GAMES Webinar 2020 – 159期(绘制专题) | 王贝贝(南京理工大学), Chao Xu(Alibaba Cloud-A.I.Labs)

【GAMES Webinar 2020-159期】(绘制专题)

报告嘉宾1: 王贝贝(南京理工大学)


报告题目:Example-Based Microstructure Rendering with Constant Storage


Rendering glinty details from specular microstructure enhances the level of realism, but previous methods require heavy storage for the high-resolution height field or normal map and associated acceleration structures. In this paper, we aim at dynamically generating theoretically infinite microstructure, preventing obvious tiling artifacts, while achieving constant storage cost. Unlike traditional texture synthesis, our method supports arbitrary point and range queries, and is essentially generating the microstructure implicitly. Our method fits the widely used microfacet rendering framework with multiple importance sampling (MIS), replacing the commonly used microfacet normal distribution functions (NDFs) like GGX by a detailed local solution, with a small amount of runtime performance overhead.


王贝贝,女,南京理工大学,副教授,硕士生导师,中国计算机学会CAD&CG专委会委员。主要研究方向是计算机图形学渲染方向,包括了全局光照算法、参与性介质光线传递和复杂材质模型等。王贝贝分别于2009年、2014年在山东大学获得学士、博士学位,期间在巴黎高科进行两年联合培养。2015年在英国游戏公司Studio Gobo参与Disney游戏Infinity 3的研发。2015年底到2017年初,在INRIA(法国信息与自动化研究所)从事博士后研究。之后加入到南京理工大学。共发表高水平论文30余篇,其中以第一作者在ACM TOG, IEEE TVCG, CGF上发表论文十余篇。ACM TOG, Siggraph Asia, EG 等期刊会议审稿人。


报告嘉宾2:Chao Xu (Alibaba Cloud-A.I.Labs)


报告题目:Multi-Scale Hybrid Micro-Appearance Modeling and Realtime Rendering of Thin Fabrics


Micro-appearance models offer state-of-the-art quality for cloth renderings. Unfortunately, they usually rely on 3D volumes or fiber meshes that are not only data-intensive but also expensive to render. Traditional surface-based models, on the other hand, are light-weight and fast to render but normally lack the fidelity and details important for design and prototyping applications. We introduce a multi-scale, hybrid model to bridge this gap for thin fabrics. Our model enjoys both the compactness and speedy rendering offered by traditional surface-based models and the rich details provided by the micro-appearance models. Further, we propose a new algorithm to convert state-of-the-art micro-appearance models into our representation while qualitatively preserving the detailed appearance. We demonstrate the effectiveness of our technique by integrating it into a real-time rendering system.


Chao Xu received his Ph. D. from Zhejiang University in 2019. His interests are mainly in the complex material representation and real-time rendering.

Chao Xu is a research engineer in Alibaba Cloud-A.I.Labs HangZhou, where he works on real-time rendering and 3D engine developing. Chao received his PHD degree from State Key Laboratory of CAD&CG, Zhejiang University in 2019 under the supervision of Prof. Hujun Bao and Prof. Rui Wang. His interests are mainly in the complex material representation and real-time rendering. Most of his works can be found in


郭延文,南京大学教授、博导,江苏省杰出青年科学基金获得者,南京大学计算机科学与技术系教师、计算机软件新技术国家重点实验室骨干。浙江大学博士、美国伊利诺伊大学香槟分校、香港大学和中文大学访问学者。主要研究方向为计算机图形学、虚拟现实和三维计算机视觉,研究成果发表20余篇ACM/IEEE Transactions期刊论文以及Siggraph, EG, CVPR, ECCV等会议论文,获授权发明专利近20项,主持国家自然科学基金面上、重点、装发预研以及与华为等公司合作项目多项。担任中国图像图形学会理事、江苏省计算机学会图形图像专委会主任和江苏省工程师学会虚拟现实专委会主任,ICVRV、ChinaVR等会议程序主席,ICCV、CVPR和PG等程序委员。

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...