Light Transport Simulation in the Gradient Domain

  • Full Conference Pass (FC) Full Conference Pass (FC)
  • Full Conference One-Day Pass (1D) Full Conference One-Day Pass (1D)

Date: Tuesday, December 4th
Time: 9:00am - 12:45pm
Venue: Hall D1 (1F, D Block)


Summary: Despite the wide adoption in film production and animation industry nowadays, Monte Carlo light transport simulation is still prone to producing noisy images within short rendering time. Accelerating the convergence of Monte Carlo rendering without sacrificing its accuracy is by far a challenging task. In this course, we will learn about gradient-domain light transport simulation, a recent family of techniques in physically based rendering introduced in the past five years that can accelerate traditional Monte Carlo rendering up to approximately an order of magnitude based on gradient estimation and image reconstruction. Particularly, we will introduce the fundamentals of gradient-domain rendering with gradient-domain path tracing, and then extend the discussion to gradient-domain bidirectional path tracing and photon density estimation. We also discuss volume rendering in the gradient domain before diving into advanced topics in recent state-of-the-art papers in this direction. We further discuss tips and tricks in open-source implementations of such algorithms, and provide ideas for future research directions.

Author(s)/Speaker(s):
Moderator: Binh-Son Hua, The University of Tokyo, Japan
Lecturer(s): Binh-Son Hua, The University of Tokyo, Japan
Adrien Gruson, The University of Tokyo, The Japanese-French Laboratory for Informatics CNRS (UMI 3527), Japan
Matthias Zwicker, University of Maryland, United States of America
Toshiya Hachisuka, The University of Tokyo, Japan

Author(s)/Speaker(s) Bio:
Binh-Son Hua is currently a post-doctoral researcher at the University of Tokyo. Before that, he was a postdoctoral researcher in Singapore University of Technology and Design. He received his PhD degree in Computer Science from National University of Singapore in 2015. His research interests are physically based rendering and 3D scene understanding. His recent works are published in both computer graphics and computer vision venues, including Eurographics, TVCG, 3DV, CVPR, and SIGGRAPH.

Binh-Son Hua is currently a post-doctoral researcher at the University of Tokyo. Before that, he was a postdoctoral researcher in Singapore University of Technology and Design. He received his PhD degree in Computer Science from National University of Singapore in 2015. His research interests are physically based rendering and 3D scene understanding. His recent works are published in both computer graphics and computer vision venues, including Eurographics, TVCG, 3DV, CVPR, and SIGGRAPH.

Adrien Gruson is a post-doctoral researcher in Computer Graphics Group at the University of Tokyo (Prof. Toshiya Hachisuka's lab). Before that, he received his Ph.D. in Computer Science from the University of Rennes 1. His research interests include physically-based rendering based on MCMC and gradient-domain approaches. He is also a member of Japanese French Laboratory of Informatics (JFLI).

Matthias Zwicker has joined the University of Maryland in 2017 as the Reginald Allan Hahne Endowed E-Nnovate Professor in Computer Science. He obtained his PhD from ETH in Zurich, Switzerland, in 2003. From 2003-2006 he was a post-doctoral associate at MIT, and then an Assistant Professor at the University of California in San Diego from 2006-2008. From 2008-2017, he was a professor in Computer Science at the University of Bern, Switzerland, and the head of the Computer Graphics Group. His research focus is on efficient high-quality rendering, signal processing techniques for computer graphics, data-driven modeling and animation, and point-based methods.

Toshiya Hachisuka is an Associate Professor in the Department of Creative Informatics at the University of Tokyo. He is interested in the intersection of computational statistics, numerical computation, and physics based computer graphics. He has published multiple work on those topics including some recent work on gradient-domain rendering via photon density estimation. He received his Ph.D. in Computer Science from University of California at San Diego in 2011 and B.Eng. from the University of Tokyo in 2006.

 

Back

/en/attendees/doctoral-consortium /en/attendees/production-gallery