Robotics Institute Seminar Series 2021-2022

Upcoming & Recent Seminars

Angela Dai: Learning from Synthetic 3D Priors for Real-World 3D Perception

Abstract: Understanding the 3D structure of real-world environments is a fundamental challenge in machine perception, with many applications towards robotic navigation and interaction, content creation, and mixed reality scenarios. In this talk, we propose to leverage structural and object priors from large-scale synthetic shape datasets to form a basis for understanding object structures from commodity RGB and RGB-D sensors. We demonstrate the effectiveness of synthetic 3D shapes as a basis for object reconstruction from single RGB images, followed by learnable 3D part-based priors that enable test-time optimization to fit accurately to real observations while preserving holistic scene consistency. These will enable the construction of intuitive, semantic primitives for future virtual or real-world interaction or manipulation of real environments.

Bio: Angela Dai is an Assistant Professor at the Technical University of Munich where she leads the 3D AI group. Prof. Dai's research focuses on understanding how the 3D world around us can be modeled and semantically understood. Previously, she received her PhD in computer science from Stanford in 2018 and her BSE in computer science from Princeton in 2013. Her research has been recognized through a ZDB Junior Research Group Award, an ACM SIGGRAPH Outstanding Doctoral Dissertation Honorable Mention, as well as a Stanford Graduate Fellowship.

Past Seminars

image (5)

© 2020 Faculty of Applied Science & Engineering