Invertible mask network for face privacy preservation

Face privacy Preservation is research subject has attracted significant interest. Existing face privacy-preserving methods aim at erasing the semantic information of faces; however, they cannot well preserve the reusability of original facial information. To achieve the naturalness of the processed face and the recoverability of the original protected face, this paper proposes a face privacy-preserving method based on Invertible Mask Network (IMN). First, a high-definition mask face is generated by the proposed Mask Generator model. Then, the mask face is put onto a protected face to obtain the masked face, in which the masked face is visually indistinguishable from the mask face. Finally, the mask face can be removed from the masked face and the recovered face can be obtained by authorized users, where the recovered face is visually indistinguishable from the protected face. The experimental results show that the proposed method can effectively protect the privacy of the protected face in subjective perception, the protection success rate is very high by the face recognition tool, and the proposed method can almost perfectly recover the protected face from the masked face.