GAMES Webinar 2023 – 302期(材质生成) | 胡义伟(Adobe Research),马晓鹤(浙江大学)

【GAMES Webinar 2023-302期】(绘制专题-材质生成)

报告嘉宾:胡义伟(Adobe Research)


报告题目:Generating Procedural Materials from Text or Image Prompts


Procedural materials, in the form of node graphs, are essentially computational graphs. Recent development of generative models enables high-quality 2D or 3D asset generation from prompts, however generating a computational graph from text prompts or image inputs is non-trivial. In this talk, we will introduce our first conditional generative model that can synthesize high-quality procedural node graphs from multi-modal inputs. The model can be served as a tool for automatic visual programming completion.


Yiwei Hu is a research scientist at Adobe Research. He obtained his Ph.D. degree from Yale University this year. Prior to Yale, he graduated from Zhejiang University. His work focuses on material modeling and rendering for next generation 3D content creation. He has a general interest in generative models for 3D graphics. He is the leading author on multiple top tier publications, including SIGGRAPH, SIGGRAPH ASIA, EGSR and Pacific Graphics.





报告题目:OpenSVBRDF: A Database of Measured Spatially-Varying Reflectance


We present the first large-scale database of measured spatially-varying anisotropic reflectance, consisting of 1,000 high-quality near-planar SVBRDFs, spanning 9 material categories such as wood, fabric and metal. Each sample is captured in 15 minutes, and represented as a set of high-resolution texture maps that correspond to spatially-varying BRDF parameters and local frames. To build this database, we develop a novel integrated system for robust, high-quality and -efficiency reflectance acquisition and reconstruction. Our setup consists of 2 cameras and 16,384 LEDs. We train 64 lighting patterns for efficient acquisition, in conjunction with a network that predicts per-point reflectance in a neural representation from carefully aligned two-view measurements captured under the patterns. The intermediate results are further fine-tuned with respect to the photographs acquired under 63 effective linear lights, and finally fitted to a BRDF model.We report various statistics of the database, and demonstrate its value in the applications of material generation, classification as well as sampling. All related data, including future additions to the database, can be downloaded from


Xiaohe Ma received her bachelor degree of engineering from Sun Yat-sen University in 2019. Currently she is a fifth year Ph.D. student in the State Key Lab of CAD&CG, Zhejiang University. Her research interests include appearance acquisition and modeling. She has published several high-quality papers as the lead author in top-tier journals, including SIGGRAPH, SIGGRAPH Asia, and TVCG.




过洁现为南京大学计算机科学与技术系副研究员,主要研究领域为计算机图形学和虚拟现实。迄今为止,共主持相关领域科研项目20余项,包括国家自然科学基金面上项目、“十三五”装发预研项目课题、江苏省自然科学基金面上项目、企业合作项目多项,在国内外主流期刊和会议上发表论文80余篇,包括SIGGRAPH、CVPR、ICCV、IEEE TVCG、IEEE TIP等,开发的材质建模、光照估计、高性能渲染等技术已被多家知名企业应用,产生了显著的经济和社会效益。过洁曾获华为火花奖、江苏省计算机学会青年科技奖、江苏省工程师学会优秀青年工程师奖等奖励,入选江苏省“双创计划”科技副总计划。


GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播?”及“如何加入GAMES微信群?”的信息;

You may also like...