{"full_name":"NVlabs/instant-ngp","owner":"NVlabs","name":"instant-ngp","shard":"1","url":"https://github.com/NVlabs/instant-ngp","description":"Instant neural graphics primitives: lightning fast NeRF and more","homepage":"https://nvlabs.github.io/instant-ngp","topics":["neural-network","machine-learning","cuda","nerf","computer-graphics","computer-vision","3d-reconstruction","signed-distance-functions","function-approximation","real-time","realtime","real-time-rendering"],"tag_pages":["computer-vision","cuda","machine-learning","neural-network","real-time","realtime"],"language":"Cuda","license":"NOASSERTION","avatar":"https://avatars.githubusercontent.com/u/2695301?v=4","created_at":"2022-01-05T17:11:30Z","pushed_at":"2026-02-02T12:32:34Z","metrics":{"stars":17602,"forks":2067,"watchers":198,"issues":1038,"prs":163,"releases":2,"issues_open":492,"issues_closed":546,"prs_open":15,"prs_closed":43,"prs_merged":105,"discussions":355},"growth":{"day":{"stars":2,"forks":0,"base_day":"2026-11-15"},"week":{"stars":16,"forks":0,"base_day":"2026-11-04"},"month":{"stars":25,"forks":3,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[17541,17542,17543,17542,17542,17544,17546,17546,17546,17548,17550,17551,17551,17553,17554,17557,17558,17557,17558,17559,17559,17561,17562,17565,17565,17565,17566,17568,17569,17569,17568,17568,17568,17567,17567,17568,17570,17571,17573,17575,17577,17577,17577,17577,17576,17578,17577,17580,17579,17582,17583,17582,17582,17584,17583,17583,17585,17585,17585,17586,17590,17594,17595,17596,17598,17600,17602],"forks":[2064,2064,2064,2064,2064,2066,2066,2066,2066,2066,2067,2067,2067,2068,2068,2069,2068,2068,2069,2069,2069,2069,2069,2068,2068,2070,2070,2070,2070,2070,2070,2069,2069,2068,2068,2068,2068,2067,2066,2065,2064,2064,2064,2064,2064,2065,2065,2065,2065,2064,2064,2064,2064,2064,2064,2064,2065,2065,2065,2067,2065,2065,2067,2067,2067,2067,2067],"watchers":[201,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,202,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,203,198,198,198,198,198,198,198,198,198,198,198,null,198,198,198,198,198,198],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,492,492,492,492,492,492],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,15,15,15,15,15,15]},"boards":{},"same_owner":[{"full_name":"NVlabs/GraspGenX","name":"GraspGenX","shard":"1","boards":{}},{"full_name":"NVlabs/SPADE","name":"SPADE","shard":"1","boards":{}},{"full_name":"NVlabs/Sana","name":"Sana","shard":"1","boards":{}},{"full_name":"NVlabs/SoL-Pi","name":"SoL-Pi","shard":"1","boards":{"new":192}}],"issues":[{"number":1219,"title":"cutlass_matmul.h:332 status failed with error Error Internal","comments":29,"created_at":"2023-02-03T10:57:34Z"},{"number":1095,"title":"how to add the depth map from colmap to instant-ngp ?","comments":29,"created_at":"2022-11-29T02:07:51Z"},{"number":727,"title":"How can i import camera animation/path from other software?","comments":28,"created_at":"2022-06-29T22:40:37Z"},{"number":939,"title":"depth loss question","comments":22,"created_at":"2022-09-08T12:43:45Z"},{"number":1345,"title":"Wrong dimensions of mesh file","comments":17,"created_at":"2023-05-09T12:07:19Z"},{"number":1142,"title":"MAKE_CUDA_ARCHITECTURES must be non-empty if set.","comments":17,"created_at":"2022-12-28T07:37:18Z"},{"number":1108,"title":"failed with error CUDA_ERROR_OUT_OF_MEMORY","comments":14,"created_at":"2022-12-02T09:11:16Z"},{"number":1318,"title":"Can't build testbed.cu:175:23: error: no match for ‘operator='","comments":13,"created_at":"2023-04-06T17:46:51Z"}],"discussions":[{"number":1610,"title":"introducing physically based rendering","comments":0,"category":"Ideas / Feature requests","created_at":"2025-12-15T11:07:30Z"},{"number":1604,"title":"Instants-ngp Output Issue After Reality Scan and Colmap","comments":1,"category":"Q&A","created_at":"2025-08-22T07:50:56Z"},{"number":1598,"title":"Blocky and incomplete mesh output despite good input","comments":0,"category":"Q&A","created_at":"2025-07-04T16:34:42Z"},{"number":1595,"title":"I can't run orange data mining on ubuntu","comments":0,"category":"Q&A","created_at":"2025-05-20T18:21:49Z"},{"number":1593,"title":"KinfuTracker camera pose to instant-ngp","comments":0,"category":"Q&A","created_at":"2025-03-28T15:32:02Z"},{"number":1571,"title":"I'm inquiring about debugging.","comments":0,"category":"Q&A","created_at":"2024-10-03T08:13:19Z"},{"number":1568,"title":"How can i export the mesh?","comments":0,"category":"Q&A","created_at":"2024-09-07T23:24:42Z"},{"number":1561,"title":"Is it possible to convert the 'fox/transforms_base.ingp' file to '.obj' using the run.py script?","comments":0,"category":"Q&A","created_at":"2024-07-30T04:55:45Z"}],"latest_release":{"name":"Version 2.0","tag":"v2.0","published_at":"2025-07-08T12:06:02Z","body":"Instant NGP just got 5x faster at rendering and 1.5x faster at training!\r\n\r\nThe 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](https://github.com/NVlabs/tiny-cuda-nn/releases/tag/v2.0).\r\n\r\nUsing 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.\r\n\r\n## How to use the new Instant NGP 2.0\r\n\r\nIf you are on Windows, simply download the [latest release](https://github.com/nvlabs/instant-ngp?tab=readme-ov-file#installation).\r\n\r\nOn Linux, pull the latest source code, make sure submodules are up-to-date, and compile.\r\n```sh\r\n$ git pull\r\n$ git submodule sync --recursive\r\n$ git submodule update --init --recursive\r\n$ <compile per instructions in README.md>\r\n```\r\n\r\nTo confirm that you are running Instant NGP 2.0, make sure that the GUI's title bar says \"instant-ngp v2.0dev\" and that there is a \"JIT fusion\" checkbox. See the screenshot below.\r\n![image](https://github.com/user-attachments/assets/a27a5b6a-5c6a-407a-8f95-a9a852e99fb1)\r\n\r\nToggle the \"JIT fusion\" checkbox to compare the new faster implementation with the old one. On RTX 4000 cards (Ada generation) or newer, the rendering speed up should be over 5x.\r\n\r\n\r\n## Other additions and changes since last release\r\n\r\n- Added more interpolation modes for camera paths, as well as live recording of keyframes\r\n- Added Python bindings for camera path editing\r\n- Added support for orthographic camera lenses\r\n- All camera lens types except for `FTheta` now support DLSS\r\n- All camera lens types can now be used in SDF, Image, and Volume modes (not just NeRF)\r\n- Fixed various miscellaneous bugs in the build system and Instant NGP itself\r\n- Glow has been removed\r\n","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}