Author ORCID Identifier
0009-0009-3182-9296
Document Type
Dissertation
Date of Award
12-31-2024
Degree Name
Doctor of Philosophy in Information Systems - (Ph.D.)
Department
Informatics
First Advisor
Tomer Weiss
Second Advisor
Salam Daher
Third Advisor
Amy K. Hoover
Fourth Advisor
Taro Narahara
Fifth Advisor
Ching-yu Huang
Abstract
Computer Graphics (CG) revolves around virtual content creation using computational methods, spanning applications from games to visual effects. Typically, the creation of CG content is led by expert practitioners who guide computational algorithms towards satisfactory results. Thus, creating CG content often requires manual iterations encompassing algorithm design, parameter tuning, and aesthetic feedback. This work investigates how to leverage crowd-sourcing to streamline such creation processes, focusing on animation and simulation. In animation, a novel crowd-sourcing framework is proposed for combat animation, enabling users to analyze motion similarities, and retrieve matching motions using novel crowd-sourced motion features. Such features enable quantifying previously intractable definitions such as if a motion is entertaining or powerful. Similarly, in simulation, a crowd-sourced Bayesian optimization framework is proposed for creating natural-looking virtual crowds, demonstrating qualitative and quantitative improvements over prior methods. The presentation concludes with a discussion on the limitations of this approach, as well as potential future work.
Recommended Citation
Zhang, Yunhao, "Crowd-sourced learning for computer graphics applications" (2024). Dissertations. 1812.
https://digitalcommons.njit.edu/dissertations/1812
