{"id":13427798,"url":"https://github.com/DariusAf/MesoNet","last_synced_at":"2025-03-16T00:32:15.398Z","repository":{"id":31992377,"uuid":"131261937","full_name":"DariusAf/MesoNet","owner":"DariusAf","description":"\"MesoNet: a Compact Facial Video Forgery Detection Network\" (D. Afchar, V. Nozick) - IEEE WIFS 2018","archived":false,"fork":false,"pushed_at":"2024-05-07T10:04:32.000Z","size":487,"stargazers_count":245,"open_issues_count":3,"forks_count":109,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-08-01T01:27:51.078Z","etag":null,"topics":["deepfake","face2face","mesonet"],"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/DariusAf.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":"2018-04-27T07:30:38.000Z","updated_at":"2024-07-18T07:47:19.000Z","dependencies_parsed_at":"2024-06-12T15:42:59.245Z","dependency_job_id":"36e5026e-f824-48eb-909a-189e1d6b7aab","html_url":"https://github.com/DariusAf/MesoNet","commit_stats":{"total_commits":18,"total_committers":4,"mean_commits":4.5,"dds":"0.16666666666666663","last_synced_commit":"ed6d4c38af070e1fa087659e524b52907f6273ae"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DariusAf%2FMesoNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DariusAf%2FMesoNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DariusAf%2FMesoNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DariusAf%2FMesoNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DariusAf","download_url":"https://codeload.github.com/DariusAf/MesoNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221631814,"owners_count":16855012,"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":["deepfake","face2face","mesonet"],"created_at":"2024-07-31T01:00:40.579Z","updated_at":"2024-10-27T05:30:26.287Z","avatar_url":"https://github.com/DariusAf.png","language":"Python","funding_links":[],"categories":["\u003ch2 id=\"Codes\"\u003eCodes\u003c/h2\u003e"],"sub_categories":[],"readme":"# MesoNet\n\nYou can find here the implementation of the network architecture and the dataset used in our paper on digital forensics. It was accepted at the [WIFS 2018 conference](http://wifs2018.comp.polyu.edu.hk).\n\n\u003e We present a method to automatically detect face tampering in videos. We particularly focus on two recent approaches used to generate hyper-realistic forged videos: deepfake and face2face. Traditional image forensics techniques are usually not well suited to videos due to their compression that strongly degrades the data. Thus, we follow a deep learning approach and build two networks, both with a low number of layers to focus on mesoscopic properties of the image. We evaluate those fast networks on both an existing dataset and a dataset we have constituted from online videos. Our tests demonstrate a successful detection for more than 98\\% for deepfake and 95\\% for face2face.\n\n[Link to full paper](https://arxiv.org/abs/1809.00888)\n\n[Demonstrastion video (light)](https://www.youtube.com/watch?v=vch1CmgX0LA)\n\n## Requirements\n\n- Python 3.5\n- Numpy 1.14.2\n- Keras 2.1.5\n\nIf you want to use the complete pipeline with the face extraction from the videos, you will also need the following librairies :\n\n- [Imageio](https://pypi.org/project/imageio/)\n- [FFMPEG](https://www.ffmpeg.org/download.html)\n- [face_recognition](https://github.com/ageitgey/face_recognition)\n\n## Dataset\n\n### Aligned face datasets\n\n|Set|Size of the forged image class|Size of real image class|\n|---|---|---|\n|Training|5111|7250|\n|Validation|2889|4259|\n\n- Training set (~150Mo)\n- Validation set (~50Mo)\n\n[Download link for the dataset](https://my.pcloud.com/publink/show?code=XZLGvd7ZI9LjgIy7iOLzXBG5RNJzGFQzhTRy)\n\n## Pretrained models\n\nYou can find the pretrained weight in the `weights` folder. The `_DF` extension correspond to a model trained to classify deepfake-generated images and the `_F2F` to Face2Face-generated images.\n\n## Authors\n\n**Darius Afchar** - École des Ponts Paristech | École Normale Supérieure (France)\n\n**Vincent Nozick** - [Website](http://www-igm.univ-mlv.fr/~vnozick/?lang=fr)\n\n## References\n\nAfchar, D., Nozick, V., Yamagishi, J., \u0026 Echizen, I. (2018, September). [MesoNet: a Compact Facial Video Forgery Detection Network](https://arxiv.org/abs/1809.00888). In IEEE Workshop on Information Forensics and Security, WIFS 2018.\n\nThis research was carried out while the authors stayed at the National Institute of Informatics, Japan.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDariusAf%2FMesoNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FDariusAf%2FMesoNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDariusAf%2FMesoNet/lists"}