11月29日，“上海人工智能实验室学术论坛”将举办第23期“星河Talk”。本期邀请德国慕尼黑工业大学教授Matthias Nießner，带来主题报告Photorealistic Reconstruction with Neural Parametric Models。

“星河Talk”第23期

【活动详情】

主题：Photorealistic Reconstruction with Neural Parametric Models

嘉宾：Matthias Nießner   Professor at the Technical University of Munich

主持人：上海人工智能实验室 林君仪（Kwan-Yee Lin） 

时间：北京时间 11月29日 16:30-17:30

参与方式：全球高校人工智能学术联盟 视频号直播

【讲座简介】

In the presentation, the speaker will discuss the latest research on creating photorealistic digital replicas of the real world. His ultimate goal is to witness the evolution of photos and videos into interactive, holographic 3D content that is indistinguishable from physical reality. Envisioning the possibility of capturing and sharing such 3D photos with friends, family, or through social media platforms, and imagining the ability to comprehensively document historical events for future generations or generate content for upcoming applications in augmented and virtual reality, now, AI-based methodologies, particularly those employing generative neural networks, have emerged as a crucial element in this endeavor. These approaches facilitate the transformation of existing image synthesis pipelines. Specifically, the speaker will delve into more recent advancements in neural rendering and reconstruction techniques, which enable them  retaining full control over traditional graphics pipelines while harnessing the modern capabilities of deep neural networks.

【本期嘉宾】

Matthias Nießner   Professor at the Technical University of Munich

Dr. Matthias Nießner is a Professor at the Technical University of Munich, leading the Visual Computing Lab. Previously, he served as a Visiting Assistant Professor at Stanford University. His research spans computer vision, graphics, and machine learning, focusing on advanced techniques for 3D reconstruction, semantic 3D scene understanding, video editing, and AI-driven video synthesis. He has published over 150 academic publications, including 25 papers in the esteemed ACM Transactions on Graphics (SIGGRAPH / SIGGRAPH Asia) journal and 55 works in leading vision conferences (CVPR, ECCV, ICCV). Several of his contributions have received best paper awards, notably at SIGCHI’14, HPG’15, SPG’18, and the SIGGRAPH’16 Emerging Technologies Award for the best Live Demo.

Dr. Nießner's work has garnered significant media attention, with numerous features in mainstream outlets such as the New York Times, Wall Street Journal, Spiegel, and MIT Technological Review, among others. His work led to several TV appearances, including on Jimmy Kimmel Live, showcasing the popular Face2Face technique. His academic YouTube channel currently has over 5 million views. He has received several awards, including the TUM-IAS Rudolph Moessbauer Fellowship (2017 – ongoing), the Google Faculty Award for Machine Perception (2017), the Nvidia Professor Partnership Award (2018), and the prestigious ERC Starting Grant 2018, which includes 1.5 million Euro in research funding. In 2019, he was honored with the Eurographics Young Researcher Award, recognizing the best emerging graphics researcher in Europe.

Beyond academia, Dr. Nießner co-founded and directs Synthesia Inc., a startup dedicated to democratizing synthetic media generation with cutting-edge AI-driven video synthesis technology. The startup recently achieved unicorn status with a valuation of 1 billion USD.

上海人工智能实验室学术论坛

“上海人工智能实验室学术论坛”分设“星河Talk”与“星启Talk”两个主题系列活动，将分别邀请全球顶尖教授和杰出青年学者作为嘉宾，线上线下分享学术成果、探讨科技前沿。更多精彩内容，敬请期待。