【GAMES Webinar 2025-381期】
模拟动画专题
可控物理仿真与生成式动画
· 1 ·
报告题目
One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
报告嘉宾
张嘉鹏
清华大学
报告时间
2025年9月25号 晚上20:00-20:15（北京时间）
报告方式
GAMES直播间:
https://live.bilibili.com/h5/24617282
报告摘要
The rapid evolution of 3D content creation, encompassing both AI-powered methods and traditional workflows, is driving an unprecedented demand for automated rigging solutions that can keep pace with the increasing complexity and diversity of 3D models. We introduce UniRig, a novel, unified framework for automatic skeletal rigging that leverages the power of large autoregressive models and a bone-point cross-attention mechanism to generate both high-quality skeletons and skinning weights. Unlike previous methods that struggle with complex or non-standard topologies, UniRig accurately predicts topologically valid skeleton structures thanks to a new Skeleton Tree Tokenization method that efficiently encodes hierarchical relationships within the skeleton. To train and evaluate UniRig, we present Rig-XL, a new large-scale dataset of over 14,000 rigged 3D models spanning a wide range of categories. UniRig significantly outperforms state-of-the-art academic and commercial methods, achieving a 215% improvement in rigging accuracy and a 194% improvement in motion accuracy on challenging datasets. Our method works seamlessly across diverse object categories, from detailed anime characters to complex organic and inorganic structures, demonstrating its versatility and robustness. By automating the tedious and time-consuming rigging process, UniRig has the potential to speed up animation pipelines with unprecedented ease and efficiency. Project Page:https://zjp-shadow.github.io/works/UniRig/
嘉宾简介
张嘉鹏，清华大学胡事民老师二年级博士生，研究方向是计算机图形学与人工智能，研究兴趣主要为三维生成与动画，曾在SIGGRAPH/TOG上发表多篇文章，如CharacterGen、UniRig等。
个人主页
https://zjp-shadow.github.io/
· 2 ·
报告题目
Controllable Complex Freezing Dynamics Simulation on Thin Films
报告嘉宾
刘义杰
南开大学
报告时间
2025年9月25号 晚上20:15-20:35（北京时间）
报告方式
GAMES直播间:
https://live.bilibili.com/h5/24617282
报告摘要
The freezing of thin films is a mesmerizing natural phenomenon, inspiring photographers to capture its beauty through their lenses and digital artists to recreate its allure using effects tools. In this paper, we present a novel method for physically simulating the intricate freezing dynamics on thin films. By accounting for the influence of phase and temperature changes on surface tension, our method reproduces Marangoni freezing and the "Snow-Globe Effect", characterized by swirling ice dendrites on the film. We introduce a novel Phase Map method on top of the state-of-the-art Moving Eulerian-Lagrangian Particles (MELP) meshless framework, enabling dendritic crystal simulation on mobile particles and offering precise control over freezing patterns. We demonstrate that our method is able to capture a wide range of dynamic freezing processes of soap bubbles and is stable for complex boundaries in our experiments.
嘉宾简介
刘义杰，南开大学任博老师三年级硕士生，研究方向为计算机图形学，基于物理与机器学习的流体模拟及流固耦合。
主持人简介
王笑琨
北京科技大学
王笑琨，北京科技大学智能科学与技术学院教授，英国计算机动画中心Marie-Curie Fellow，入选欧盟玛丽居里学者、北科青年学者、北京科协青年人才托举工程。CCF计算机辅助设计与图形学专委会、人机交互专委会，CAAI智慧医疗专委会，CSIG人机交互专委会等委员。主要研究方向包括图形与虚拟现实，智能交互与仿真等，在SIGGRAPH Asia、IEEE TVCG、IEEE VR、EG、SCA、CGF等主流期刊会议上发表论文40余篇。曾获CGI2020最佳论文，CCF CAD & CG2022最佳论文，中国黄金协会科技进步一等奖，中国电子学会科技进步二等奖等。主持国家科技重大专项课题、国家自然科学基金面上、国家重点研发计划子课题等项目10余项。
长按二维码，关注公众号
GAMES网站: http://games-cn.org