3D Asset Generation: Generating Action Primitives

Students: Nathalie Chang, Yuqin Jiao | Advisor: Kris Kitani, Xiaoxuan Ma

Students

Nathalie Chang

Nathalie Chang is a graduate student in the Master of Science in Computer Vision program at Carnegie Mellon University. She received her Bachelor’s degree in Computer Science from the National Tsing Hua University. Prior to CMU, she worked as a research assistant at the Multimedia Technology Laboratory in Academia Sinica. Her research interests lie in 3D/4D reconstruction and generation. In this project, she is focusing on the non-rigging 4D reconstruction method.

Yuqin Jiao

Yuqin Jiao is a graduate student in the Master of Science in Computer Vision program at Carnegie Mellon University, with a background in Architecture and a Graduate Certificate in Applied Data Science from UC Berkeley. Her expertise spans computer vision, 3D reconstruction, and machine learning, with experience in VLMs and model training. In this project, she focuses on the rigging pipeline, including interactive skeleton editing and rig generation.

Advisors

Prof. Kris M. Kitani

Kris Kitani is an Associate Research Professor at the Robotics Institute, Carnegie Mellon University, and Co-Director of the Extended Reality Technology Center (XRTC). His research spans computer vision, human activity forecasting, first-person vision, inverse reinforcement learning, and assistive technologies for people with visual impairment. In this project, he advises on 3D reconstruction, motion generation, and interactive rigging pipelines for animatable character generation from monocular video.

Dr. Xiaoxuan Ma

Xiaoxuan Ma is a postdoctoral researcher at Carnegie Mellon University in the Robotics Institute advised by Prof. Kris Kitani. Prior to that, she received her Ph.D., M.S., and B.S. degrees in Computer Science from Peking University. Her research interests lie in 3D computer vision, with a focus on perceiving and understanding the dynamic 3D world.