Machine Learning and Friends Lunch (Online)

Title: "Learning 3D Shape Structure and Semantics"

Abstract: Humans accomplish everyday tasks by perceiving, modeling, and interacting with a wide range of 3D objects, with diverse geometry, rich semantics, and complicated structures. One fundamental goal of computational visual perception is to equip intelligent agents with similar capabilities to understand the 3D world. In this talk, I will introduce my research on learning complicated structures and actionable semantics of 3D shapes, which can benefit various downstream applications in computer graphics, vision, and robotics, including shape part segmentation, shape generation, shape editing, robotic part assembly, and robotic manipulation.

Bio: Kaichun Mo is a sixth-year and final-year Ph.D. Student in Computer Science at Stanford University, advised by Prof. Leonidas Guibas. Before that, he received his BS.E. degree from the ACM Honored Class at Shanghai Jiao Tong University. His research interests focus on understanding 3D shape structure and semantics for various applications in 3D vision, graphics, and robotic manipulation. He has interned at Adobe Research, Autodesk Research (AI Lab), and Facebook AI Research. He has published papers at CVPR, ICCV, ECCV, NeurIPS, ICLR, Siggraph Asia, AAAI, CoRL.

To obtain the Zoom link for this event, please see the event announcements from MLFL on the college email lists or contact Kalpesh Krishna.