{"id":22407634,"url":"https://github.com/xavierjiezou/pmaa","last_synced_at":"2025-07-31T19:31:48.486Z","repository":{"id":184759824,"uuid":"672432948","full_name":"XavierJiezou/PMAA","owner":"XavierJiezou","description":"Official PyTorch implementation of \"PMAA: A Progressive Multi-scale Attention Autoencoder Model for High-Performance Cloud Removal from Multi-temporal Satellite Imagery\" (ECAI 2023).","archived":false,"fork":false,"pushed_at":"2023-08-23T01:56:19.000Z","size":34078,"stargazers_count":13,"open_issues_count":2,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-01-29T20:33:49.196Z","etag":null,"topics":["attention","autoencoder","cloud-removal","generative-model","image-processing","image-restoration","lightweight","low-level-vision","remote-sensing"],"latest_commit_sha":null,"homepage":"https://xavierjiezou.github.io/PMAA/","language":"JavaScript","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/XavierJiezou.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}},"created_at":"2023-07-30T04:17:29.000Z","updated_at":"2023-12-19T09:32:17.000Z","dependencies_parsed_at":null,"dependency_job_id":"a70899fb-7c09-4d4c-88ef-dab3a55e80f3","html_url":"https://github.com/XavierJiezou/PMAA","commit_stats":{"total_commits":11,"total_committers":2,"mean_commits":5.5,"dds":0.09090909090909094,"last_synced_commit":"2af430ca4af22477eb1428fd08e6e5b1e62e393f"},"previous_names":["xavierjiezou/pmaa"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XavierJiezou%2FPMAA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XavierJiezou%2FPMAA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XavierJiezou%2FPMAA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XavierJiezou%2FPMAA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/XavierJiezou","download_url":"https://codeload.github.com/XavierJiezou/PMAA/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228283750,"owners_count":17896267,"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":["attention","autoencoder","cloud-removal","generative-model","image-processing","image-restoration","lightweight","low-level-vision","remote-sensing"],"created_at":"2024-12-05T11:14:56.812Z","updated_at":"2025-07-31T19:31:48.464Z","avatar_url":"https://github.com/XavierJiezou.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n    \u003cimg alt=\"logo\" src=\"image/README/ecai23.png\" /\u003e\n\u003ch1 align=\"center\"\u003ePMAA: A Progressive Multi-scale Attention Autoencoder Model for High-Performance Cloud Removal from Multi-temporal Satellite Imagery\u003c/h1\u003e\n\u003cp align=\"center\"\u003eThis repository is the official PyTorch implementation of the accepted paper PMAA of ECAI 2023 Oral.\n\u003c/p\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://blog.csdn.net/qq_42951560\"\u003eXuechao Zou\u003csup\u003e1,*\u003c/sup\u003e\u003c/a\u003e,\n    \u003ca href=\"https://cslikai.cn/\"\u003eKai Li\u003csup\u003e2,*\u003c/sup\u003e\u003c/a\u003e,\n    \u003ca href=\"https://www.cs.tsinghua.edu.cn/info/1116/5088.htm\"\u003eJunliang Xing\u003csup\u003e2\u003c/sup\u003e\u003c/a\u003e,\n    \u003ca href=\"https://www.cs.tsinghua.edu.cn/info/1117/3542.htm\"\u003ePin Tao\u003csup\u003e1,2,†\u003c/sup\u003e\u003c/a\u003e,\n    \u003ca href=\"https://cs.qhu.edu.cn/jxgz/jxysz/szgk/22173.htm\"\u003eYachao Cui\u003csup\u003e1\u003c/sup\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://www.qhu.edu.cn/\"\u003eQinghai University\u003c/a\u003e\u003csup\u003e1\u003c/sup\u003e\n    •\n    \u003ca href=\"https://www.tsinghua.edu.cn/\"\u003eTsinghua University\u003c/a\u003e\u003csup\u003e2\u003c/sup\u003e\n  \u003c/p\u003e\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://arxiv.org/abs/2303.16565\"\u003ePaper Preprint \u003c/a\u003e\n    |\n    \u003ca href=\"https://xavierjiezou.github.io/PMAA\"\u003eProject Page\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n\u003c!