instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

View on GitHub↗Upstream NVlabs/instant-ngp↗

Builder

NVlabs

NVlabs • individual

Stars

17,350

Using upstream star count

Forks

2,059

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Jan 5, 2022

Project creation date

README Summary

Instant-ngp is NVIDIA's implementation of instant neural graphics primitives that can train Neural Radiance Fields (NeRF) in seconds rather than hours. The repository provides lightning-fast neural rendering for 3D scenes, images, and neural signed distance functions using multi-resolution hash encoding. It includes CUDA implementations optimized for modern GPUs to achieve real-time performance.

AI Dev Skills

Unmapped

Tags

Neural Radiance Fields (NeRF)3D Scene ReconstructionNovel View SynthesisMulti-resolution Hash EncodingVolume RenderingNeural Graphics PrimitivesCUDA GPU ProgrammingReal-time 3D RenderingComputer VisionDeep Learning for GraphicsFilm/VFXDifferentiable RenderingOn-premise3DImmersive Media ProductionDigital Twin CreationSelf-hostedAutonomous VehiclesRobotics3D Content GenerationReal-time AI GraphicsPhotogrammetry EnhancementVideoImageReal EstateGamingNeural Rendering3D Asset GenerationAR/VRArchitectureVirtual Reality Content Creation3D Scene Reconstruction from PhotosEntertainmentCuda

Recent Activity

Updated 2 months ago

7 Days

30 Days

90 Days

Quality

research

Quality: high
Maturity: research

PM Skills

Developer Platform

Languages

Cuda100.0%

Timeline

Project created: Jan 5, 2022
Forked: Mar 22, 2026
Your last push: 2 months ago
Upstream last push: 2 months ago
Tracked since: Feb 2, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…