OpenForensics: Multi-Face Forgery Detection And Segmentation In-The-Wild Dataset [V.1.0.0]
收藏NIAID Data Ecosystem2026-03-13 收录
下载链接：
https://zenodo.org/record/5528417
下载链接
链接失效反馈官方服务：
资源简介：
OpenForensics is the first large-scale dataset posing a high level of challenges. This dataset is designed with face-wise rich annotations explicitly for face forgery detection and segmentation. With its rich annotations, OpenForensics dataset has great potentials for research in both deepfake prevention and general human face detection. Project Page: https://sites.google.com/view/ltnghia/research/openforensics
OpenForensics是首个具有高挑战性的大规模数据集。该数据集专为人脸伪造检测与分割任务设计，附带逐人脸维度的丰富标注信息。凭借丰富的标注资源，OpenForensics数据集在深度伪造防范以及通用人脸检测两大研究领域均具备巨大的研究潜力。项目主页：https://sites.google.com/view/ltnghia/research/openforensics
创建时间：
2021-10-23
