{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/arc2face-a-foundation-model-of-human-faces","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","arxiv_id":"2403.11641","date":"2024-03-18","proceeding":null,"authors":["Foivos Paraperas Papantoniou","Alexandros Lattas","Stylianos Moschoglou","Jiankang Deng","Bernhard Kainz","Stefanos Zafeiriou"],"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.","url_abs":"https://arxiv.org/abs/2403.11641v2","url_pdf":"https://arxiv.org/pdf/2403.11641v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"arc2face-a-foundation-model-of-human-faces","repo_url":"https://huggingface.co/FoivosPar/Arc2Face","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"arc2face-a-foundation-model-of-human-faces","repo_url":"https://github.com/dariant/id-booth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"arc2face-a-foundation-model-of-human-faces","repo_url":"https://github.com/foivospar/Arc2Face","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diffusion-personalization","task_name":"Diffusion Personalization"},{"task_slug":"diffusion-personalization-tuning-free","task_name":"Diffusion Personalization Tuning Free"},{"task_slug":"face-generation","task_name":"Face Generation"},{"task_slug":"face-recognition","task_name":"Face Recognition"}],"methods":[{"method_slug":"adaptive-instance-normalization","method_name":"Adaptive Instance Normalization"},{"method_slug":"arcface","method_name":"ArcFace"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"gfp-gan","method_name":"GFP-GAN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"spatial-feature-transform","method_name":"Spatial Feature Transform"},{"method_slug":"stylegan","method_name":"StyleGAN"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/diffusion-personalization-tuning-free-on","task":"Diffusion Personalization Tuning Free","dataset":"AgeDB","model":"Arc2Face","rank_in_archive_order":1,"of":7,"metrics":{"Cosine Similarity":"0.796","FID":"6.628","LPIPS":"0.508"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.11641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11641"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/foivospar/Arc2Face","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://huggingface.co/FoivosPar/Arc2Face","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dariant/id-booth","reach":null}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"listed":{"samples":4,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"61d57ee7686dcea8","entry":"SEModule","repo":"dariant/id-booth","repo_kind":"listed","path":"FR_training/backbones/iresnet.py","file_url":"https://github.com/dariant/id-booth/blob/HEAD/FR_training/backbones/iresnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61d57ee7686dcea8"}},{"code_sha256_prefix":"5bbb61b811d60b28","entry":"IBasicBlock","repo":"dariant/id-booth","repo_kind":"listed","path":"FR_training/backbones/iresnet.py","file_url":"https://github.com/dariant/id-booth/blob/HEAD/FR_training/backbones/iresnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5bbb61b811d60b28"}},{"code_sha256_prefix":"8143d02e7fe4fc3e","entry":"IResNet","repo":"dariant/id-booth","repo_kind":"listed","path":"FR_training/backbones/iresnet.py","file_url":"https://github.com/dariant/id-booth/blob/HEAD/FR_training/backbones/iresnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8143d02e7fe4fc3e"}},{"code_sha256_prefix":"6940658d039b0db4","entry":"ReferenceAdapter","repo":"foivospar/Arc2Face","repo_kind":"listed","path":"arc2face/ref_adapter.py","file_url":"https://github.com/foivospar/Arc2Face/blob/HEAD/arc2face/ref_adapter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6940658d039b0db4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}