NVIDIAGameWorks/kaolin-wisp

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1498 stars · 141 forks observed · 2026-08-28

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

NVIDIA Kaolin Wisp is a PyTorch library and engine for neural fields research, built on NVIDIA Kaolin Core. It provides differentiable renderers, data structures (octrees, hash grids, triplanar features), datasets, interactive visualization, and trainer classes for models like NeRFs, NGLOD, instant-ngp, and VQAD.

Use cases

• train NeRF models from images
• research neural signed distance fields
• build custom neural field architectures with hash grids and octrees
• interactively visualize and debug neural field training
• render novel views of 3D scenes
• experiment with instant-ngp style multiresolution hash grids

When to choose

• you need a flexible PyTorch framework for neural fields research
• you want differentiable rendering and sparse data structures out of the box
• you need interactive training visualization on NVIDIA GPUs
• you want reference implementations of NeRF, NGLOD, and instant-ngp variants

When to avoid

• you need a production-ready 3D reconstruction pipeline rather than a research toolkit
• you don't have a CUDA-capable NVIDIA GPU
• you need a simple one-command NeRF trainer with minimal configuration
• your project requires a permissive open-source license (NVIDIA Source Code License applies)

Facets

library · maturity maintenance

machine-learning deep-learning graphics simulation image-processing data-visualization deep-learning machine-learning graphics computer-vision developer-tools python windows neural-fields nerf sdf pytorch 3d-reconstruction differentiable-rendering nvidia research gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NVIDIAGameWorks/kaolin-wisp")