NVlabs /instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
★ 17,602⑂ 2,067👁 198⑃ 163● 1,038▤ 2
+2
日增长
+16
周增长
+25
月增长
17,602
stars
2,067
forks
198
watchers
163
prs
1,038
issues
2
releases
README
Instant Neural Graphics Primitives ! Ever wanted to train a NeRF model of a fox in under 5 seconds? Or fly around a scene captured from photos of a factory robot? Of course you have! Here you will find an implementation of four __neural graphics primitives__, being neural radiance fields (NeRF), signed distance functions (SDFs), neural images, and neural volumes. In each case, we train and render a MLP with multiresolution hash input encoding using the __tiny-cuda-nn__ framework. __Instant Neural Graphics Primitives with a Multiresolution Hash Encoding__ Thomas Müller, Alex Evans, Christoph Schied, Alexander Keller _ACM Transactions on Graphics (__SIGGRAPH__), July 2022_ __Project page / Paper / Video / Presentation / Real-Time Live / BibTeX__ For business inquiries, please submit the NVIDIA research licensing form. Installation If you have Windows, download one of the following releases corresponding to your graphics card and extract it. Then, start instant-ngp.exe. - RTX 5000 series and other Blackwell cards - RTX 3000 & 4000 series, RTX A4000–A6000, and other Ampere & Ada cards - RTX 2000 series, Titan RTX, Quadro RTX 4000–8000, and other Turing cards - GTX 1000 series, Titan Xp, Quadro P1000–P6000, and other Pascal cards Keep reading for a guided tour of the application or, if you are interested in creating your own NeRF, watch the video tutorial or read the written instructions. If you use Linux, or want the developer Python bindings, or if your GPU is not listed above (e.g. Hopper, Volta, or Maxwell generations), you need to build __instant-ngp__ yourself. Usage __instant-ngp__ comes with an interactive GUI that includes many features: - comprehensive controls for interactively exploring neural graphics primitives, - VR mode for viewing neural graphics primitives through a virtual-reality headset, - saving and loading "snapshots" so you can share your graphics primitives on the internet, - a camera path editor to create videos, - NeRF-Mesh and SDF-Mesh conversion, - camera pose and lens optimization, - and many more. NeRF fox Simply start instant-ngp and drag the data/nerf/fox folder into the window. Or, alternatively, use the command line: sh instant-ngp$ ./instant-ngp data/nerf/fox You can use __any__ NeRF-compatible dataset, e.g. from original NeRF, the SILVR dataset, or the DroneDeploy dataset. To create your own NeRF, watch the video tutorial or read the written instructions. SDF armadillo Drag data/sdf/armadillo.obj into the window or use the command: sh instant-ngp$ ./instant-ngp data/sdf/armadillo.obj Image of Einstein Drag data/image/albert.exr into the window or use the command: sh instant-ngp$ ./instant-ngp data/image/albert.exr To reproduce the gigapixel results, download, for example, the Tokyo image and convert it to .bin using the scripts/convert_image.py script. This custom format improves compatibility and loading speed when res
Top issues
#1219cutlass_matmul.h:332 status failed with error Error Internal29 comments · 2023-02-03#1095how to add the depth map from colmap to instant-ngp ?29 comments · 2022-11-29#727How can i import camera animation/path from other software?28 comments · 2022-06-29#939depth loss question22 comments · 2022-09-08#1345Wrong dimensions of mesh file17 comments · 2023-05-09#1142MAKE_CUDA_ARCHITECTURES must be non-empty if set.17 comments · 2022-12-28#1108failed with error CUDA_ERROR_OUT_OF_MEMORY14 comments · 2022-12-02#1318Can't build testbed.cu:175:23: error: no match for ‘operator='13 comments · 2023-04-06
Discussions
#1610introducing physically based rendering0 comments · 2025-12-15#1604Instants-ngp Output Issue After Reality Scan and Colmap1 comments · 2025-08-22#1598Blocky and incomplete mesh output despite good input0 comments · 2025-07-04#1595I can't run orange data mining on ubuntu0 comments · 2025-05-20#1593KinfuTracker camera pose to instant-ngp0 comments · 2025-03-28#1571I'm inquiring about debugging.0 comments · 2024-10-03#1568How can i export the mesh?0 comments · 2024-09-07#1561Is it possible to convert the 'fox/transforms_base.ingp' file to '.obj' using the run.py script?0 comments · 2024-07-30
Latest release
Version 2.0 v2.0 2025-07-08Instant NGP just got 5x faster at rendering and 1.5x faster at training! The speedup comes from a new just-in-time (JIT) compiler in tiny-cuda-nn, the neural network library that Instant NGP is based on; see tiny-cuda-nn's 2.0 release notes. Using this new JIT compiler, Instant NGP fuses the entire NeRF ray marcher, as well as several other core components, into single CUDA kernels. That is to say: the 5x speed-up comes from optimization through fusion rather than algorithmic changes. Therefore all existing snapshots, and configurations still work unmodified. How to use the new Insta