Arc2Face: A foundation model for ID-consistent human faces
File(s)
Accepted version
Author(s)
Papantoniou, Foivos Paraperas
Lattas, Alexandros
Moschoglou, Stylianos
Deng, Jiankang
Kainz, Bernhard
Type
Conference Paper
Abstract
This paper presents Arc2Face, an identity-conditioned face foundation model, which, given the ArcFace embedding of a person, can generate diverse photo-realistic images with an unparalleled degree of face similarity than existing models. Despite previous attempts to decode face recognition features into detailed images, we find that common high-resolution datasets (e.g.FFHQ) lack sufficient identities to reconstruct any subject. To that end, we meticulously upsample a significant portion of the WebFace42M database, the largest public dataset for face recognition (FR). Arc2Face builds upon a pretrained Stable Diffusion model, yet adapts it to the task of ID-to-face generation, conditioned solely on ID vectors. Deviating from recent works that combine ID with text embeddings for zero-shot personalization of text-to-image models, we emphasize on the compactness of FR features, which can fully capture the essence of the human face, as opposed to hand-crafted prompts. Crucially, text-augmented models struggle to decouple identity and text, usually necessitating some description of the given face to achieve satisfactory similarity. Arc2Face, however, only needs the discriminative features of ArcFace to guide the generation, offering a robust prior for a plethora of tasks where ID consistency is of paramount importance. As an example, we train a FR model on synthetic images from our model and achieve superior performance to existing synthetic datasets.
Date Issued
2025-01-01
Date Acceptance
2024-09-29
Citation
Lecture Notes in Computer Science, 2025, 15095, pp.241-261
ISBN
9783031729126
ISSN
0302-9743
Publisher
Springer Nature Switzerland
Start Page
241
End Page
261
Journal / Book Title
Lecture Notes in Computer Science
Volume
15095
Copyright Statement
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Identifier
https://doi.org/10.1007/978-3-031-72913-3_14
Source
European Conference on Computer Vision
Subjects
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2024-09-29
Finish Date
2024-10-04
Coverage Spatial
Milan, Italy
Date Publish Online
2024-12-02