Home Projects instant-ngp
instant-ngp
Cuda

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

by NVlabs · GitHub
Stars
Forks
Created
Last commit
Cuda
Language
3d-reconstructioncomputer-graphicscomputer-visionCuda
View on GitHub
In plain words

Train and render 3D models quickly using advanced neural graphics techniques.

From the README

Install
$ git clone --recursive https://github.com/nvlabs/instant-ngp
$ cd instant-ngp

Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
instant-ngp — GitHub preview card
📈 Star history
17.49k17.45k
2026-06-282026-08-31
📈 Track instant-ngp

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Instant neural graphics primitives: lightning fast NeRF and more

instant-ngp has 17.5k stars on GitHub. It has been forked 2.1k times. instant-ngp is written mainly in Cuda. It has been in active development since 2022. Its main topics are 3d-reconstruction, computer-graphics, computer-vision, cuda.

Frequently asked questions

What is instant-ngp?

Instant neural graphics primitives: lightning fast NeRF and more

Is instant-ngp open source?

instant-ngp is an open-source project.

Is instant-ngp free?

Yes. instant-ngp is free and open source — you can use, modify and self-host it.

What language is instant-ngp written in?

instant-ngp is written mainly in Cuda.

🏅 Maintainer of this project?
olud.ai badge — instant-ngp

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=nvlabs-instant-ngp)](https://olud.ai/project/nvlabs-instant-ngp.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
ScanNet
2.3k · 3d-reconstruction
sharescomputer-graphics3d-reconstruction
neural-rgbd-surface-reconstruction
Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"
631 · 3d-reconstruction
sharescomputer-graphics3d-reconstruction
humanrf
Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"
496 · 3d-reconstruction
sharescomputer-graphics3d-reconstruction
HashNeRF-pytorch
Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives:…
1k · 3d-reconstruction
sharescomputer-graphics3d-reconstruction
Instant-angelo
Instant-angelo: Build high-fidelity Digital Twin within 20 Minutes!
462 · 3d
sharescomputer-graphics3d-reconstruction
LichtFeld-Studio
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native ap…
3.4k · computer-graphics
sharescomputer-graphicscuda
Structured3D
[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
674 · 3d-reconstruction
sharescomputer-graphics3d-reconstruction
Skyfall-GS
[ECCV 2026] Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
927 · 3d-reconstruction
sharescomputer-graphics3d-reconstruction
ECON
[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration
1.2k · 3d-reconstruction
sharescomputer-graphics3d-reconstruction
neuralangelo
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 20…
4.6k · 3d-reconstruction
sharescomputer-graphics3d-reconstruction

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.