Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

Mitsuba 3

mitsuba-renderer.org

  • Free plan
  • Windows
  • macOS
  • Linux
  • API
  • Self-hosted

What Mitsuba 3 is

Mitsuba 3 is a free, open-source system for research-oriented forward and inverse light-transport simulation. It supports monochrome, RGB, and spectral rendering, with optional tracking of polarization, and can calculate how simulations change when camera pose, geometry, materials, textures, or volumes change. Its rendering code is compiled for CPUs through LLVM and NVIDIA GPUs through CUDA and OptiX. Python integration lets users develop materials, textures, and rendering algorithms; the documentation also includes a tutorial on interoperability with PyTorch. The recommended installation method is pip, using `pip install mitsuba`. Python 3.10 or later is required. GPU computation optionally requires NVIDIA driver 535 or later, and parallel CPU computation optionally requires LLVM 18 or later. The project says it has been tested on Linux x86_64, macOS aarch64 and x86_64, and Windows x86_64. The Python package includes thirteen variants by default; adding others requires compiling a custom Dr.Jit version with CMake. Tutorials, notebooks, how-to guides, and API and plugin references are available. The license permits redistribution and use in source and binary forms subject to its conditions.

Who it suits

Mitsuba 3 is aimed at researchers and developers experimenting with graphics, inverse rendering, or shape optimization. Its Python workflow and rendering variants suit users who need to explore light-transport simulations.

Good to know, and what to watch

  • Supports monochrome, RGB, and spectral rendering
  • Computes derivatives with respect to scene inputs
  • Compiles rendering code for CPUs and NVIDIA GPUs
  • Includes Python integration and a PyTorch tutorial
  • Requires Python 3.10 or later
  • GPU computation optionally requires NVIDIA driver 535 or later
  • Parallel CPU computation optionally requires LLVM 18 or later
  • Additional variants require compiling custom Dr.Jit with CMake

Free

Free

Open source

The verdict

Mitsuba 3 offers a research-focused simulation workflow with multiple rendering modes and derivative computation. Check the Python and optional hardware requirements, and note that the default package includes thirteen variants.

What the maker publishes

Architecture
It is written in portable C++17 on top of the Dr.Jit just-in-time compiler. source
Audience
The project describes itself as research-oriented and provides tutorials for applications including inverse rendering and shape optimization. source
Color and light
It supports monochrome, RGB, and spectral rendering variants, with optional polarization effects. source
Compatibility
Mitsuba 3 strives to retain scene compatibility with Mitsuba 0.6 and Mitsuba 2. source
Developer
The project says it was created by Wenzel Jakob and developed at EPFL in Switzerland. source
Differentiable rendering
It computes derivatives of simulations with respect to inputs such as camera pose, geometry, materials, textures, and volumes. source
Installation
The recommended installation method is pip, using the command `pip install mitsuba`. source
Installation
The recommended installation method is pip, which also installs Dr.Jit if it is not already available. source
Integration
The documentation includes a tutorial on interoperability between PyTorch and Mitsuba. source
Integrations
The documentation includes a tutorial on interoperability between PyTorch and Mitsuba. source
Intended users
The project describes itself as research-oriented and says its Python workflow enables experimentation in computer graphics and other disciplines. source
Learning resources
The documentation provides tutorials, notebooks, how-to guides, and API and plugin references. source
License
The repository license permits redistribution and use in source and binary forms subject to its listed conditions. source
Limits
The Python package includes thirteen variants by default; additional variants require compiling a custom version of Dr.Jit using CMake. source
Performance
Dr.Jit compiles rendering code for CPUs through LLVM and for NVIDIA GPUs through CUDA and OptiX. source
Platforms
The project says it has been tested on Linux x86_64, macOS aarch64 and x86_64, and Windows x86_64. source
Plugin system
Its core libraries and plugins cover functionality from materials and light sources to complete rendering algorithms. source
Purpose
Mitsuba 3 is a research-oriented system for forward and inverse light-transport simulation. source
Purpose
Mitsuba 3 is a research-oriented renderer for forward and inverse light-transport simulation. source
Python
Mitsuba 3 integrates with Python, where users can develop materials, textures, and rendering algorithms. source
Rendering variants
It supports monochrome, RGB, and spectral rendering, with optional polarization tracking. source
Security and support
The pages reviewed provide installation guidance, documentation, and tutorials but do not state security certifications or a support service. source
Supported systems
The project says it has been tested on Linux x86_64, macOS aarch64 and x86_64, and Windows x86_64. source
System requirements
Installation requires Python 3.10 or later; GPU computation optionally requires NVIDIA driver 535 or later, and parallel CPU computation optionally requires LLVM 18 or later. source

Checked against the maker's pages on 11 Oct 2026.