报告时间：2019年9月5日（星期四）下午2:00-3:00
报告地点：浙江大学紫金港校区蒙民伟楼402室
报告题目：A brief introduction to differentiable rendering
主讲人：Shuang Zhao，Assistant Professor of Computer Science at the University of California, Irvine (UCI)。
主持人：王锐  教授

Abstract:
Inverse rendering problems focus on the inference of object geometry or material properties based on physical measurements of light (e.g., photographs and transient images). Mathematically, inverse rendering problems are generally modeled as nonlinear optimizations of discrepancies between physical measurements and their simulated counterparts. To solve these optimizations efficiently, gradient-based methods are desired, necessitating the development of differentiable rendering techniques.
In this talk, I will go over the basics (i.e., perturbation Monte Carlo) as well as recent advances of differentiable rendering theory. Additionally, I will show how differentiable rendering has benefited some of my recent works in material appearance modeling and low-level vision.

Short bio:
Shuang Zhao is an Assistant Professor of Computer Science at the University of California, Irvine (UCI) and co-direct UCI's Interactive Graphics & Visualization Lab (iGravi). Before joining UCI, Shuang was a postdoctoral associate at MIT. Shuang received his Ph.D. in computer science from Cornell University in 2014.
Shuang’s group works mainly in physics-based computer graphics and scientific computing with a focus on modeling and simulating how light interacts with complex materials (e.g., cloth, animal fur, and human skin). Additionally, his group aims to develop efficient solutions to the inverse problems centered around the inference of geometric or material properties from physical or simulated measurements.