{"id":28449282,"url":"https://github.com/gpuopen-effects/fidelityfx-denoiser","last_synced_at":"2025-10-29T02:34:06.764Z","repository":{"id":62008801,"uuid":"315609568","full_name":"GPUOpen-Effects/FidelityFX-Denoiser","owner":"GPUOpen-Effects","description":"FidelityFX Denoiser","archived":false,"fork":false,"pushed_at":"2022-10-25T02:36:11.000Z","size":6932,"stargazers_count":144,"open_issues_count":3,"forks_count":20,"subscribers_count":14,"default_branch":"master","last_synced_at":"2025-06-06T14:07:35.301Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GPUOpen-Effects.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-11-24T11:21:59.000Z","updated_at":"2025-06-04T15:33:21.000Z","dependencies_parsed_at":"2022-10-25T03:45:17.895Z","dependency_job_id":null,"html_url":"https://github.com/GPUOpen-Effects/FidelityFX-Denoiser","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/GPUOpen-Effects/FidelityFX-Denoiser","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GPUOpen-Effects%2FFidelityFX-Denoiser","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GPUOpen-Effects%2FFidelityFX-Denoiser/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GPUOpen-Effects%2FFidelityFX-Denoiser/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GPUOpen-Effects%2FFidelityFX-Denoiser/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GPUOpen-Effects","download_url":"https://codeload.github.com/GPUOpen-Effects/FidelityFX-Denoiser/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GPUOpen-Effects%2FFidelityFX-Denoiser/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262888818,"owners_count":23380111,"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":"2025-06-06T14:07:36.031Z","updated_at":"2025-10-29T02:34:01.727Z","avatar_url":"https://github.com/GPUOpen-Effects.png","language":"C","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FidelityFX Denoiser\n\nCopyright (c) 2021 Advanced Micro Devices, Inc. All rights reserved.\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\nThe above copyright notice and this permission notice shall be included in\nall copies or substantial portions of the Software.\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN\nTHE SOFTWARE.\n\n## Overview\n\nFidelityFX Denoiser contains a collection of highly optimized denoiser implementations for specific use cases.\n\n## FidelityFX Shadow Denoiser\n\nA spatio-temporal denoiser for raytraced soft shadows. It is intended to be used on a shadow mask that was created from at most one jittered shadow ray per pixel.\nIt makes use of a tile classification pass to skip work on areas without spatial variance in the shadow mask.\nIn cases of low temporal sample counts, the contribution from the spatial filters are increased, which successively cools off as the temporal sample count increases.\nThe denoiser aims to avoid ghosting artifacts by analyzing the local pixel neighborhood and clamping the accumulated history.\n\n### Links\n\n- ffx-shadows-dnsr contains the [Shadow Denoiser](https://github.com/GPUOpen-Effects/FidelityFX-Denoiser/tree/master/ffx-shadows-dnsr)\n\n## FidelityFX Reflection Denoiser\n\nThe reflection denoiser includes a high performance spatio-temporal denoiser specialized for reflection denoising.\nThe preferred use case of this denoiser is within applications requiring denoised radiance values generated by some stochastic reflection implementation.\nExamples of stochastic reflections:\n- Stochastic Screen Space Reflections\n- Stochastic Raytraced Reflections\n\n### Links\n\n- ffx-reflection-dnsr contains the [Reflection Denoiser](https://github.com/GPUOpen-Effects/FidelityFX-Denoiser/tree/master/ffx-reflection-dnsr)\n- Visit [FidelityFX SSSR](https://github.com/GPUOpen-Effects/FidelityFX-SSSR/tree/master/sample) to see the reflection denoiser in action.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgpuopen-effects%2Ffidelityfx-denoiser","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgpuopen-effects%2Ffidelityfx-denoiser","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgpuopen-effects%2Ffidelityfx-denoiser/lists"}