.png){kind=icon}
.png){kind=icon}
Return
An entity based multi-direction cooperative deformation algorithm for generating personalized human shape
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-018-5711-4.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Personalized human shape plays an important role in system of virtual garment customization. In this paper, a new entity based multi-direction cooperative deformation algorithm (MDCD) is proposed to generate personalized human shape. We primarily extract the description parameters of entities using different direction sections based on unified division method. By introducing the entity curve interpolation and correspondence between elementary and target entities, the generated distortion of various human entities from simulated deformation function will be avoided. With the good capacity of accuracy and reusability of human entities, the MDCD algorithm can greatly improve the generation efficiency of personalized human shapes. The elementary entities on template model are firstly located using the division method of Poser, and description parameters on entities are then extracted based on the entity direction. Thus, shape characteristics can be represented by a set of direction curves on different angles by entity curve interpolation. Subsequently shape characteristics on personalized human body are generated by a comparison of direction curves of template and target entities. Finally, the MDCD algorithm is applied for generating personalized entities and shapes. Experiments show that compared with the existed algorithms, personalized human shapes generated by our method are smoother and more similar to the template model.
Keywords:
Personalized human shape
Human entities
Multi-direction cooperative deformation
Entity curve interpolation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W