NVlabs/instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
This tool helps 3D artists, game developers, and researchers quickly convert sets of 2D images or 3D models into interactive, photorealistic 3D scenes. You provide photos of an object or environment, or existing 3D assets like a detailed armadillo model, and it generates a digital replica that can be explored in real-time. This is for professionals who need to rapidly create and visualize complex 3D content from real-world captures or existing assets.
17,310 stars.
Use this if you need to rapidly create, train, and render high-fidelity 3D scenes or objects from photographs or 3D models, especially for applications like virtual reality or scene reconstruction.
Not ideal if you lack an NVIDIA RTX GPU, as performance will be significantly limited, or if you primarily work with traditional polygonal modeling and texturing workflows.
Stars
17,310
Forks
2,057
Language
Cuda
License
—
Category
Last pushed
Feb 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVlabs/instant-ngp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
nerfstudio-project/nerfstudio
A collaboration friendly studio for NeRFs
google/nerfies
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.
SuLvXiangXin/zipnerf-pytorch
Unofficial implementation of ZipNeRF
google/hypernerf
Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural...
yashbhalgat/HashNeRF-pytorch
Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives:...