{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:16:10Z","timestamp":1782317770914,"version":"3.54.5"},"publisher-location":"Cham","reference-count":101,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729126","type":"print"},{"value":"9783031729133","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72913-3_14","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:46:22Z","timestamp":1733089582000},"page":"241-261","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["Arc2Face: A Foundation Model for\u00a0ID-Consistent Human Faces"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7203-8866","authenticated-orcid":false,"given":"Foivos Paraperas","family":"Papantoniou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9964-6105","authenticated-orcid":false,"given":"Alexandros","family":"Lattas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7421-1335","authenticated-orcid":false,"given":"Stylianos","family":"Moschoglou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-6216","authenticated-orcid":false,"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7813-5023","authenticated-orcid":false,"given":"Bernhard","family":"Kainz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5222-1740","authenticated-orcid":false,"given":"Stefanos","family":"Zafeiriou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"14_CR1","unstructured":"https:\/\/thispersondoesnotexist.com\/"},{"key":"14_CR2","unstructured":"https:\/\/github.com\/zllrunning\/face-parsing.PyTorch"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"An, S., Xu, H., Shi, Y., Song, G., Ogras, U.Y., Luo, L.: Panohead: geometry-aware 3d full-head synthesis in 360deg. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20950\u201320959 (2023)","DOI":"10.1109\/CVPR52729.2023.02007"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Bae, G., et al.: Digiface-1m: 1 million digital face images for face recognition. In: WACV (2023)","DOI":"10.1109\/WACV56688.2023.00352"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Bansal, A., et al.: Universal guidance for diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 843\u2013852 (2023)","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"14_CR6","doi-asserted-by":"publisher","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999, pp. 187\u2013194. ACM Press\/Addison-Wesley Publishing Co., Boston (1999). https:\/\/doi.org\/10.1145\/311535.311556","DOI":"10.1145\/311535.311556"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Boutros, F., Damer, N., Kirchbuchner, F., Kuijper, A.: Elasticface: elastic margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1578\u20131587 (2022)","DOI":"10.1109\/CVPRW56347.2022.00164"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3d generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16123\u201316133 (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-gan: periodic implicit generative adversarial networks for 3d-aware image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition,. pp. 5799\u20135809 (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"14_CR10","unstructured":"Chen, L., et\u00a0al.: Photoverse: tuning-free image customization with text-to-image diffusion models (2023)"},{"key":"14_CR11","unstructured":"Chen, Z., et al.: Dreamidentity: improved editability for efficient face-identity preserved image generation. arXiv preprint arXiv:2307.00300 (2023)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., Yoon, S.: Ilvr: conditioning method for denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14367\u201314376 (2021)","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Dan\u011b\u010dek, R., Black, M.J., Bolkart, T.: Emoca: emotion driven monocular face capture and animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20311\u201320322 (2022)","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Yang, J., Lattas, A., Zafeiriou, S.: Variational prototype learning for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11906\u201311915 (2021)","DOI":"10.1109\/CVPR46437.2021.01173"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Xiang, J., Tong, X.: Gram: generative radiance manifolds for 3d-aware image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10673\u201310683 (2022)","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"14_CR17","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Ding, Z., et al.: Diffusionrig: learning personalized priors for facial appearance editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12736\u201312746 (2023)","DOI":"10.1109\/CVPR52729.2023.01225"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Duong, C.N., et al.: Vec2face: unveil human faces from their blackbox features in face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6132\u20136141 (2020)","DOI":"10.1109\/CVPR42600.2020.00617"},{"issue":"4","key":"14_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459936","volume":"40","author":"Y Feng","year":"2021","unstructured":"Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3d face model from in-the-wild images. ACM