中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Data-driven facial animation via semi-supervised local patch alignment

文献类型:期刊论文

作者Zhang, Jian; Yu, Jun; You, Jane; Tao, Dapeng; Li, Na; Cheng, Jun
刊名PATTERN RECOGNITION
出版日期2016
英文摘要This paper reports a novel data-driven facial animation technique which drives a neutral source face to get the expressive target face using a semi-supervised local patch alignment framework. We define the localpatch and assume that there exists a linear transformation between a patch of the target face and the intrinsic embedding of the corresponding patch of the source face. Based on this assumption, we compute the intrinsic embeddings of source patches and align these embeddings to form the result. During the course of alignment, we use a set of motion data as shape regularizer to impel the result to approach the unknown target face. The intrinsic embedding can be computed through both locally linear embedding andlocal tangent space alignment. Experimental results indicate that the proposed framework can obtain decent face driving results. Quantitative and qualitative evaluations of the proposed framework demonstrate its superiority to existing methods.
收录类别SCI
原文出处http://www.sciencedirect.com/science/article/pii/S0031320316000923
语种英语
源URL[http://ir.siat.ac.cn:8080/handle/172644/9914]  
专题深圳先进技术研究院_集成所
作者单位PATTERN RECOGNITION
推荐引用方式
GB/T 7714
Zhang, Jian,Yu, Jun,You, Jane,et al. Data-driven facial animation via semi-supervised local patch alignment[J]. PATTERN RECOGNITION,2016.
APA Zhang, Jian,Yu, Jun,You, Jane,Tao, Dapeng,Li, Na,&Cheng, Jun.(2016).Data-driven facial animation via semi-supervised local patch alignment.PATTERN RECOGNITION.
MLA Zhang, Jian,et al."Data-driven facial animation via semi-supervised local patch alignment".PATTERN RECOGNITION (2016).

入库方式: OAI收割

来源:深圳先进技术研究院

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。