报告摘要:In recent years, we have been witness to some truly amazing results produced by contemporary GenAI models for images and video, but the progress on 3D generation has lagged behind. Why is that? In this talk, I will highlight several key challenges that are making 3D generation harder than its 2D counterpart, despite the rapid advances in neural fields, differentiable rendering, diffusion models, and the emergence of large language models (LLMs). To set the context, I will briefly recount how these topics have evolved and become intricately connected in the past few years, especially in the context of generative AI with an emphasis on 3D reasoning and content creation. I will then introduce several recent works from my group on 3D representation learning and generative modeling to address some of the challenges. While popular trends and successes will be highlighted, I also want to raise critical and unresolved issues that will hopefully drive several new research trends over these emerging topics for 3D GenAI.
|
报告人简介:Hao (Richard) Zhang is a professor in the School of Computing Science at Simon Fraser University, Canada. He is a Fellow of the IEEE, holds a Distinguished University Professorship, and is an Amazon Scholar. Richard earned his Ph.D. from the University of Toronto, and MMath and BMath degrees from the University of Waterloo. His research is in computer graphics and visual computing with special interests in geometric and generative modeling, shape analysis, 3D vision, geometric deep learning, as well as computational design and fabrication. Awards won by Richard include a Canadian Human-Computer Communications Society Achievement Award in Computer Graphics (2022), a Google Faculty Award (2019), a National Science Foundation of China Overseas Outstanding Young Researcher Award (2015), an NSERC Discovery Accelerator Supplement Award (2014), and a Best Dataset Award from ChinaGraph (2020). He and his students have won the CVPR 2020 Best Student Paper Award and Best Paper Awards at Symposium on Geometry Processing 2008 and CAD/Graphics 2017. Richard has served as an editor-in-chief for Computer Graphics Forum (2014-2018), the Technical Papers Assistant Chair for SIGGRAPH Asia 2024, paper co-chairs for SGP 2013, GI 2015, and CGI 2018, and a conference chair for International Geometry Summit 2019. Richard will be the Technical Papers Chair for SIGGRAPH 2025.
|
![](img/Richard.png) |