Trans. Graph. (ToG) 40(4), 1\u201313 (2021)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Filntisis, P.P., Retsinas, G., Paraperas-Papantoniou, F., Katsamanis, A., Roussos, A., Maragos, P.: Visual speech-aware perceptual 3d facial expression reconstruction from videos. arXiv preprint arXiv:2207.11094 (2022)","DOI":"10.1109\/CVPRW59228.2023.00609"},{"key":"14_CR22","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"issue":"4","key":"14_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592133","volume":"42","author":"R Gal","year":"2023","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Encoder-based domain tuning for fast personalization of text-to-image models. ACM Trans. Graph. (TOG) 42(4), 1\u201313 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Gecer, B., Ploumpis, S., Kotsia, I., Zafeiriou, S.: Ganfit: generative adversarial network fitting for high fidelity 3d face reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00125"},{"key":"14_CR25","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"14_CR26","unstructured":"Gu, J., Liu, L., Wang, P., Theobalt, C.: Stylenerf: a style-based 3d aware generator for high-resolution image synthesis. In: International Conference on Learning Representations (2022)"},{"key":"14_CR27","first-page":"9841","volume":"33","author":"E H\u00e4rk\u00f6nen","year":"2020","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., Paris, S.: Ganspace: discovering interpretable gan controls. Adv. Neural. Inf. Process. Syst. 33, 9841\u20139850 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR28","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"14_CR29","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"14_CR30","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"14_CR31","unstructured":"Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Technical Report (2008)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: Humannorm: learning normal diffusion model for high-quality and realistic 3d human generation. arXiv preprint arXiv:2310.01406 (2023)","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Kang, M., Shin, J., Park, J.: Studiogan: a taxonomy and benchmark of gans for image synthesis. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3306436"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up gans for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Kansy, M., et al.: Controllable inversion of black-box face recognition models via diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 3167\u20133177 (2023)","DOI":"10.1109\/ICCVW60793.2023.00341"},{"key":"14_CR36","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"14_CR37","first-page":"852","volume":"34","author":"T Karras","year":"2021","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. Adv. Neural. Inf. Process. Syst. 34, 852\u2013863 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Kim, M., Jain, A.K., Liu, X.: Adaface: quality adaptive margin for face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18750\u201318759 (2022)","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Kim, M., Liu, F., Jain, A., Liu, X.: Dcface: synthetic face generation with dual condition diffusion model. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01223"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Kirschstein, T., Giebenhain, S., Nie\u00dfner, M.: Diffusionavatars: deferred diffusion for high-fidelity 3d head avatars. arXiv preprint arXiv:2311.18635 (2023)","DOI":"10.1109\/CVPR52733.2024.00524"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"14_CR44","doi-asserted-by":"publisher","unstructured":"Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 36(6), 194:1\u2013194:17 (2017). https:\/\/doi.org\/10.1145\/3130800.3130813","DOI":"10.1145\/3130800.3130813"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M.M., Shan, Y.: Photomaker: customizing realistic human photos via stacked id embedding. arXiv preprint arXiv:2312.04461 (2023)","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"14_CR46","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"14_CR47","first-page":"5775","volume":"35","author":"C Lu","year":"2022","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: Dpm-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. Adv. Neural. Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR48","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: Dpm-solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"issue":"5","key":"14_CR49","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1109\/TPAMI.2018.2827389","volume":"41","author":"G Mai","year":"2018","unstructured":"Mai, G., Cao, K., Yuen, P.C., Jain, A.K.: On the reconstruction of face images from deep face templates. IEEE Trans. Pattern Anal. Mach. Intell. 41(5), 1188\u20131202 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR50","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2022)"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Mensah, D., Kim, N.H., Aittala, M., Laine, S., Lehtinen, J.: A hybrid generator architecture for controllable face synthesis. