CS SEMINAR

Deep learning for 3D geometry and shape manipulation

Speaker
Dr. Weiyue Wang, Waymo (Software Engineer at Waymo Perception)
Chaired by
Dr LEE Gim Hee, Associate Professor, School of Computing
leegh@comp.nus.edu.sg

01 Apr 2021 Thursday, 10:00 AM to 11:00 AM

via Zoom

Abstract:
Applications in virtual and augmented reality and robotics require rapid creation and access to a large number of 3D models. To represent 3D shapes, many of these methods utilize either voxels or point clouds due to ease of encoding them in a neural network. However, such representations are often limited in terms of resolution. This talk will focus on 3D triangle mesh and signed distance field, which are more flexible and widely used in the computer graphic community, and the deep learning methods on these representations.


Biodata:
Weiyue Wang is a software engineer at Waymo Perception. Before that, she was a Ph.D. student at University of Southern California, working in Computer Graphics and Immersive Technologies Lab under Prof. Ulrich Neumann. Her research focuses on computer vision, particularly 3D scene understanding and reconstruction.