{"id":20373502,"url":"https://github.com/megengine/nbnet","last_synced_at":"2025-04-12T06:51:50.436Z","repository":{"id":63176122,"uuid":"343448126","full_name":"MegEngine/NBNet","owner":"MegEngine","description":"NBNet: Noise Basis Learning for Image Denoising with Subspace Projection","archived":false,"fork":false,"pushed_at":"2021-09-23T10:50:54.000Z","size":1916,"stargazers_count":154,"open_issues_count":13,"forks_count":23,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-12T06:51:45.305Z","etag":null,"topics":["denoise","megengine"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MegEngine.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-03-01T14:37:46.000Z","updated_at":"2025-03-20T16:04:08.000Z","dependencies_parsed_at":"2022-11-14T11:01:45.602Z","dependency_job_id":null,"html_url":"https://github.com/MegEngine/NBNet","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MegEngine%2FNBNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MegEngine%2FNBNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MegEngine%2FNBNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MegEngine%2FNBNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MegEngine","download_url":"https://codeload.github.com/MegEngine/NBNet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248530604,"owners_count":21119595,"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":["denoise","megengine"],"created_at":"2024-11-15T01:18:41.933Z","updated_at":"2025-04-12T06:51:50.411Z","avatar_url":"https://github.com/MegEngine.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NBNet: Noise Basis Learning for Image Denoising with Subspace Projection \n\nCode for CVPR21 paper [NBNet](https://arxiv.org/abs/2012.15028).\n\n\u003cu\u003e*The illustration of our key insight:*\u003c/u\u003e\n\n\u003cimg src=\"./Fig/fig2.png\" alt=\"projection_concept\" style=\"zoom:100%;\" /\u003e\n\n## Dependencies\n\n- MegEngine \u003e= 1.3.1 (For DistributedDataParallel)\n\n\n\n## Training\n\n### Preparation\n\n```\npython prepare_data.py --data_dir yours_sidd_data_path\n```\n\n\n\n### Begin training:\n\nFor SIDD benchmark,  use:\n\n```\npython train_mge.py -d prepared_data_path -n num_gpus\n```\n\n\n\nFor DnD benchmark,  we use MixUp additionally:\n\n```\npython train_mge.py -d prepared_data_path -n num_gpus --dnd\n```\n\n### Begin testing:\nDownload the pretrained checkpoint and use:\n\n```\npython test.py -d prepared_data_path -c checkpoint_path\n```\nThe result is **PSNR 39.765**.\n\n\n\n## Pretrained model\n\nMegEngine checkpoint for SIDD benchmark can be downloaded via \n[Google Drive](https://drive.google.com/file/d/1RPAf9ZJqqq9ePPVTtJRlixX4-h3HJTCc/view?usp=sharing)\nor\n[GitHub Release](https://github.com/megvii-research/NBNet/releases).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmegengine%2Fnbnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmegengine%2Fnbnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmegengine%2Fnbnet/lists"}