{"id":25698032,"url":"https://github.com/hi-tech-ai/watermark-remove","last_synced_at":"2026-06-17T11:31:52.867Z","repository":{"id":233039078,"uuid":"785866900","full_name":"hi-tech-AI/watermark-remove","owner":"hi-tech-AI","description":"Watermark Removal using TensorFlow","archived":false,"fork":false,"pushed_at":"2025-02-14T16:14:55.000Z","size":1627,"stargazers_count":1,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"tensorflow","last_synced_at":"2025-02-25T02:40:30.735Z","etag":null,"topics":["artefact-removal","deep-learning","skip-connections","tensorflow","watermark","watermark-detection","watermark-removal"],"latest_commit_sha":null,"homepage":"","language":"Python","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/hi-tech-AI.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":"2024-04-12T19:48:20.000Z","updated_at":"2025-02-14T16:16:35.000Z","dependencies_parsed_at":"2024-08-08T09:21:52.417Z","dependency_job_id":null,"html_url":"https://github.com/hi-tech-AI/watermark-remove","commit_stats":null,"previous_names":["morning120429/watermark-remove","hi-tech-ai/watermark-remove","py-master-dev/watermark-remove"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hi-tech-AI/watermark-remove","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-tech-AI%2Fwatermark-remove","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-tech-AI%2Fwatermark-remove/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-tech-AI%2Fwatermark-remove/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-tech-AI%2Fwatermark-remove/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hi-tech-AI","download_url":"https://codeload.github.com/hi-tech-AI/watermark-remove/tar.gz/refs/heads/tensorflow","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-tech-AI%2Fwatermark-remove/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34447264,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-17T02:00:05.408Z","response_time":127,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["artefact-removal","deep-learning","skip-connections","tensorflow","watermark","watermark-detection","watermark-removal"],"created_at":"2025-02-25T02:37:37.670Z","updated_at":"2026-06-17T11:31:52.852Z","avatar_url":"https://github.com/hi-tech-AI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Watermark-Removal\n\n![version](https://img.shields.io/badge/version-v1.0.0-green.svg?style=plastic)\n![pytorch](https://img.shields.io/badge/tensorflow-v1.15.0-green.svg?style=plastic)\n![license](https://img.shields.io/badge/license-CC_BY--NC-green.svg?style=plastic)\n\nAn open source project that uses a machine learning based image inpainting methodology to remove watermark from images which is totally indistinguishable from the ground truth version of the image.\n\nThis project was inspired by the [Contextual Attention](https://arxiv.org/abs/1801.07892) (CVPR 2018) and [Gated Convolution](https://arxiv.org/abs/1806.03589) (ICCV 2019 Oral).\n\n\u003cimg src=\"https://user-images.githubusercontent.com/51057490/140277713-c7d6e2b9-db62-4793-823a-25ed0c4e2771.png\" width=\"45%\"/\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140277781-5b5218bb-9044-4ec9-a349-eea93bc56d4a.png\" width=\"45%\"/\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140277929-3f187647-0e63-4bcb-b9f1-472f7558aae5.jpeg\" width=\"45%\"/\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140277957-6ddb7dec-25c8-42f1-8e39-be491d4f2248.png\" width=\"45%\"/\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140277983-265a1c9e-6093-4154-8252-838baca21c41.jpeg\" width=\"45%\" /\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140278002-56c4ae3d-6bfb-4ba3-aa02-7bd28474bfdf.png\" width=\"45%\" /\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140278030-d2a962ce-3722-43f1-b1bd-0ffde2aa7026.jpeg\" width=\"45%\" /\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140278040-10e401d7-4b7d-4d81-91fe-e9f01ef4ce7f.png\" width=\"45%\" /\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140278017-34862de0-86eb-40f0-b04b-7dc02fe38a77.jpeg\" width=\"45%\" /\u003e \u003cimg src=\"https://user-images.githubusercontent.com/51057490/140278011-e0ae9ed0-e4ed-44ed-a9ac-28eb8456797a.png\" width=\"45%\" /\u003e\n\n## Run\n\n- use [Google colab](https://research.google.com/colaboratory/)\n\n- First of all, clone this repo\n\n      git clone https://github.com/morning120429/watermark-remove\n\n- Change Directory to the repo\n\n      cd watermark-removal\n\n- Change Python version to 3.7 because tensorflow 1.15.0 does not support Python 3.8 or higher\n\n- Since Google Colab uses the latest Tensorflow 2x version and this project uses 1.15.0, downgrade to Tensorflow 1.15.0 version and restart the runtime, (`although the new version of Google Colab does not need you to restart the runtime`).\n\n      pip install tensorflow==1.15.0\n\n- Install OpenCV 4.9.0.80\n\n      pip install opencv-python==4.9.0.80\n\n- Install tensorflow toolkit [neuralgym](https://github.com/JiahuiYu/neuralgym).\n\n      pip install git+https://github.com/JiahuiYu/neuralgym\n\n- Download the model dirs using this [link](https://drive.google.com/drive/folders/1xRV4EdjJuAfsX9pQme6XeoFznKXG0ptJ?usp=sharing) and put it under `model/` (rename `checkpoint.txt` to `checkpoint` because sometimes google drive automatically adds .txt after download)\n\nAnd you're all Set!!\n\n- Now remove the watermark on the image by runing the `main.py` file\n\n      python main.py --image path-to-input-image --output path-to-output-image --checkpoint_dir model/ --watermark_type istock\n\n## Citing\n\n```\n@article{yu2018generative,\n  title={Generative Image Inpainting with Contextual Attention},\n  author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},\n  journal={arXiv preprint arXiv:1801.07892},\n  year={2018}\n}\n\n@article{yu2018free,\n  title={Free-Form Image Inpainting with Gated Convolution},\n  author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},\n  journal={arXiv preprint arXiv:1806.03589},\n  year={2018}\n}\n```\n## @tech_hosting\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhi-tech-ai%2Fwatermark-remove","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhi-tech-ai%2Fwatermark-remove","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhi-tech-ai%2Fwatermark-remove/lists"}