Creative AI: Perceptual Data-Guided Computational Design
With the increasing amount of 3D data captured from the real world and human perceptual data that can be obtained from virtual reality, it becomes highly promising to devise data-driven computational design approaches for creating highly immersive 3D virtual environments, as well as "functional" 3D models that can be 3D-printed and used for real-world purposes. In this talk, I will discuss the recent progress of our group in data-driven computational design, including automatic interior design, architectural design, zoomorphic furniture design, and the design of reconfigurable objects and dissections puzzles. I will conclude my talk by discussing some interesting problems in computer graphics, vision, cognitive science and robotics along this direction.
Craig Yu is an assistant professor at the University of Massachusetts Boston. His research interests are in computer graphics, vision and virtual reality, particularly in devising data-driven optimization approaches for designing 3D models and virtual environments. He obtained his PhD degree in Computer Science from UCLA in 2013, where he received the Outstanding Recognition in Research. He was a visiting scientist at MIT and a visiting scholar at Stanford University. He is a recipient of the Cisco Outstanding Graduate Research Award, the Award of Excellence from Microsoft Research and the UCLA Dissertation Year Fellowship. His research has been published in top graphics and vision venues, including SIGGRAPH, SIGGRRAPH Asia, ICCV and CVPR; was awarded the Best Paper Honorable Mention in 3DV 2016; and has been featured in New Scientist, the UCLA Headlines, the UCLA Mathematics Newsletter and newspapers internationally. His lab is supported by the NSF.