Keynote Presentations

Tzu-Mao Li, University of California, San Diego

Topic:

Classical Computer Graphics in the Age of Generative AI

Date:

09:40 ~ 10:40, October 14

Abstract:

The rise of end-to-end data-driven approaches such as deep learning and generative AI has cast doubt on classical graphics approaches built on explicit, carefully engineered algorithms. In this talk, I will argue that these classical techniques will remain to be fundamental components of visual computing pipelines, and will further be the main driving force towards addressing issues with controllability, interpretability, efficiency, and data scarcity. I will use our recent works as examples to show that insights from classical methods can be used as principled loss functions that provide guarantees for data-driven methods, as preconditioners that accelerate optimization, and as forward models for challenging inverse problems. These examples illustrate how classical techniques can both be adapted to combine with data-driven methods, or can be used standalone when there is not enough data. Finally, I will share some thoughts on the state of the field and a path forward.

Bio:

Tzu-Mao Li is an assistant professor at the CSE department of University of California, San Diego. He is a member of the Center for Visual Computing at UCSD. His research 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. His Ph.D. thesis "Differentiable Visual Computing" has received the ACM SIGGRAPH 2020 Outstanding Doctoral Dissertation Award. He also received the NSF CAREER Award in 2023.

Young Min Kim, Seoul National University

Topic:

Taming 2D foundation models for 3D tasks

Date:

09:10 ~ 10:20, October 16

Abstract:

After the introduction of foundation models around 2020, we are witnessing many advancements of AI beyond supervised learning, especially in languages, images, and videos. However, the sea of data to train such models often struggles to grasp structural or contextual reasoning in some problems. While there are still ongoing advances to develop 3D foundation models, I would like to share what we have observed to tackle 3D tasks using 2D foundation models. They are surprisingly effective in extracting semantics from rendered 3D assets, while it requires significant effort to deduce fine-grained spatial contexts. While the optimal representation might be yet to be found, geometric knowledge can complement powerful foundation models and guide us to understand the structure of the world.

Bio:

Young Min Kim is an Associate Professor in the Department of Electrical and Computer Engineering at Seoul National University, Seoul, Korea, where she is leading a 3D vision lab. She received a B.S. from Seoul National University in 2006 and an M.S. and Ph.D. in electrical engineering from Stanford University in 2008 and 2013, respectively. Before joining SNU, she was a Senior Research Scientist at the Korea Institute of Science and Technology (KIST). Her research interest lies in 3D vision, where she combines computer vision, graphics, and robotics algorithms to solve practical problems. She serves as an area chair in CVPR, ICCV, ACCV, program committee for Pacific Graphics, AAAI, and technical papers committee for SIGGRAPH Asia. She is also a program chair for 3DV 2026.

Kunwoo Lee, DGIST

Topic:

Bridging Theory and Practice: Prof. Kunwoo Lee's Contribution to CAD and Digital Engineering

Date:

13:30 ~ 14:30, October 16

Abstract:

This Lifetime Achievement Award lecture reflects on over four decades of Professor Kunwoo Lee’s contributions to CAD, computer graphics, and digital engineering. The journey began with early research on hierarchical assembly modeling and automatic assembling procedure generation, advancing CAD systems beyond simple geometry to capture complex relationships. Subsequent work is on extending conventional CAD system for human-centered design, including parametric human body modeling and biomedical applications, demonstrating the direct societal impact of engineering research. More recent efforts focus on extending CAD for 3D printing, enabling internal structural optimization and fully integrated solid-and-void designs. Alongside research, contributions to education, textbooks, knowledge sharing, and industrial applications have fostered collaboration, interdisciplinary growth, and global recognition for Asian researchers. The lecture concludes with reflections on the importance of collaboration, teaching, and human-centered research, and offers guidance to young researchers on curiosity, resilience, interdisciplinarity, and societal impact in the evolving landscape of digital design and engineering.

Bio:

Kunwoo Lee is a president of DGIST (Daegu Gyeongbuk Institute of Science and Technology) in Korea. He received his BS (1978) from Seoul National University, and MS (1981) and PhD (1984) in mechanical engineering from MIT. He has been the Co-Editor-in-Chief of Computer-Aided Design of Elsevier from 2004 to 2014, and an editor in chief of the Journal of Computational Design and Engineering of Oxford Press since 2014. He has been the founding president of Advanced Institute of Convergence Technology of Seoul National University from 2004 to 2009, the Dean of the College of Engineering of Seoul National University from 2013 to 2017, the founding Dean of the Graduate School of Engineering Practice of Seoul National University from 2016 to 2017, and a Vice President of the National Academy of Engineering of Korea from 2015 to 2020. Currently, he is a member of The Korean Academy of Science and Technology and a fellow of the American Society of Mechanical Engineers. He was the president of the Korean Society of Mechanical Engineers in 2013 and the Korean Society for Engineering Education from 2017 to 2018.

His research interests include CAD system supporting multi-resolution modeling, custom tailoring systems for shoes and wigs, dental CAD system, 3D printers, and integrated framework called human-centered CAD system in which products can be designed based on simultaneous simulation of products and human operator. His research is so practical that he established two start-ups, one in Korea and the other in US.

He is the author of the book, “Principles of CAD/CAM/CAE Systems”, published by Addison-Wesley in 1999. It has been an exceedingly popular textbook and more than 10,000 copies have been sold. His papers and patents were cited 7,354 times.