Building Virtual Representations of our 3D World
Building Virtual Representations of our 3D World
Ask the Experts
June 21, 2023 | 12-12:30 PM ET
Join MIT Professor Vincent Sitzmann for a virtual discussion on the intersection of robotics, computer vision, and computer graphics, focusing on AI that learns human-like perception. By analyzing a single image, we can create a 3D representation of the environment, incorporating physical properties such as geometry, appearance, materials, motion, lighting, and density. Professor Sitzmann’s research group, the Scene Representation Group, explores these “Neural Scene Representations” to enhance our understanding of and interaction with the world. Moderated by Aude Oliva, lab co-director.
Meet the Expert
Speaker
Vincent Sitzmann, Ph.D., is an assistant professor in the Department of Electrical Engineering and Computer Science at MIT, where he leads the Scene Representation Group. Previously, he was a postdoctoral associate at the MIT Computer Science and Artificial Intelligence Laboratory. His research interest lies in neural scene representations — the way neural networks learn to represent information about our world. The Sitzmann lab will investigate neural scene representations, inverse graphics, neural rendering, and their applications in vision, graphics, robotics, and AI. His goal is for independent agents to reason about our world given only a few visual observations, a task that is simple for humans, but currently impossible for AI. Sitzmann received a PhD in electrical engineering and an MS in computer science from Stanford University, and a BS in electrical engineering from the Technical University of Munich in Germany.