{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/faceforensics-a-large-scale-video-dataset-for","title":"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces","arxiv_id":"1803.09179","date":"2018-03-24","proceeding":null,"authors":["Andreas Rössler","Davide Cozzolino","Luisa Verdoliva","Christian Riess","Justus Thies","Matthias Nießner"],"abstract":"With recent advances in computer vision and graphics, it is now possible to\ngenerate videos with extremely realistic synthetic faces, even in real time.\nCountless applications are possible, some of which raise a legitimate alarm,\ncalling for reliable detectors of fake videos. In fact, distinguishing between\noriginal and manipulated video can be a challenge for humans and computers\nalike, especially when the videos are compressed or have low resolution, as it\noften happens on social networks. Research on the detection of face\nmanipulations has been seriously hampered by the lack of adequate datasets. To\nthis end, we introduce a novel face manipulation dataset of about half a\nmillion edited images (from over 1000 videos). The manipulations have been\ngenerated with a state-of-the-art face editing approach. It exceeds all\nexisting video manipulation datasets by at least an order of magnitude. Using\nour new dataset, we introduce benchmarks for classical image forensic tasks,\nincluding classification and segmentation, considering videos compressed at\nvarious quality levels. In addition, we introduce a benchmark evaluation for\ncreating indistinguishable forgeries with known ground truth; for instance with\ngenerative refinement models.","url_abs":"http://arxiv.org/abs/1803.09179v1","url_pdf":"http://arxiv.org/pdf/1803.09179v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-manipulation-detection","task_name":"Image Manipulation Detection"}],"methods":[],"datasets_introduced":[{"slug":"faceforensics","name":"FaceForensics","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.09179","atlas_url":"https://app.syntology.ai/?focus=1803.09179","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}