IPAB Seminar-27/8/24 Title: Audience-aware Computer Graphics Speaker: Tzu-Mao Li Abstract: Modern computer graphics is capable of producing images and animations that are almost indistinguishable from real footage. However, rarely do our graphics pipelines account for how the images and animations are perceived by the audience. For example, how do we generate non-photorealistic drawings that can be perceived to have certain 3D properties? How do we generate animations that can elicit emotion from the viewers? I will talk about our recent work (collaboration with Kartik Chandra, Josh Tenenbaum, Jonathan Ragan-Kelley) on augmenting graphics pipelines with the capability of optimizing for the viewers' perception. Our key idea is to model the perception of the audience as Bayesian inference, and optimize the scene or animation to lead to desired inference results. We will show two examples where we apply this idea: generating optical illusion using "inverse inverse rendering" and generating animation with story using "inverse inverse planning". Bio: Tzu-Mao Li is an assistant professor at the CSE department of UCSD, working with awesome people at the Center for Visual Computing. He explores the connections between visual computing algorithms and modern data-driven methods and develops programming languages and systems for facilitating the exploration. He did a 2-year postdoc with Jonathan Ragan-Kelley at both MIT CSAIL and UC Berkeley. He did his Ph.D. in the computer graphics group at MIT CSAIL, advised by Frédo Durand. He received his B.S. and M.S. degrees in computer science and information engineering from National Taiwan University in 2011 and 2013, respectively, where he worked with Yung-Yu Chuang at the Communication and Multimedia Lab. He received the ACM SIGGRAPH 2020 Outstanding Doctoral Dissertation Award and the NSF CAREER Award. Aug 27 2024 11.00 - 12.00 IPAB Seminar-27/8/24 Tzu-Mao Li G.07
IPAB Seminar-27/8/24 Title: Audience-aware Computer Graphics Speaker: Tzu-Mao Li Abstract: Modern computer graphics is capable of producing images and animations that are almost indistinguishable from real footage. However, rarely do our graphics pipelines account for how the images and animations are perceived by the audience. For example, how do we generate non-photorealistic drawings that can be perceived to have certain 3D properties? How do we generate animations that can elicit emotion from the viewers? I will talk about our recent work (collaboration with Kartik Chandra, Josh Tenenbaum, Jonathan Ragan-Kelley) on augmenting graphics pipelines with the capability of optimizing for the viewers' perception. Our key idea is to model the perception of the audience as Bayesian inference, and optimize the scene or animation to lead to desired inference results. We will show two examples where we apply this idea: generating optical illusion using "inverse inverse rendering" and generating animation with story using "inverse inverse planning". Bio: Tzu-Mao Li is an assistant professor at the CSE department of UCSD, working with awesome people at the Center for Visual Computing. He explores the connections between visual computing algorithms and modern data-driven methods and develops programming languages and systems for facilitating the exploration. He did a 2-year postdoc with Jonathan Ragan-Kelley at both MIT CSAIL and UC Berkeley. He did his Ph.D. in the computer graphics group at MIT CSAIL, advised by Frédo Durand. He received his B.S. and M.S. degrees in computer science and information engineering from National Taiwan University in 2011 and 2013, respectively, where he worked with Yung-Yu Chuang at the Communication and Multimedia Lab. He received the ACM SIGGRAPH 2020 Outstanding Doctoral Dissertation Award and the NSF CAREER Award. Aug 27 2024 11.00 - 12.00 IPAB Seminar-27/8/24 Tzu-Mao Li G.07
