Getting started#
Mitsuba 3 is a research-oriented rendering system for forward and inverse light-transport simulation. It consists of a small set of core libraries and a wide variety of plugins that implement functionality ranging from materials and light sources to complete rendering algorithms. Mitsuba 3 strives to retain scene compatibility with its predecessors: Mitsuba 0.6 and Mitsuba 2. However, in most other respects, it is a completely new system following a different set of goals.
Installation#
Mitsuba 3 can be installed via pip from PyPI. This is the recommended method of installation.
pip install mitsuba
This command will also install Dr.Jit on your system if not already available.
See the developer guide for complete instructions on building from the git source tree.
Requirements#
Python >= 3.8(optional) For computation on the GPU:
NVidia driver >= 495.89(optional) For vectorized / parallel computation on the CPU:
LLVM >= 11.1
Hello World!#
You should now be all setup to render your first scene with Mitsuba 3. Running the Mitsuba 3 code below will render the famous Cornell Box scene and write the rendered image to a file on disk.
import mitsuba as mi
mi.set_variant('scalar_rgb')
img = mi.render(mi.load_dict(mi.cornell_box()))
mi.Bitmap(img).write('cbox.exr')
Quickstart#
For the new users, we put together absolute beginner’s tutorials for both Dr.Jit and Mitsuba.
Video tutorials#
The following YouTube playlist contains various video tutorials related to Mitsuba 3 and Dr.Jit, perfect to get you started with those two libraries.
Citation#
When using Mitsuba 3 in academic projects, please cite:
@software{jakob2022mitsuba3,
title = {Mitsuba 3 renderer},
author = {Wenzel Jakob and Sébastien Speierer and Nicolas Roussel and Merlin Nimier-David and Delio Vicini and Tizian Zeltner and Baptiste Nicolet and Miguel Crespo and Vincent Leroy and Ziyi Zhang},
note = {https://mitsuba-renderer.org},
version = {3.0.1},
year = 2022,
}