12月12日（周一）上午9:00「青源Live第57期丨英伟达AI Lab科学家、GET3D一作高俊：从图像中学习3D对象的生成建模」将在线举办，多伦多大学博士生、英伟达AI Lab研究科学家高俊做报告分享，欢迎预约观看并参与线上交流。

高俊

高俊是多伦多大学的一名在读博士，师从Sanja Fidler教授。他也是英伟达多伦多AI Lab的一名研究科学家。他于2018年在北京大学获得学士学位。他的研究主要关注3D深度学习以及其与2D图像间的交互。

Jun Gao is a PhD student at the University of Toronto with Prof. Sanja Fidler, he is also a Research Scientist at Nvidia’s Toronto AI lab. He obtained his Bachelor’s degree from Peking University in 2018. His research mainly focuses on 3D deep learning and its interaction with 2D images.

“

从图像中学习3D对象的生成建模

Towards Generative Modeling of 3D Objects Learned from Images

随着许多行业对创建大型3D虚拟世界的需求不断增加，对多样化和有趣的3D内容需求也越来越大。人工智能非常有可能完成这项。在本次分享中，高俊博士将讨论最近在纹理网格形式的3D对象合成方面的工作，使它们能够轻松地用于现有的图形引擎。研究者设计了一种新的基于四面体网格的可微分3D表示，以实现具有任意拓扑结构的3D网格的高质量重建，并进一步开发了一个生成模型，将可微分等表面模型与可微分渲染相结合，并使用材质生成复杂纹理以生成网格。该模型进一步为3D网格创建的交互式工具开辟了一条新途径，使非专家也可以使用它并为元宇宙的未来提供动力。

With the increasing demand for creating large 3D virtual worlds in many industries, there is an immense need for diverse and interesting 3D content. A.I. is existentially enabling this quest. In this talk, I will discuss our recent work on 3D object synthesis in the form of textured meshes, allowing them to be easily used in existing graphics engines. We devise a new differentiable 3D representation based on a tetrahedral grid to enable high-quality recovery of 3D mesh with arbitrary topology, and  further develop a generative model to combine differentiable iso-surfacing models with differentiable rendering and produce complex textures with materials for mesh generation. Our model further enables a novel avenue in interactive tooling for 3D mesh creation, making it accessible to non experts and powering the future of metaverse.

活动时间：12月12日（周一）9:00-10:00

活动形式：线上直播，扫描下方二维码报名

更多内容 尽在智源社区公众号