Semantic and Generative Deep Learning of 3D Object Shapes
4:15pm - 5:15pm
ZOOM Meeting ID: 967 9359 9681 Passcode: 281682


Geometric deep learning is among the new trend of technologies that can model and learn from non-Euclidean data such as point clouds; it has recently been successfully used in data-driven solutions of 3D surface reconstruction, 3D semantic analysis, robotic manipulation, etc. In this talk, we introduce our recent progress along this line, including an analytic meshing technique that can exactly recover the surfaces from deep implicit networks, and sparse steerable convolution that enables efficient SE(3)-equivariant convolutions. We then introduce how these techniques can be used for robotic manipulation/grasping, autonomous driving, and other applications. We discuss the future potentials and challenges therein.

ZOOM Meeting ID: 967 9359 9681 Passcode: 281682
Recommended For
Faculty and staff, PG students, UG students
Speakers / Performers:
Prof. Kui JIA
South China University of Technology
Systems Hub, HKUST(GZ)
Science & Technology
Post an event
Campus organizations are invited to add their events to the calendar.