Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors

This paper studies how to synthesize face images of non-existent persons, to create a dataset that allows effective training of face recognition models. Two important goals are (1) the ability to generate a large number of distinct identities (inter-class separation) with (2) a wide variation in appearance of each identity (intra-class variation). However, existing works 1) are typically limited in how many well-separated identities can be generated and 2) either neglect or use a separate editing model for attribute augmentation.

We propose Vec2Face, a holistic model that uses only a sampled vector as input and can flexibly generate and control face images and their attributes. Composed of a feature masked autoencoder and a decoder, Vec2Face is supervised by face image reconstruction and can be conveniently used in inference. Using vectors with low similarity among themselves as inputs, Vec2Face generates well-separated identities. Randomly perturbing an input identity vector within a small range allows Vec2Face to generate faces of the same identity with robust variation in face attributes. It is also possible to generate images with designated attributes by adjusting vector values with a gradient descent method.

Vec2Face has efficiently synthesized as many as 200K identities with 10 million total images, whereas 60K is the largest number of identities created in the previous works. Face recognition models trained with the generated HSFace datasets, from 10k to 200k identities, achieve state-of-the-art accuracy, from 92\% to 93.22\%, on five real-world test sets. For the first time, our model created using a synthetic training set achieves higher accuracy than the model created using a same-scale training set of real face images (on the CALFW test set).