Dr. Srinath Sridhar, Brown University, USA gave a talk on Learning to Generate, Edit, and Arrange 3D Shapes on 13 January.
Here is the summary of the talk in Dr. Sridhar’s words:
In computer vision and robotics, we often need to deal with 3D objects. For instance, we may want to generate instances of 3D chairs, edit the generated chairs using natural language instructions, or arrange them in a canonical orientation. In this talk, I will present some of our work on addressing these problems. First, I will talk about ShapeCrafter, a model for recursively generating and modifying 3D shapes using natural language descriptions. ShapeCrafter generates a 3D shape distribution that gradually evolves as more phrases are added resulting in shapes closer to text instructions. In addition, I will introduce the notions of invariance, equivariance, and ‘canonicalization’, and discuss their importance in 3D understanding. I will describe ConDor, a self-supervised method for canonicalizing the orientation of full and partial 3D shapes. Finally, I will identify future directions including opportunities for expanding 3D understanding to neural fields, articulating objects, and object collections.
Dr. Srinath Sridhar is an assistant professor of Computer Science at Brown University where he leads the Interactive 3D Vision & Learning Lab (IVL). He received his PhD at the Max Planck Institute for Informatics and was subsequently a postdoctoral researcher at Stanford. His research work is in 3D computer vision and machine learning. He is specifically interested in 3D spatiotemporal visual understanding of human physical interactions with the world. He builds methods for human-centric, object-centric, and interaction-centric understanding of our world from videos and images. He is a recipient of the NSF CAREER award, Google Research Scholar award, and his work received the Eurographics Best Paper Honorable Mention. He has previously spent time at Microsoft Research Redmond, and Honda Research Institute.