Topic: Computer Graphics in the AI Age

Speaker: Prof. Baoquan Chen, Peking University

Host: Prof. Baoyuan Wu, Associate Professor, School of Data Science, CUHK-Shenzhen

Date: Wednesday, May 22, 2024

Time: 10:00 a.m. - 11:00 a.m.

Venue: Room 101, Teaching Complex C

Language: English
 

嘉 宾 简 介 
Speaker Profile

陈宝权教授
Prof. Baoquan Chen

北京大学
Peking University

陈宝权，北京大学教授，智能学院副院长。陈宝权教授的研究领域涵盖计算机图形学、三维视觉、可视化以及人机交互。他已在国际期刊和会议上发表了200余篇学术论文，其中超过60篇发表于计算机图形学领域的顶级期刊《ACM Transactions on Graphics》（TOG）。陈教授在多个享有盛誉的会议上获得了最佳论文奖，包括2023年SIGGRAPH Asia、2023年SIGGRAPH（荣誉提名）和2005年IEEE Visualization。陈教授曾担任《ACM Transactions on Graphics》和《IEEE Transactions on Visualization and Graphics》副编辑，ACM SIGGRAPH Asia和IEEE VIS会议指导委员会成员，SIGGRAPH Asia 2014和IEEE Visualization 2005的会议主席，以及可视化和计算机图形学领域众多会议的程序主席或委员会成员。

陈教授曾担任北京电影学院未来影像高精尖创新中心的首席科学家（2016-2021年），目前担任北京大学艺术学院的客座教授。他曾获得2003年美国国家科学基金会杰出青年学者奖（NSF CAREER Award）、2004年明尼苏达大学（双城）McKnight学者奖，以及2014年中国计算机图形学大会杰出奖。陈教授持有清华大学电子工程硕士学位和纽约州立大学石溪分校计算机科学博士学位。因其在空间数据可视化领域的贡献，陈教授于2020年当选为IEEE Fellow，并分别于2021年和2024年入选IEEE Visualization Academy和ACM SIGGRAPH Academy。

Baoquan Chen is a Professor of Peking University, where he is associate dean of the School of Artificial Intelligence. His research interests generally lie in computer graphics, 3D vision, visualization, and human-computer interaction. He has published 200+ papers in international journals and conferences, including 60+ papers in ACM Transactions on Graphics (TOG), and won several best paper awards in prestigious conferences, including SIGGRAPH Asia 2023, SIGGRAPH 2023 (Honorary Mention), and IEEE Visualization 2005. Chen has served as associate editor of ACM Transactions on Graphics and IEEE Transactions on Visualization and Graphics, conference steering committee member of ACM SIGGRAPH Asia and IEEE VIS, conference chair of SIGGRAPH Asia 2014 and IEEE Visualization 2005, as well as program chair/committee member of numerous conferences in the visualization and computer graphics fields.

Chen served as the Chief Scientist of Beijing Advanced Innovation Center for Future Visual Entertainment, Beijing Film Academy (2016-2021). He is a guest professor of the School of Art, Peking University. Chen is the recipient of 2003 NSF CAREER award, 2004 McKnight Land-Grant Professorship at the University of Minnesota (Twin Cities), and 2014 Outstanding Award of Chinagraph. Chen received an MS in Electronic Engineering from Tsinghua University, and a PhD in Computer Science from the State University of New York at Stony Brook. For his contribution to spatial data visualization, he was elected IEEE Fellow in 2020, and was inducted to IEEE Visualization Academy and ACM SIGGRAPH Academy in 2021 and 2024, respectively.

摘 要
Abstract

物理学家费曼曾经说过：“我不能创造的，我就无法理解。”计算机图形学（CG）的主要任务是创造/合成一个数字世界。正如CG之父、图灵奖获得者伊万·萨瑟兰所言，这个世界要“看起来真实、行动真实、听起来真实、感觉真实”。而人工智能的核心目标是理解世界并能够在其中行动。60年过去了，CG尚未完全实现其使命，而当前的AI，即使在其鼎盛时期，也无法充分理解和行动于现实世界。在本次讲座中，我将展示CG和AI相互促进的重要机遇。简单来说，CG能够为具身人工智能体（AI agents）提供不可或缺的“试验场”，而人工智能的工具则将让萨瑟兰看似遥不可及的愿景变得前所未有的接近现实。

Physicist Feynman once said: “What I cannot create, I do not understand.” The principle mission of computer graphics (CG) is to create/synthesize a digital world, which, according to “the father of CG,” also Turing Award winner, Ivan Sutherland, “… is to make that (digital) world look real, act real, sound real, feel real.” Whilst the central objective of Artificial Intelligence is to understand the world and be able to act in it. After 60 years, CG has yet to fully achieve is mission, whilst the current AI, even in its heyday, still cannot understand and act in the real world with sufficient competence. In this talk, I will illustrate the important opportunity that CG and AI mutually advance each other. Putting in the simplest form, CG is able to offer an indispensable ‘playground’ for embodied AI agents, while the tools of AI make Sutherland’s seemingly far-fetched vision ever closer to the reality.