GAMES Webinar 2024 – 315期(All about manifolds) |邢健开(清华大学),Zhimin Fan(Nanjing University)

【GAMES Webinar 2024-315期】(渲染专题-All about manifolds)



报告题目:Extended Path Space Manifold for Physically Based Differentiable Rendering


Physically based differentiable rendering has become an increasingly important topic in recent years. However, existing approaches cannot robustly handle complex illumination effects including reflections, refractions, caustics, shadows, and highlights, especially when the initial and target locations of such illumination effects are not close to each other in the image space. To address this problem, we propose a novel data structure named extended path space manifolds. The manifolds are defined in the combined space of path vertices and scene parameters. By enforcing geometric constraints, the path vertices could be implicitly and uniquely determined by perturbed scene parameters. This enables the manifold to track specific illumination effects and the corresponding paths, i.e., specular paths will still be specular paths after scene parameters are perturbed. We further propose a physically based differentiable rendering method built upon the theoretical results of extended path space manifolds. By incorporating the path derivatives computed from the manifolds and an optimal transport based loss function, our method is demonstrated to be more effective and robust than state-of-the-art approaches in inverse rendering applications involving complex illumination effects.


Jiankai Xing is currently a Ph.D student at Tsinghua University. His advisor is Kun Xu. He received his bachelor degree from Tsinghua University in 2021. His research focuses on differentiable rendering and inverse rendering.


报告嘉宾:Zhimin Fan(Nanjing University)


报告题目:Manifold Path Guiding for Importance Sampling Specular Chains


Complex visual effects such as caustics are often produced by light paths containing multiple consecutive specular vertices (dubbed specular chains), which pose a challenge to unbiased estimation in Monte Carlo rendering. In this work, we study the light transport behavior within a sub-path that is comprised of a specular chain and two non-specular separators. We show that the specular manifolds formed by all the sub-paths could be exploited to provide coherence among sub-paths. By reconstructing continuous energy distributions from historical and coherent sub-paths, seed chains can be generated in the context of importance sampling and converge to admissible chains through manifold walks. We verify that importance sampling the seed chain in the continuous space reaches the goal of importance sampling the discrete admissible specular chain. Based on these observations and theoretical analyses, a progressive pipeline, manifold path guiding, is designed and implemented to importance sample challenging paths featuring long specular chains. To our best knowledge, this is the first general framework for importance sampling discrete specular chains in regular Monte Carlo rendering. Extensive experiments demonstrate that our method outperforms state-of-the-art unbiased solutions with up to 40× variance reduction, especially in typical scenes containing long specular chains and complex visibility.


Zhimin Fan is currently a M.S. student at Nanjing University, under the supervision of Jie Guo and Yanwen Guo. He received his bachelor’s degree from Southeast University in 2023. His research focuses on physically-based rendering, specifically on topics related to light transport simulation including specular light transport and path guiding.



王贝贝, 南京大学(苏州校区)智能科学与技术学院教授。研究方向为计算机图形学渲染方向,分别于2009年和2014年在山东大学获得学士和博士学位,曾在INRIA从事博士后研究,曾在香港理工大学访问交流,曾参与Disney Infinity研发,提出SpongeCake材质模型。发表ACM TOG、SIGGRAPH(Asia)多篇。担任SIGGRAPH 2023-2024程序委员会委员。曾获陆增镛CAD&CG高科技奖二等奖。


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...