Code Monkey home page Code Monkey logo

peterzs / variance-aware-path-guiding Goto Github PK

View Code? Open in Web Editor NEW

This project forked from irath96/variance-aware-path-guiding

0.0 0.0 0.0 120.87 MB

Implementation of the paper "Variance-Aware Path Guiding" (SIGGRAPH 2020)

License: GNU General Public License v3.0

CMake 2.11% Python 1.99% Shell 0.26% C 13.88% Makefile 0.01% C++ 69.58% XSLT 0.06% Batchfile 0.03% PowerShell 0.01% TeX 1.05% Objective-C 2.34% Objective-C++ 0.16% GLSL 0.14% CSS 0.08% Fortran 6.68% JavaScript 0.04% Perl 0.16% HTML 1.38% Gnuplot 0.01% Lua 0.03%

variance-aware-path-guiding's Introduction

Variance-Aware Path Guiding

Teaser Figure

This repository contains the authors' implementation of the "Variance-Aware Path Guiding" guiding target function as demonstrated in "Practical Path Guiding for Efficient Light-Transport Simulation" [Müller et al. 2017].

Selecting the guiding distribution

In addition to the parameters of the original implementation, we add the following parameters that allow switching between the previous guiding target function and our proposed target functions. These can be set in the Mitsuba GUI or in the scene files by using their property name (denoted by the monospace text in brackets).

Guiding Distribution (distribution)

The guiding distribution that should be approximated. The following values are valid:

  • radiance: Guiding distribution used by previous works.
  • simple: Approximates parts of the integrand.
    Robust for very short renders (< 10 seconds), but worse than full for longer renders
  • full: Approximates the full integrand.
    Recommended for longer renders (> 10 seconds), otherwise use simple

Default = radiance (for reproducibility)
Recommended = full (as evaluated in our paper)

DI strategy (diStrategy)

The strategy for direct illumination guiding. The following values are valid:

  • no: Do not guide towards direct illumination [Mueller et al. 2017].
  • unweighted: Guide direct illumination, ignoring MIS [Mueller et al. 2017, kickstart].
  • weighted: Guide direct illumination weighted by MIS weights.

Default = no (for reproducibility)
Recommended = no (for robustness, as evaluated in our paper)

Compilation

Mitsuba

To compile the Mitsuba code, please follow the instructions from the Mitsuba documentation (sections 4.1.1 through 4.6). Since our new code uses C++11 features, a slightly more recent compiler and dependencies than reported in the mitsuba documentation may be required. We only support compiling mitsuba with the scons build system.

We tested our Mitsuba code on

  • Windows (Visual Studio 2013 Win64, custom dependencies via git clone https://github.com/Tom94/mitsuba-dependencies-windows mitsuba/dependencies)
  • macOS (High Sierra / Mojave, custom dependencies via git clone https://github.com/Tom94/mitsuba-dependencies-macOS mitsuba/dependencies)
  • Linux (GCC 6.3.1)

Visualization Tool

The visualization tool, found in the visualizer subfolder, uses the CMake build system. Simply invoke the CMake generator on the visualizer subfolder to generate Visual Studio project files on Windows, and a Makefile on Linux / OS X.

The visualization tool was tested on

  • Windows (Visual Studio 2013-2017 Win64)
  • macOS (High Sierra)
  • Linux (GCC 6.3.1)

License

The new code introduced by this project is licensed under the GNU General Public License (Version 3). Please consult the bundled LICENSE file for the full license text.

The bundled KITCHEN scene is governed by the CC-BY 3.0 license.

variance-aware-path-guiding's People

Contributors

bashprince avatar irath96 avatar tom94 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.