{"id":19248559,"url":"https://github.com/NVIDIA-RTX/RTXGI","last_synced_at":"2025-09-10T18:31:45.553Z","repository":{"id":228470141,"uuid":"771592385","full_name":"NVIDIAGameWorks/RTXGI","owner":"NVIDIAGameWorks","description":"RTXGI v2.0 Update including Neural Radiance Cache and Spatial Hash Radiance Cache ","archived":false,"fork":false,"pushed_at":"2024-03-19T15:04:58.000Z","size":17934,"stargazers_count":106,"open_issues_count":0,"forks_count":7,"subscribers_count":20,"default_branch":"main","last_synced_at":"2024-05-21T14:05:19.216Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"CMake","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NVIDIAGameWorks.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-03-13T15:26:15.000Z","updated_at":"2024-06-03T18:09:51.045Z","dependencies_parsed_at":"2024-06-03T18:23:17.900Z","dependency_job_id":null,"html_url":"https://github.com/NVIDIAGameWorks/RTXGI","commit_stats":null,"previous_names":["nvidiagameworks/rtxgi"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2FRTXGI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2FRTXGI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2FRTXGI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIAGameWorks%2FRTXGI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIAGameWorks","download_url":"https://codeload.github.com/NVIDIAGameWorks/RTXGI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":232552495,"owners_count":18540809,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-09T18:08:48.446Z","updated_at":"2025-09-10T18:31:38.628Z","avatar_url":"https://github.com/NVIDIAGameWorks.png","language":"CMake","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RTXGI\n![banner](docs/figures/banner.png)\n\u003cbr /\u003e\n\u003cdiv align=\"center\"\u003e\n    · \n    \u003ca href=\"CHANGELOG.md\"\u003eChange Log\u003c/a\u003e\n    ·\n    \u003ca href=\"docs/QuickStart.md\"\u003eQuick Start\u003c/a\u003e\n    ·\n    \u003ca href=\"docs/NrcGuide.md\"\u003eNRC Guide\u003c/a\u003e\n    ·\n    \u003ca href=\"docs/SharcGuide.md\"\u003eSHaRC Guide\u003c/a\u003e\n    ·\n\u003c/div\u003e\n\u003cbr/\u003e\n\nAdvances in path tracing techniques have allowed for the capture of lighting data from the environment, enabling the use of indirect illumination in real-time with both improved accuracy and speed. RTXGI SDK implements two such techniques, replacing traditional probe-based irradiance caching with a world-space radiance cache which can be used to sample outgoing radiance each time scene geometry is hit during path tracing. \n\nThese techniques may be combined with a regular path tracing pipeline for the primary rays, sampling cached data only for indirect bounce evaluation. By replacing the whole path trace with a single ray hit evaluation and cache lookup, the cost is reduced with little to no compromise in signal quality, while remaining responsive to change and supporting large-scale dynamic scenes with complex lighting setups. \n\nRTXGI SDK provides an example integration (DX12 and Vulkan) of two state-of-the-art radiance caching techniques for path tracing - a (currently experimental) AI-based approach known as Neural Radiance Cache (NRC), and Spatially Hashed Radiance Cache (SHaRC). The former requires Tensor Cores while the latter has certain limitations but is currently supported on a wider range of hardware without any vendor-specific requirements. RTXGI SDK also hosts documentation and distribution corresponding to both of these techniques, see [Project Structure][ProjectStructure] section for further details.\n\n\n## Project structure\n|Directory                   |Details                                      |\n|----------------------------|---------------------------------------------|\n|[/docs][docs]               |_Documentation for showcased tech_           |\n|[/donut][donut]             |_Framework used for the samples_             |\n|[/external][external]       |_Helper dependencies for the samples_        |\n|[/media][media]             |_Assets and scene definitions_               |\n|[/samples][samples]         |_Samples showcasing usage of NRC, SHaRC_     |\n|[/sdk-libraries][libraries] |_Binaries, src, includes for NRC, SHaRC_     |\n\n\n## Getting up and running\n\n### Prerequisites\nAny DXR GPU for SHaRC **|** NV GPUs ≥ Turing (arch 70) for NRC **|** [CMake v3.24.3][CMake] **|** [Git LFS][LFS] **|** [Vulkan SDK 1.3.268.0][VKSDK] **|** [VS 2022][VS22] **|** Windows SDK ≥ 10.0.20348.0 **|** Driver ≥ 555.85\n\n### Further steps\n- [Quick start guide][QuickStart] for building and running the pathtracer example.\n- [NRC integration guide][NrcGuide] and the [SHaRC integration guide][SharcGuide] respectively.\n- [Change log][ChangeLog] for release information.\n\n## Contact\nRTXGI SDK is actively being developed. Please report any issues directly through the GitHub issue tracker, and for any information or suggestions contact us at rtxgi-sdk-support@nvidia.com.\n\n## Citation\nUse the following BibTex entry to cite the usage of RTXGI in published research:\n```bibtex\n@online{RTXGI,\n   title   = {{{NVIDIA}}\\textregistered{} {RTXGI}},\n   author  = {{NVIDIA}},\n   year    = 2024,\n   url     = {https://github.com/NVIDIAGameWorks/RTXGI},\n   urldate = {2024-03-18},\n}\n```\n\n## License\nSee [LICENSE.md](LICENSE.md)\n\n## RTXGI v1.x\nVersion v1.x of RTXGI which includes the DDGI algorithm is located in a separate repo at the following url: https://github.com/NVIDIAGameWorks/RTXGI-DDGI\".\n\n\n[ChangeLog]: CHANGELOG.md\n[QuickStart]: docs/QuickStart.md\n[SharcGuide]: docs/SharcGuide.md\n[NrcGuide]: docs/NrcGuide.md\n[ProjectStructure]: #project-structure\n[docs]: docs\n[donut]: donut\n[external]: external\n[media]: media\n[samples]: samples/pathtracer\n[libraries]: sdk-libraries\n[CMake]: https://cmake.org/download/\n[LFS]: https://git-lfs.com/\n[VKSDK]: https://vulkan.lunarg.com/sdk/home#windows\n[VS22]: https://visualstudio.microsoft.com/vs/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIA-RTX%2FRTXGI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FNVIDIA-RTX%2FRTXGI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIA-RTX%2FRTXGI/lists"}