Abstract

The growing interest in immersive technology and lifelike virtual worlds has underscored the importance of creating automated methods to generate characters with a wide range of morphological variations. Traditional methods have either depended heavily on manual effort or simplified the challenge by only addressing static meshes or basic deformation transfers, without supporting dynamic shape morphing with deformation. In this work, we introduce a novel method that leverages cross-parameterization to semi-automate the creation of characters that are not only morphologically varied but also capable of synthesized deformation and animations. The key innovation of our work lies in the parameterization of deforming characters into a hierarchical spherical domain. This domain is methodically constructed to encapsulate the deforming features, ensuring that the hierarchical relationships among these features are preserved within this data structure. This approach takes into account the characteristics of mesh topology, deformation, and animation, thereby reducing parametric distortion, improving the bijectivity of the parameterization process, and ensuring better alignment quality of deforming features. Our alignment algorithm simplifies the process by concentrating on principal joint pairs, making it significantly easier and more intuitive than previous methods that required the manual pinpointing of feature points on meshes. Our method stands out by delivering high-quality outcomes in 3D morphing, texture mapping, character creation, and deformation transfer, marking a significant advancement over recent developments in the field. These results have the potential to significantly decrease the workload associated with asset generation and enhance visual diversity across various domains, including film, animation, virtual societies, and interactive entertainment.

Library of Congress Subject Headings

Morphing (Computer animation); Virtual reality; Parametric modeling; Computer animation--Automation

Publication Date

4-2024

Document Type

Dissertation

Student Type

Graduate

Degree Name

Computing and Information Sciences (Ph.D.)

Department, Program, or Center

Computing and Information Sciences Ph.D, Department of

College

Golisano College of Computing and Information Sciences

Advisor

Chao Peng

Advisor/Committee Member

Joe Geigel

Advisor/Committee Member

David Long

Campus

RIT – Main Campus

Plan Codes

COMPIS-PHD

Download

Share

COinS