mitsuba-renderer/mitsuba3

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

2899 stars · 357 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

simulation graphics machine-learning gpu-computing graphics simulation computer-vision machine-learning windows python cpp cross-platform rendering light-transport inverse-rendering differentiable-rendering physically-based-rendering ray-tracing drjit spectral-rendering research linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mitsuba-renderer/mitsuba3")