{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:39:51Z","timestamp":1777657191656,"version":"3.51.4"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israeli Science Foundation","doi-asserted-by":"crossref","award":["3441\/21"],"award-info":[{"award-number":["3441\/21"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:p>We introduce MyStyle, a personalized deep generative prior trained with a few shots of an individual. MyStyle allows to reconstruct, enhance and edit images of a specific person, such that the output is faithful to the person's key facial characteristics. Given a small reference set of portrait images of a person (~ 100), we tune the weights of a pretrained StyleGAN face generator to form a local, low-dimensional, personalized manifold in the latent space. We show that this manifold constitutes a personalized region that spans latent codes associated with diverse portrait images of the individual. Moreover, we demonstrate that we obtain a personalized generative prior, and propose a unified approach to apply it to various ill-posed image enhancement problems, such as inpainting and super-resolution, as well as semantic editing. Using the personalized generative prior we obtain outputs that exhibit high-fidelity to the input images and are also faithful to the key facial characteristics of the individual in the reference set. We demonstrate our method with fair-use images of numerous widely recognizable individuals for whom we have the prior knowledge for a qualitative evaluation of the expected outcome. We evaluate our approach against few-shots baselines and show that our personalized prior, quantitatively and qualitatively, outperforms state-of-the-art alternatives.<\/jats:p>","DOI":"10.1145\/3550454.3555436","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T21:19:07Z","timestamp":1669843147000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":66,"title":["MyStyle"],"prefix":"10.1145","volume":"41","author":[{"given":"Yotam","family":"Nitzan","sequence":"first","affiliation":[{"name":"Google Research and Tel-Aviv University, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kfir","family":"Aberman","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiurui","family":"He","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Orly","family":"Liba","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michal","family":"Yarom","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yossi","family":"Gandelsman","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inbar","family":"Mosseri","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yael","family":"Pritch","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Cohen-Or","sequence":"additional","affiliation":[{"name":"Google Research and Tel-Aviv University, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"e_1_2_2_2_1","volume-title":"StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows. arXiv preprint arXiv:2008.02401","author":"Abdal Rameen","year":"2020","unstructured":"Rameen Abdal, Peihao Zhu, Niloy Mitra, and Peter Wonka. 2020. StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows. arXiv preprint arXiv:2008.02401 (2020)."},{"key":"e_1_2_2_3_1","volume-title":"ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement. arXiv preprint arXiv:2104.02699","author":"Alaluf Yuval","year":"2021","unstructured":"Yuval Alaluf, Or Patashnik, and Daniel Cohen-Or. 2021a. ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement. arXiv preprint arXiv:2104.02699 (2021)."},{"key":"e_1_2_2_4_1","volume-title":"HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing. arXiv preprint arXiv:2111.15666","author":"Alaluf Yuval","year":"2021","unstructured":"Yuval Alaluf, Omer Tov, Ron Mokady, Rinon Gal, and Amit H Bermano. 2021b. HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing. arXiv preprint arXiv:2111.15666 (2021)."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130818"},{"key":"e_1_2_2_6_1","volume-title":"Semantic photo manipulation with a generative image prior. arXiv preprint arXiv:2005.07727","author":"Bau David","year":"2020","unstructured":"David Bau, Hendrik Strobelt, William Peebles, Jonas Wulff, Bolei Zhou, Jun-Yan Zhu, and Antonio Torralba. 2020. Semantic photo manipulation with a generative image prior. arXiv preprint arXiv:2005.07727 (2020)."},{"key":"e_1_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Amit H. Bermano Rinon Gal Yuval Alaluf Ron Mokady Yotam Nitzan Omer Tov Oren Patashnik and Daniel Cohen-Or. 2022. State-of-the-Art in the Architecture Methods and Applications of StyleGAN.","DOI":"10.1111\/cgf.14503"},{"key":"e_1_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Yochai Blau and Tomer Michaeli. 2018. The Perception-Distortion Tradeoff. In CVPR.","DOI":"10.1109\/CVPR.2018.00652"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00544"},{"key":"e_1_2_2_10_1","volume-title":"A communication tool for people with speech impairments. https:\/\/blog.google\/outreach-initiatives\/accessibility\/project-relate\/","author":"Cattiau Julie","year":"2022","unstructured":"Julie Cattiau. 2021. A communication tool for people with speech impairments. https:\/\/blog.google\/outreach-initiatives\/accessibility\/project-relate\/. Accessed: January 2022."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"e_1_2_2_12_1","volume-title":"Artwork Personalization at Netflix. https:\/\/netflixtechblog.com\/artwork-personalization-c589f074ad76","author":"Chandrashekar Ashok","year":"2022","unstructured":"Ashok Chandrashekar, Fernando Amat, Justin Basilico, and Tony Jebara. 2021. Artwork Personalization at Netflix. https:\/\/netflixtechblog.com\/artwork-personalization-c589f074ad76. Accessed: January 2022."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00824"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492914000129"},{"key":"e_1_2_2_15_1","volume-title":"Stylegan-nada: Clip-guided domain adaptation of image generators. arXiv preprint arXiv:2108.00946","author":"Gal Rinon","year":"2021","unstructured":"Rinon Gal, Or Patashnik, Haggai Maron, Gal Chechik, and Daniel Cohen-Or. 2021. Stylegan-nada: Clip-guided domain adaptation of image generators. arXiv preprint arXiv:2108.00946 (2021)."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2967754"},{"key":"e_1_2_2_17_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"e_1_2_2_19_1","volume-title":"GANSpace: Discovering Interpretable GAN Controls. arXiv preprint arXiv:2004.02546","author":"H\u00e4rk\u00f6nen Erik","year":"2020","unstructured":"Erik H\u00e4rk\u00f6nen, Aaron Hertzmann, Jaakko Lehtinen, and Sylvain Paris. 2020. GANSpace: Discovering Interpretable GAN Controls. arXiv preprint arXiv:2004.02546 (2020)."},{"key":"e_1_2_2_20_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_2_21_1","volume-title":"Proc. NeurIPS.","author":"Karras Tero","year":"2020","unstructured":"Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, and Timo Aila. 2020a. Training Generative Adversarial Networks with Limited Data. In Proc. NeurIPS."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00278"},{"key":"e_1_2_2_25_1","volume-title":"Few-shot Image Generation with Elastic Weight Consolidation. arXiv preprint arXiv:2012.02780","author":"Li Yijun","year":"2020","unstructured":"Yijun Li, Richard Zhang, Jingwan Lu, and Eli Shechtman. 2020b. Few-shot Image Generation with Elastic Weight Consolidation. arXiv preprint arXiv:2012.02780 (2020)."},{"key":"e_1_2_2_26_1","volume-title":"Time-travel rephotography. arXiv preprint arXiv:2012.12261","author":"Luo Xuan","year":"2020","unstructured":"Xuan Luo, Xuaner Zhang, Paul Yoo, Ricardo Martin-Brualla, Jason Lawrence, and Steven M Seitz. 2020a. Time-travel rephotography. arXiv preprint arXiv:2012.12261 (2020)."},{"key":"e_1_2_2_27_1","volume-title":"Seitz","author":"Luo Xuan","year":"2020","unstructured":"Xuan Luo, