彭思达，浙江大学软件学院“百人计划”研究员，博士生导师，研究方向为三维计算机视觉和计算机图形学。至今在TPAMI、CVPR、ICCV等期刊或会议发表六十余篇论文，谷歌学术引用5600余次，其中一篇一作论文获得CVPR最佳论文提名，成果获得GitHub数万次stars和2024年中国CCF图形开源软件奖；入选斯坦福2024全球Top 2%科学家榜单、2024年中国计算机学会优博（国内计算机领域评选十人）；被苹果公司评为2022 Apple Scholar（亚太地区唯一），被华为公司评为2024启真优秀青年学者。
课程摘要：
Physics simulation has become the third pillar of science and engineering, alongside theory and experiments. Two distinct simulation paradigms have emerged: the classical laws of physics approach, e.g., leveraging partial differential equations (PDEs) derived from first principles, and the data-driven approach, e.g., training neural networks from observations. My research asks: how can we effectively merge these two approaches to amplify their respective strengths? In this talk, I will show that by organically integrating these two approaches, we can create physics simulations that significantly outperform classical physics-only approaches in terms of (1) accuracy, (2) speed, and (3) accessibility. Simultaneously, our hybrid physics-data simulations possess exceptional generalization capabilities, which, unlike their pure data-driven counterparts, carefully incorporate PDEs as an inductive bias.
讲者简介：
Peter Yichen Chen is an incoming assistant professor at the University of British Columbia, where he directs the UBC PhysAI Lab. He was a postdoc at MIT CSAIL and earned his CS PhD from Columbia University. Earlier, he was a Sherwood Prize–winning math undergrad at UCLA. Peter’s research advances 3D content creation for artists, design/fabrication/control for engineers, and material discovery for scientists. His interdisciplinary work spans computer graphics, machine learning, scientific computing, mechanics, and robotics.
课程摘要：In this lecture, I will describe physics-based character control, which has a wide range of applications from computer games to humanoid robot control. Character control in a physical environment presents challenges due to complex body dynamics and the discontinuity of ground reaction forces. Recent advances in deep reinforcement learning have significantly improved character controllability and expanded the range of possible movements. I will first outline classic and fundamental approaches to character locomotion control. Then, I will discuss recent methods for generating character movements learned from human motion capture data.
讲者简介：
Taku Komura is a professor in the Department of Computer Science, The University of Hong Kong. Before joining The University of Hong Kong in 2020, he worked at the University of Edinburgh (2006-2020), City University of Hong Kong (2002-2006) and RIKEN (2000-2002). He received his BSc, MSc and PhD in Information Science from University of Tokyo. His research has focused on data-driven character animation, physically-based animation, crowd simulation, 3D modelling, cloth animation, anatomy-based modelling and robotics. Recently, his main research interests have been on physically-based animation and the application of machine learning techniques for animation synthesis. He received the Royal Society Industry Fellowship (2014), the Google AR/VR Research Award (2017) and the SIGGRAPH Best Paper Award (2022).
窦志扬，香港大学(HKU)计算机科学系研究生，师从王文平教授和Taku Komura教授，曾在宾夕法尼亚大学(UPenn)的Grasp Lab和图形学实验室访问刘玲洁教授并与UPenn MEAN的Cythia Sung教授密切合作。他的研究兴趣包括计算机图形学、几何处理、角色动画、物理仿真动画与人体行为建模与分析，研究成果发表在SIGGRAPH、SIGGRAPH ASIA、EUROGRAPHICS、ACM TOG、TVCG、SGP.CVPR、ICCV、ECCV、ICLR等国际顶级会议和期刊，曾获SIGGRAPH最佳论文奖、CGF年度高被引论文奖、港大基金会2023/24学年优秀博士生奖、Meshy Al Fellowship Finalist等。他现阶段的研究重点是将几何、拓扑和物理的先验融入到4D数据的获取、分析与生成过程之中
Lixin Yang is a Research Assistant Professor in School of Artificial Intelligence (SAI), Shanghai Jiao Tong University (SJTU). Since 2019, he has been part of the Machine Vision and Intelligence Group under the supervision of Prof. Cewu Lu, where he obtained his Ph.D. in 2023. Prior to that, he received his M.S degree at the Intelligent Robot Lab in SJTU. His research interests include 3D Vision and Robotics. Currently, he is focusing on modeling and imitating the hand manipulating objects, including 3D hand/object pose/shape estimation, grasp/motion generation, imitation learning, dexterous manipulation.
董豪，北京大学计算机学院前沿计算研究中心助理教授、研究员及博士生导师，科技部科技创新2030项目首席，入选国家级高层次青年人才计划。研究领域涵盖物体操纵、任务决策和具身导航，致力于构建通用具身智能算法与系统。他在RSS、ICRA、CoRL、NeurIPS、ICLR、CVPR、ICCV等国际顶级会议和期刊发表论文70余篇，谷歌学术引用量超8000次。荣获IROS 2024最佳应用论文入围奖、NeurIPS 2022 MyoChallenge操作赛冠军、ACM MM 2017最佳开源软件奖等。长期担任NeurIPS、CVPR、AAAI、ICRA、Machine Intelligence Research等顶级会议和期刊的领域主席及副编委、获Machine Intelligence Research 杰出副编委奖等。
胡瑞珍，深圳大学特聘教授，博士生导师，国家优秀青年科学基金、广东省杰出青年项目获得者。研究方向为计算机图形学，长期从事智能几何建模与处理方面的研究，发表 ACM SIGGRAPH/TOG 论文三十余篇；入选中科协青年人才托举工程；荣获亚洲图形学协会青年学者奖、全国几何设计与计算青年学者奖；担任期刊IEEE TVCG、IEEE CG&A和Computers & Graphics等国际期刊编委；担任国际会议SGP 2024/CVM 2023/SMI 2020 Technical Paper、SIGGRAPH Asia Technical Communications and Posters以及EG 2024 Short Paper程序委员会主席，连续多年担任SIGGRAPH等大会程序委员会委员；担任中国图象图形学学会智能图形专委会副主任、中国计算机学会计算机辅助设计与图形学专委会常委/副秘书长、计算机图形学与混合现实在线平台(GAMES)执委会主席。
徐凯，国防科技大学教授。普林斯顿大学访问学者。研究方向为计算机图形学、三维视觉、具身智能、数字孪生等。在国际上较早开展了数据驱动三维感知、建模与交互工作，提出面向复杂三维数据的结构化感知、建模与交互理论方法系统。主持国家自然科学基金青年科学基金A类（原杰青）项目、重点项目等。发表TOG/TPAMI/TVCG/CVPR/ICCV等A类论文100余篇。担任图形领域顶级国际期刊ACM Transactions on Graphics、IEEE Transactions on Visualization and Computer Graphics的编委，Computational Visual Media的领域执行编委。多次担任领域内重要会议的大会主席和程序主席。担任中国图象图形学会智能图形专委会副主任、中国工业与应用数学学会几何设计与计算专委会副主任。曾获湖南省自然科学一等奖2项（排名1和3）、中国计算机学会自然科学一等奖2项（排名1和3）、军队科技进步二等奖、军队教学成果二等奖、中国电子学会青年科学家奖。