2025):14.

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。