# mitsuba-renderer/mitsuba3

Mitsuba 3: A Retargetable Forward and Inverse Renderer

Repository: https://github.com/mitsuba-renderer/mitsuba3
Canonical: https://ross.abutalabs.com/products/mitsuba3
Homepage: https://www.mitsuba-renderer.org/
Language: C++
License: NOASSERTION
License Family: other
Last push: 2026-08-26T12:44:25+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 84, longevity 100
- inputs: {"age_days": 1953, "days_push": 7, "days_rel": 26, "gap_med": 51, "n_releases_24m": 8}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2899, forks 357 (observed 2026-08-28T04:07:28.835996+00:00)

## What it is
Mitsuba 3 is a research-oriented, retargetable rendering system for forward and inverse light transport simulation, written in C++17 on top of the Dr.Jit JIT compiler. The same codebase can be compiled into variants for scalar RGB, spectral, or differentiable rendering on CPU (LLVM) or NVIDIA GPUs (CUDA/OptiX), with deep Python integration.

## Use cases
- render photorealistic images with physically based light transport
- run differentiable rendering for inverse rendering and scene reconstruction
- simulate spectral light transport including polarization
- accelerate ray tracing on NVIDIA GPUs with OptiX
- prototype new materials and rendering algorithms in Python
- fit material and geometry parameters from photographs

## When to choose
- you need state-of-the-art forward or inverse light transport simulation for research
- you want a Python-first renderer with JIT compilation to CPU or GPU
- you need spectral or polarization-aware rendering
- you are doing differentiable rendering or physics-based machine learning

## When to avoid
- you need a production game-engine renderer or real-time rendering
- you only need simple offline rendering without research features
- you require a permissively licensed library for commercial embedding without reviewing its license terms

## Facets
- artifact type: library
- maturity: active
- function: simulation, graphics, machine-learning, gpu-computing
- domain: graphics, simulation, computer-vision, machine-learning
- platform: windows, python, cpp, cross-platform
- tags: rendering, light-transport, inverse-rendering, differentiable-rendering, physically-based-rendering, ray-tracing, drjit, spectral-rendering, research, linux, macos, gpu

## Member repositories
- mitsuba-renderer/mitsuba3 (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:28.835996+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:35:11.477756+00:00, confidence not recorded.
  - readme: https://github.com/mitsuba-renderer/mitsuba3 (fetched 2026-08-28T04:07:28.835996+00:00, sha 7f29202e9360)
  - homepage: https://www.mitsuba-renderer.org/ (fetched 2026-08-29T09:49:55.277433+00:00, sha 37913439504c)
- Data as of 2026-08-30T08:39:29.467469+00:00.