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201310 (2023)","DOI":"10.1145\/3588432.3591563"},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: Agedb: the first manually collected, in-the-wild age database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop (2017)","DOI":"10.1109\/CVPRW.2017.250"},{"key":"14_CR53","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: Giraffe: representing scenes as compositional generative neural feature fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11453\u201311464 (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"14_CR54","unstructured":"Pan, X., Dong, L., Huang, S., Peng, Z., Chen, W., Wei, F.: Kosmos-g: generating images in context with multimodal large language models. arXiv preprint arXiv:2310.02992 (2023)"},{"key":"14_CR55","doi-asserted-by":"crossref","unstructured":"Papantoniou, F.P., Lattas, A., Moschoglou, S., Zafeiriou, S.: Relightify: relightable 3d faces from a single image via diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8806\u20138817 (2023)","DOI":"10.1109\/ICCV51070.2023.00809"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Peng, X., et al.: Portraitbooth: a versatile portrait model for fast identity-preserved personalization. arXiv preprint arXiv:2312.06354 (2023)","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"14_CR57","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"14_CR58","doi-asserted-by":"crossref","unstructured":"Qiu, H., Yu, B., Gong, D., Li, Z., Liu, W., Tao, D.: SynFace: face recognition with synthetic data. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01070"},{"key":"14_CR59","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR60","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents, 1(2), 3 (2022). arXiv preprint arXiv:2204.06125"},{"key":"14_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1007\/978-3-030-68238-5_34","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"A Razzhigaev","year":"2020","unstructured":"Razzhigaev, A., Kireev, K., Kaziakhmedov, E., Tursynbek, N., Petiushko, A.: Black-box face recovery from identity features. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12539, pp. 462\u2013475. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-68238-5_34"},{"key":"14_CR62","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"14_CR64","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"14_CR65","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: Hyperdreambooth: hypernetworks for fast personalization of text-to-image models. arXiv preprint arXiv:2307.06949 (2023)","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"14_CR66","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR67","unstructured":"Sauer, A., Karras, T., Laine, S., Geiger, A., Aila, T.: Stylegan-t: unlocking the power of gans for fast large-scale text-to-image synthesis. arXiv preprint arXiv:2301.09515 (2023)"},{"key":"14_CR68","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR69","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"14_CR70","first-page":"33999","volume":"35","author":"K Schwarz","year":"2022","unstructured":"Schwarz, K., Sauer, A., Niemeyer, M., Liao, Y., Geiger, A.: Voxgraf: fast 3d-aware image synthesis with sparse voxel grids. Adv. Neural. Inf. Process. Syst. 35, 33999\u201334011 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR71","unstructured":"Seitzer, M.: pytorch-fid: FID Score for PyTorch (2020). https:\/\/github.com\/mseitzer\/pytorch-fid. version 0.3.0"},{"key":"14_CR72","doi-asserted-by":"crossref","unstructured":"Sengupta, S., Chen, J.C., Castillo, C., Patel, V.M., Chellappa, R., Jacobs, D.W.: Frontal to profile face verification in the wild. In: WACV (2016)","DOI":"10.1109\/WACV.2016.7477558"},{"issue":"4","key":"14_CR73","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/TPAMI.2020.3034267","volume":"44","author":"Y Shen","year":"2020","unstructured":"Shen, Y., Yang, C., Tang, X., Zhou, B.: Interfacegan: interpreting the disentangled face representation learned by gans. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 2004\u20132018 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR74","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: Proceedings of the 32nd International Conference on Machine Learning, Lille, France, vol.\u00a037, pp. 2256\u20132265 (2015)"},{"key":"14_CR75","doi-asserted-by":"crossref","unstructured":"Somepalli, G., Singla, V., Goldblum, M., Geiping, J., Goldstein, T.: Diffusion art or digital forgery? investigating data replication in diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6048\u20136058 (2023)","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"14_CR76","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"14_CR77","unstructured":"Truong, T.D., Duong, C.N., Le, N., Savvides, M., Luu, K.: Vec2face-v2: unveil human faces from their blackbox features via attention-based network in face recognition. arXiv preprint arXiv:2209.04920 (2022)"},{"issue":"1","key":"14_CR78","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1162\/jocn.1991.3.1.71","volume":"3","author":"M Turk","year":"1991","unstructured":"Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71\u201386 (1991)","journal-title":"J. Cogn. Neurosci."