{"id":12493875,"url":"https://github.com/dhryougit/AFM","last_synced_at":"2025-10-30T19:31:43.063Z","repository":{"id":248212057,"uuid":"778805333","full_name":"dhryougit/AFM","owner":"dhryougit","description":null,"archived":false,"fork":false,"pushed_at":"2024-11-12T04:53:24.000Z","size":577,"stargazers_count":25,"open_issues_count":2,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-11-12T05:25:27.741Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/dhryougit.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-03-28T12:48:27.000Z","updated_at":"2024-11-12T04:53:27.000Z","dependencies_parsed_at":"2024-07-13T06:22:50.231Z","dependency_job_id":"076506b3-e405-4d2b-aaaf-1cde6e7ca9f9","html_url":"https://github.com/dhryougit/AFM","commit_stats":null,"previous_names":["dhryougit/afm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhryougit%2FAFM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhryougit%2FAFM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhryougit%2FAFM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhryougit%2FAFM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dhryougit","download_url":"https://codeload.github.com/dhryougit/AFM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239044842,"owners_count":19572738,"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":"2024-07-13T06:03:02.396Z","updated_at":"2025-10-30T19:31:42.601Z","avatar_url":"https://github.com/dhryougit.png","language":"Python","funding_links":[],"categories":["Beyond Vision"],"sub_categories":["**Other**"],"readme":"\u003c!-- The official pytorch implementation of the paper **[Simple Baselines for Image Restoration (ECCV2022)](https://arxiv.org/abs/2204.04676)** --\u003e\n\n# Robust Image Denoising through Adversarial Frequency Mixup (2024 CVPR) [[paper]](https://openaccess.thecvf.com/content/CVPR2024/html/Ryou_Robust_Image_Denoising_through_Adversarial_Frequency_Mixup_CVPR_2024_paper.html)\n\n\n## Installation\nThis implementation based on [BasicSR](https://github.com/xinntao/BasicSR) which is a open source toolbox for image/video restoration tasks and [NAFNet](https://github.com/megvii-research/NAFNet) \n\n```python\npython 3.8.8\npytorch 1.9.0\ncuda 11.3\n```\n\n```\ngit clone https://github.com/dhryougit/AFM.git\ncd AFM\npip install -r requirements.txt\npython setup.py develop --no_cuda_ext\n```\n\nWe used NVIDIA RTX A6000 D6 48GB for trianing our models.\u003cbr\u003e\u003cbr\u003e\n\n\n## QuickStart\nFor training \n```\npython3 -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 basicsr/train.py -opt options/train/DnCNN.yml --name=DnCNN-afm-b --afm_type=AFM_B --seed=10 --afm_rate=0.8 --afm_easy_rate=0.3 --launcher pytorch\n```\n\u003cbr\u003e\n\nFor test\n```\npython3 -m torch.distributed.launch --nproc_per_node=1 basicsr/test.py -opt options/test/DnCNN.yml -name=AFM_test --launcher pytorch\n```\n\u003cbr\u003e\n\n## Dataset\n\nTraining dataset : [SIDD](https://abdokamel.github.io/sidd/#sidd-medium)\n\nEvaluation datasets : [Poly](https://github.com/csjunxu/PolyU-Real-World-Noisy-Images-Dataset), [CC](https://github.com/csjunxu/MCWNNM-ICCV2017), HighISO, iPhone, Huawei.\n\nAdditioanl real-world noise datasets can be downloaded from \"https://github.com/ZhaomingKong/Denoising-Comparison\"\u003cbr\u003e\u003cbr\u003e\n\n\n\n## Results and Pre-trained model\n\n\n| Dataset | Poly |CC |HighISO |iPhone |Huawei | OOD Avg.|\n|:----|:----|:----|:----|:----|:----|-----|\n|PSRN| 37.75  | 36.84 | 39.17   | 40.65   | 38.39   | 38.56   |\n|SSIM| 0.9804 | 0.9830 | 0.9801  | 0.9777  | 0.9683  | 0.9779  |\n\nPre-trained model of our Dncnn trained on AFM-B can be downloaded from (https://drive.google.com/file/d/1uPJP2zNc4ViFc1QU7TXGAwrFIEScBJvL/view?usp=sharing)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdhryougit%2FAFM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdhryougit%2FAFM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdhryougit%2FAFM/lists"}