-- Optional: include a graphic explaining your approach/main result, bibtex entry, link to demos, blog posts and tutorials --\u003e\n\n![pmaa](image/README/pmaa.png)\n\n\u003c!-- ![transformer+lim](image/README/transformer+lim.png) --\u003e\n\u003c/p\u003e\n\n## News\n\n- [2023/07/30] Code release.\n- [2023/07/16] PMAA got accepted by ECAI 2023 Oral.\n- [2023/03/29] PMAA is on arXiv now.\n\n## Requirements\n\nTo install dependencies:\n\n```setup\npip install -r requirements.txt\n```\n\n\u003c!-- \u003e📋  Describe how to set up the environment, e.g. pip/conda/docker commands, download datasets, etc... --\u003e\n\nTo download datasets:\n\n- _Sen2_MTC_Old_: [multipleImage.tar.gz](https://doi.org/10.7910/DVN/BSETKZ)\n\n- _Sen2_MTC_New_: [CTGAN.zip](https://drive.google.com/file/d/1-hDX9ezWZI2OtiaGbE8RrKJkN1X-ZO1P/view?usp=share_link)\n\n## Training\n\nTo train the models in the paper, run these commands:\n\n```train\npython train_old.py\npython train_new.py\n```\n\n\u003c!-- \u003e📋  Describe how to train the models, with example commands on how to train the models in your paper, including the full training procedure and appropriate hyperparameters. --\u003e\n\n## Evaluation\n\nTo evaluate my models on two datasets, run:\n\n```eval\npython test_old.py\npython test_new.py\n```\n\n\u003c!-- \u003e📋  Describe how to evaluate the trained models on benchmarks reported in the paper, give commands that produce the results (section below). --\u003e\n\n## Pre-trained Models\n\nYou can download pretrained models here:\n\n- Our awesome model trained on _Sen2_MTC_old_: [pmaa_old.pth](/pretrained/pmaa_old.pth)\n- Our awesome model trained on _Sen2_MTC_new_: [pmaa_new.pth](/pretrained/pmaa_new.pth)\n\n\u003c!-- \u003e📋  Give a link to where/how the pretrained models can be downloaded and how they were trained (if applicable).  Alternatively you can have an additional column in your results table with a link to the models. --\u003e\n\n## Results\n\n![res](image/README/res.png)\n\n### Quantitative Results\n\n![exp](image/README/exp.png)\n\n### Qualitative Results\n\n![vis](image/README/vis.png)\n\n\u003c!-- \u003e📋  Include a table of results from your paper, and link back to the leaderboard for clarity and context. If your main result is a figure, include that figure and link to the command or notebook to reproduce it.  --\u003e\n\n\u003c!-- ## Contact\n\nIf you have any questions, please contact: xuechaozou@foxmail.com --\u003e\n\n## Citation\n\nIf you use our code or models in your research, please cite with:\n\n```latex\n@article{zou2023pmaa,\n  title={PMAA: A Progressive Multi-scale Attention Autoencoder Model for High-Performance Cloud Removal from Multi-temporal Satellite Imagery},\n  author={Zou, Xuechao and Li, Kai and Xing, Junliang and Tao, Pin and Cui, Yachao},\n  journal={European Conference on Artificial Intelligence (ECAI)},\n  year={2023},\n  pages={3165-3172},\n}\n```\n\n\u003c!-- \u003e📋  Pick a licence and describe how to contribute to your code repository.  --\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxavierjiezou%2Fpmaa","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxavierjiezou%2Fpmaa","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxavierjiezou%2Fpmaa/lists"}