Turning images into an interactive world
https://shenlong.web.illinois.edu/
COM2 Level 4
Executive Classroom, COM2-04-02
Abstract:
Our group's goal is to build a world simulator from visual observations that can answer "what-if" questions. Toward this goal, we develop various methods to understand the world from images and harness both physical simulation and generative models to create new visual experiences. In today’s talk, we will focus on creating physical, photorealistic, and immersive experiences that allow users and agents to interact with images, videos, and 3D worlds captured from the real world. We will cover applications in content creation, autonomy, and agriculture. Finally, I will provide a brief personal outlook on open research topics that make all images and videos interactive.
Bio:
Shenlong Wang is an Assistant Professor in the Department of Computer Science at the University of Illinois Urbana-Champaign, specializing in computer vision and robotics. His recent research focuses on creating a digital replica of the world and simulating realistic new content to train and validate autonomous agents. Shenlong’s past work received IROS Best Application Paper Runner-Up and CVPR Best Paper Candidate. His contributions to autonomy and simulation have led to 25 filed patents. Shenlong has received the NSF CAREER Award, Amazon Research Award, and various fellowships from Facebook, Adobe, and the Royal Bank of Canada. He regularly serves as an area chair for conferences in computer vision, robotics, and machine learning.