GAMES Webinar 2021 – 207期(绘制专题) | Cheng Zhang (UC Irvine)，Zihan Yu（UC Irvine）
【GAMES Webinar 2021-207期】(绘制专题)
报告嘉宾1：Cheng Zhang (UC Irvine)
报告时间：2021年11月11号星期四上午10:00-10:30（北京时间）
报告题目：Antithetic Sampling for Monte Carlo Differentiable Rendering
报告摘要：
Stochastic sampling of light transport paths is key to Monte Carlo forward rendering, and previous studies have led to mature techniques capable of drawing high-contribution light paths in complex scenes. These sampling techniques have also been applied to differentiable rendering.
In this paper, we demonstrate that path sampling techniques developed for forward rendering can become inefficient for differentiable rendering of glossy materials – especially when estimating derivatives with respect to global scene geometries. To address this problem, we introduce antithetic sampling of BSDFs and light-transport paths, allowing significantly faster convergence and can be easily integrated into existing differentiable rendering pipelines. We validate our method by comparing our derivative estimates to those generated with existing unbiased techniques. Further, we demonstrate the effectiveness of our technique by providing equal-quality and equal-time comparisons with existing sampling methods.
讲者简介：
Cheng Zhang is a final-year Ph.D. candidate ( 2017 – Now ) in the Computer Science department at UC Irvine under the supervision of professor Shuang Zhao. Before that, Cheng obtained his B.E. in Electrical Engineering from BJUT (2011-2015) and his M.S. in Computer Science from Columbia University (2015-2017). Cheng is the recipient of the 2021 Facebook Fellowship.
Cheng’s research focuses on physics-based rendering and its inverse problems centered around the inference of geometric and material properties from physical measurements (i.e. photographs, depth data). To develop efficient solutions to the inverse rendering problems, he has been working actively on the topic of physics-based differentiable rendering.
讲者个人主页：https://www.ics.uci.edu/~chengz20/
报告嘉宾2：Zihan Yu（UC Irvine）
报告时间：2021年11月11号星期四晚上10:30-11:00（北京时间）
报告题目：Path-Space Differentiable Rendering of Participating Media
报告摘要：
Physics-based differentiable rendering—which focuses on estimating derivatives of radiometric detector responses with respect to arbitrary scene parameters—has a diverse array of applications from solving analysis-by-synthesis problems to training machine-learning pipelines incorporating forward-rendering processes. Unfortunately, existing general-purpose differentiable rendering techniques lack either the generality to handle volumetric light transport or the flexibility to devise Monte Carlo estimators capable of handling complex geometries and light transport effects.
In this paper, we bridge this gap by showing how generalized path integrals can be differentiated with respect to arbitrary scene parameters. Specifically, we establish the mathematical formulation of generalized differential path integrals that capture both interfacial and volumetric light transport. Our formulation allows the development of advanced differentiable rendering algorithms capable of efficiently handling challenging geometric discontinuities and light transport phenomena such as volumetric caustics.
We validate our method by comparing our derivative estimates to those generated using the finite differences. Further, to demonstrate the effectiveness of our technique, we compare both differentiable rendering and inverse rendering performance with state-of-the-art methods.
Zihan is a second-year Ph.D. student at the School of Information and Computer Science, UC Irvine, supervised by Prof. Shuang Zhao. His research interests are in physically-based rendering and differentiable rendering. Before coming to UCI, he received his M.S. in Computer Science from Columbia University and his B.E. in Software Engineering from Tongji University.
讲者个人主页：zihan.me
主持人简介：
过洁，南京大学计算机科学与技术系、软件新技术国家重点实验室副研究员。2013年毕业于南京大学，获得博士学位。目前主要研究方向为真实感绘制、实时绘制、复杂材质分析建模以及虚拟现实技术等。发表学术论文50余篇，包括计算机图形学领域顶级会议/期刊ACM SIGGRAPH/SIGGRAPH ASIA、IEEE TVCG，视觉领域顶级会议CVPR、ICCV、ECCV 等。个人主页：http://118.25.137.210/
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；
GAMES主页的“资源分享”有往届的直播讲座的视频及PPT等。
观看直播的链接：http://webinar.games-cn.org
