NCSI: 3D Human Model Animation System Using Deep Pose Retargeting

Status	Completed
Mentor Name	Hao Ji
Mentor's XSEDE Affiliation	Education Allocation
Mentor Has Been in XSEDE Community	4-5 years
Project Title	3D Human Model Animation System Using Deep Pose Retargeting
Summary	Recent progress in deep learning research has catalyzed the development of high-quality pose estimation and 3D object reconstruction. In this project, we plan to leverage deep learning techniques to build a 3d human model animation system, which consists of the following tasks: (1) estimating deep 3D human pose from a sequence of images; (2) creation of personalized 3D avatars; and (3) retargeting deep pose to constructed 3D avatars. The proposed framework will have the great potential to be applied to many domains, including but not limited to, fashion, fitness, education, and entertainment.
Job Description	The students will investigate deep models (i.e,Cascaded Pyramid Network) to estimate 3D human pose from a sequence of images (or video frames), reconstruct 3D human avatars from multiple input images, and retarget deep pose learned from images to the 3D constructed personalized avatar.
Computational Resources	XSEDE Bridges' GPU clusters
Contribution to Community
Position Type	Intern
Training Plan	I will offer a "Deep Learning" course in the spring semester of 2019. This course will further students' knowledge and skills in Machine Learning. During this project, I will work closely with the students and plan to have weekly meetings with them to guide their research progress.
Student Prerequisites/Conditions/Qualifications	Must be an undergraduate at California State Polytechnic University, Pomona Must have good programming skills in Python.
Duration	Semester
Start Date	01/19/2019
End Date	05/10/2019