NVlabs/nvdiffrast
Some data may be outdated — see provenance labels.
Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering observed · 2026-09-23
Health v2 · maintenance only
49/100
- Activity 48
- Release rhythm 21
- Longevity 100
Flags: no_license
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-22. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2179
- days_rel: 317
- days_push: 317
- n_releases_24m: 1
Adoption not part of the score
1922 stars · 244 forks observed · 2026-09-23
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
Nvdiffrast is a PyTorch library from NVIDIA providing high-performance, GPU-accelerated primitive operations for rasterization-based differentiable rendering, including rasterization, interpolation, texturing, and antialiasing. It is intentionally low-level, leaving camera models and material/lighting models to the user, and all operations and their gradients run on CUDA.
Use cases
- differentiable rendering for 3D reconstruction from images
- optimize 3D mesh textures and geometry via gradient descent
- train neural networks that render 3D scenes in PyTorch
- inverse graphics and 3D-aware generative model training
- fast GPU rasterization with gradients for research pipelines
When to avoid
- you need a high-level renderer with built-in camera, lighting, and material models
- you don't have an NVIDIA GPU or CUDA toolkit
- you want a pure-Python or CPU-only solution
Facets
library · maturity stable
graphics machine-learning image-processing computer-vision graphics deep-learning machine-learning windows python differentiable-rendering pytorch cuda rasterization 3d-graphics nvidia inverse-graphics gpu-accelerated linux gpu
2 sources
- readme: https://github.com/NVlabs/nvdiffrast · fetched 2026-09-23 · 2c53380264d4
- homepage: https://nvlabs.github.io/nvdiffrast · fetched 2026-08-29 · f7ab0316efd6
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| NVlabs/nvdiffrast | main | 49 |
For agents
markdown · JSON · MCP: product_card(name="NVlabs/nvdiffrast")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem