Computer Science Seminar
Date: Thursday, 21 December 2023
Time: 02:00 PM
Venue: Lecture Hall 202
Learning to See the World in 3D
Ayush Tewari
MIT, USA.
21-12-23

---

Abstract

Looking at a single image is sufficient for us to build rich mental representations that enable reasoning about scene geometry, materials, dynamics, and more. Inferring such representations of the world from little information is a core aspect of human intelligence. It helps us understand and interact with our surroundings and with each other. My research aims to build similar computational models -- methods that can perceive the rich 3D structured world from sparse observations such as images and videos. I will discuss the main challenges in this 3D perception problem and how my research addresses them. I will focus on my research on using 3D generative models to discover structured representations of the world from 2D data.

About the speaker: Ayush Tewari is a postdoctoral researcher at MIT CSAIL with Bill Freeman, Josh Tenenbaum, and Vincent Sitzmann. He had previously completed his Ph.D. at the Max Planck Institute for Infcormatics with Christian Theobalt. You can find more about his research on his webpage https://ayushtewari.com/.