In this talk, I will introduce the notion of 'canonicalization' and how it can be used to solve 3D computer vision tasks. I will describe Normalized Object Coordinate Space (NOCS), a 3D canonical container that we have developed for 3D estimation, aggregation, and synthesis tasks. I will demonstrate how NOCS allows us to address previously difficult tasks like category-level 6DoF object pose estimation, and correspondence-free multiview 3D shape aggregation. Finally, I will discuss future directions including opportunities to extend NOCS for tasks like articulated and non-rigid shape and pose estimation.
Biography: Srinath Sridhar (https://ai.stanford.edu/~ssrinath) is a postdoctoral researcher at Stanford University working with Leo Guibas. He completed his PhD at the Max Planck Institute for Informatics in Germany where he was advised by Christian Theobalt and Antti Oulasvirta. His research interests are in 3D computer vision and machine learning, specifically focusing on the visual understanding of 3D human physical interactions. He has won several fellowships and awards (e.g., Eurographics Best Paper Honorable Mention) for his work, and has previously spent time at Microsoft Research Redmond and the Honda Research Institute. He will start as an assistant professor of CS at Brown University in Fall 2020.