If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
The first deep-learning approach for denoising Monte Carlo-rendered images suitable for a production environment.
Steve Bako
University of California, Santa Barbara
Thijs Vogels
Disney Research, ETH Zürich
Brian McWilliams
Disney Research Zürich
Mark Meyer
Pixar Animation Studios
Jan Novak
Disney Research Zürich
Alex Harvill
Pixar Animation Studios
Pradeep Sen
University of California, Santa Barbara
Tony DeRose
Pixar Animation Studios
Fabrice Rousselle
Disney Research Zürich
A machine-learning technique for reconstructing sparsely sampled image sequences rendered using Monte Carlo methods. The primary focus is on reconstruction of global illumination with extremely low sampling budgets at interactive rates.
Chakravarty Reddy Alla Chaitanya
McGill University, NVIDIA, Université de Montréal
Anton Kaplanyan
NVIDIA, Karlsruher Institut für Technologie
Christoph Schied
Karlsruher Institut für Technologie, NVIDIA
Marco Salvi
NVIDIA
Aaron Lefohn
NVIDIA
Derek Nowrouzezahrai
Université de Montréal, McGill University
Timo Aila
NVIDIA
This paper presents a domain-specific language that simplifies implementation of Monte Carlo rendering algorithms. The user writes sampling code in the
language, then at compile time it automatically generates the necessary PDF code. This enables the user to write complex rendering algorithms in a simpler, more understandable way.
Luke Anderson
Massachusetts Institute of Technology
Tzu-Mao Li
Massachusetts Institute of Technology
Jaakko Lehtinen
Aalto University
Frédo Durand
Massachusetts Institute of Technology
This paper demonstrates an approach for achieving both modularity and high performance for shader code in current and upcoming real-time rendering engines. It presents a shader compiler and an engine design that enables authoring modular shader code and maps that to efficient a parameter-binding model on modern graphics APIs.
Yong He
Carnegie Mellon University
Tim Foley
NVIDIA Corporation
Teguh Hofstee
Carnegie Mellon University
Haomin Long
Tsinghua University
Kayvon Fatahalian
Carnegie Mellon University
In this proposed compression scheme for a-priori bounding-volume hierarchies on parametric patches, the resulting hierarchy can be utilized with leaf geometry or even directly applied as a geometry approximation.
Michael Guthe
Universität Bayreuth
Kai Selgrad
Friedrich-Alexander-Universität Erlangen-Nürnberg
Alexander Lier
Friedrich-Alexander-Universität Erlangen-Nürnberg
Magdalena Martinek
Friedrich-Alexander-Universität Erlangen-Nürnberg
Christoph Buchenau
Universität Bayreuth
Franziska Kranz
Friedrich-Alexander-Universität Erlangen-Nürnberg
Henry Schafer
Friedrich-Alexander-Universität Erlangen-Nürnberg
Marc Stamminger
Friedrich-Alexander-Universität Erlangen-Nürnberg