

InsightFace is an open source 2D&3D deep face analysis toolbox, mainly based on PyTorch and MXNet. The training data containing the annotation (and the models trained with these data) are available for non-commercial research purposes only.īoth manual-downloading models from our github repo and auto-downloading models with our python-library follow the above license policy(which is for non-commercial research purposes only).

There is no limitation for both academic and commercial usage. The code of InsightFace is released under the MIT License. : We launch a Masked Face Recognition Challenge & Workshop on ICCV 2021. : Leaderboard of ICCV21 - Masked Face Recognition Challenge released. : We achieved 1st place on the VISA track of NIST-FRVT 1:1 by using Partial FC (Xiang An, Jiankang Deng, Jia Guo). : MFR-Ongoing challenge launched(same with IFRT), which is an extended version of iccv21-mfr. Of ECCV-2022 WCPA Workshop, paper and code. Perspective Projection Based Monocular 3D Face Reconstruction Challenge : Now we have web-demos: face-localization, face-recognition, and face-swapping. : MFR-Ongoing website is refactored, please create issues if there's any bug. : Single line code for facial identity swapping in our python packge ver 0.7, please check the example here. : We launch a large scale in the wild face anti-spoofing challenge on CVPR23 Workshop, see details at challenges/cvpr23-fas-wild. : We move the swapping demo to Discord bot, which support editing on Midjourney generated images, see detail at web-demos/swapping_discord. : We have launched the ongoing version of wild face anti-spoofing challenge.

InsightFace project is mainly maintained By Jia Guo and Jiankang Deng.įor all main contributors, please check contributing.