},{"key":"14_CR79","doi-asserted-by":"crossref","unstructured":"Valevski, D., Lumen, D., Matias, Y., Leviathan, Y.: Face0: instantaneously conditioning a text-to-image model on a face. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618249"},{"key":"14_CR80","unstructured":"Vendrow, E., Vendrow, J.: Realistic face reconstruction from deep embeddings. In: NeurIPS 2021 Workshop Privacy in Machine Learning (2021). https:\/\/openreview.net\/forum?id=-WsBmzWwPee"},{"key":"14_CR81","unstructured":"Wang, Q., et al.: Stableidentity: inserting anybody into anywhere at first sight. arXiv preprint arXiv:2401.15975 (2024)"},{"key":"14_CR82","unstructured":"Wang, Q., Bai, X., Wang, H., Qin, Z., Chen, A.: Instantid: zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519 (2024)"},{"key":"14_CR83","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, Y., Zhang, H., Shan, Y.: Towards real-world blind face restoration with generative facial prior. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00905"},{"issue":"3","key":"14_CR84","first-page":"3121","volume":"45","author":"W Xia","year":"2022","unstructured":"Xia, W., Zhang, Y., Yang, Y., Xue, J.H., Zhou, B., Yang, M.H.: Gan inversion: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3121\u20133138 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR85","doi-asserted-by":"crossref","unstructured":"Xiao, G., Yin, T., Freeman, W.T., Durand, F., Han, S.: Fastcomposer: tuning-free multi-subject image generation with localized attention. arXiv preprint arXiv:2305.10431 (2023)","DOI":"10.1007\/s11263-024-02227-z"},{"key":"14_CR86","unstructured":"Yan, Y., et al.: Facestudio: put your face everywhere in seconds. arXiv preprint arXiv:2312.02663 (2023)"},{"issue":"4","key":"14_CR87","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3626235","volume":"56","author":"L Yang","year":"2023","unstructured":"Yang, L., et al.: Diffusion models: a comprehensive survey of methods and applications. ACM Comput. Surv. 56(4), 1\u201339 (2023)","journal-title":"ACM Comput. Surv."},{"key":"14_CR88","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, J., Chang, E.C., Liang, Z.: Neural network inversion in adversarial setting via background knowledge alignment. In: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, pp. 225\u2013240 (2019)","DOI":"10.1145\/3319535.3354261"},{"key":"14_CR89","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"14_CR90","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models. GitHub repository https:\/\/github.com\/tencent-ailab\/IP-Adapter (2024)"},{"key":"14_CR91","unstructured":"Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014)"},{"key":"14_CR92","unstructured":"Yuan, G., et al.: Inserting anybody in diffusion models via celeb basis. arXiv preprint arXiv:2306.00926 (2023)"},{"key":"14_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: Dreamface: progressive generation of animatable 3d faces under text guidance. arXiv preprint arXiv:2304.03117 (2023)","DOI":"10.1145\/3592094"},{"key":"14_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"14_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"14_CR96","unstructured":"Zheng, T., Deng, W.: Cross-Pose LFW: a database for studying cross-pose face recognition in unconstrained environments. Technical Report (2018)"},{"key":"14_CR97","unstructured":"Zheng, T., Deng, W., Hu, J.: Cross-Age LFW: a database for studying cross-age face recognition in unconstrained environments. Technical Report (2017)"},{"key":"14_CR98","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: General facial representation learning in a visual-linguistic manner. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18697\u201318709 (2022)","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"14_CR99","unstructured":"Zhou, Y., Zhang, R., Sun, T., Xu, J.: Enhancing detail preservation for customized text-to-image generation: a regularization-free approach. arXiv preprint arXiv:2305.13579 (2023)"},{"key":"14_CR100","first-page":"16648","volume":"34","author":"J Zhu","year":"2021","unstructured":"Zhu, J., et al.: Low-rank subspaces in gans. Adv. Neural. Inf. Process. Syst. 34, 16648\u201316658 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR101","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et\u00a0al.: Webface260m: a benchmark unveiling the power of million-scale deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10492\u201310502 (2021)","DOI":"10.1109\/CVPR46437.2021.01035"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72913-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:24:23Z","timestamp":1733095463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72913-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031729126","9783031729133"],"references-count":101,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72913-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}