NCSI: 3D Object Reconstruction from Multi-View RGB-D Data

Status	Completed
Mentor Name	Hao Ji
Mentor's XSEDE Affiliation	Education Allocation
Mentor Has Been in XSEDE Community	4-5 years
Project Title	3D Object Reconstruction from Multi-View RGB-D Data
Summary	Advances in sensor technology have made possible the utilization of commodity RGB-D cameras to generate high-quality 3D models of physical objects required to many applications such as robotics, fabrication, augmented and virtual reality. In this project, we will investigate an accelerated implementation of 3D reconstruction from multi-view RGB-D data, by taking advantage of the power of high-performance computing systems. We are seeking students to be involved in this project who would like to develop an understanding of 3D reconstruction process and practical skills of utilizing high-performance clusters to process RGB-D data.
Job Description	1) The students will capture RGB-D data of physical objects using multiple, synchronized depth sensors in our lab at Cal Poly Pomona, 2) The students will study the algorithms for 3D reconstruction such as pose estimation and depth frame registration, and 3) The students will learn how to use high-performance computing systems for RGB-D data processing.
Computational Resources	XSEDE Bridges GPU Cluster and Bridges Regular Memory Cluster.
Contribution to Community
Position Type	Apprentice
Training Plan	I will teach the students about the algorithms for 3D reconstruction and how to use XSEDE clusters. 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
Duration	Summer
Start Date	05/27/2020
End Date	08/12/2020