GAMES Webinar 2020 – 158期(绘制专题) | Cheng Zhang(UC Irvine), Fujun Luan(Cornell University)
【GAMES Webinar 2020-158期】(绘制专题)
报告嘉宾1： Cheng Zhang(UC Irvine)
报告时间：2020年10月15日上午10:00-10:45（北京时间）
报告题目：Path-Space Differentiable Rendering
报告摘要：
Physics-based differentiable rendering, the estimation of derivatives of radiometric measures 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, general-purpose differentiable rendering remains challenging due to the lack of efficient estimators as well as the need to identify and handle complex discontinuities such as visibility boundaries. In this paper, we show how path integrals can be differentiated with respect to arbitrary differentiable changes of a scene. We provide a detailed theoretical analysis of this process and establish new differentiable rendering formulations based on the resulting differential path integrals. Our path-space differentiable rendering formulation allows the design of new Monte Carlo estimators that offer significantly better efficiency than state-of-the-art methods in handling complex geometric discontinuities and light transport phenomena such as caustics.
We validate our method by comparing our derivative estimates to those generated using the finite-difference method. To demonstrate the effectiveness of our technique, we compare inverse-rendering performance with a few state-of-the-art differentiable rendering methods.
讲者简介：
physics-based rendering with focus on modeling and simulating of light interactions with complex material and differentiable rendering, which serves as an efficient tool for solving inverse rendering problems.
讲者个人主页: https://www.ics.uci.edu/~chengz20/
报告嘉宾2：Fujun Luan(Cornell University)
报告时间：2020年10月15日上午10:45-11:30（北京时间）
报告题目：Tile Pair-Based Adaptive Multi-Rate Stereo Shading
报告摘要：
We introduce a suite of Langevin Monte Carlo algorithms for efficient photorealistic rendering of scenes with complex light transport effects, such as caustics, interreflections, and occlusions. Our algorithms operate in primary sample space, and use the Metropolis-adjusted Langevin algorithm (MALA) to generate new samples. Drawing inspiration from state-of-the-art stochastic gradient descent procedures, we combine MALA with adaptive preconditioning and momentum schemes that re-use previously-computed first-order gradients, either in an online or in a cache-driven fashion. This combination allows MALA to adapt to the local geometry of the primary sample space, without the computational overhead associated with previous Hessian-based adaptation algorithms. We use the theory of controlled Markov chain Monte Carlo to ensure that these combinations remain ergodic, and are therefore suitable for unbiased Monte Carlo rendering. Through extensive experiments, we show that our algorithms, MALA with online and cache-driven adaptation, can successfully handle complex light transport in a large variety of scenes, leading to improved performance (on average more than 3× variance reduction at equal time, and 7× for motion blur) compared to state-of-the-art Markov chain Monte Carlo rendering algorithms.
讲者简介：
Fujun Luan is a PhD candidate at Cornell University working in the Graphics and Vision Group, under the supervision of Kavita Bala. Before that, he graduated from Tsinghua University , advised by Kun Xu and Shi-Min Hu. His research interests are mainly in computer graphics and computer vision. Specifically, he is currently focusing on learning-based forward and inverse graphics problems through differentiable rendering.
讲者个人主页: https://www.cs.cornell.edu/~fujun/
主持人简介：
http://www.cad.zju.edu.cn/home/rwang
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
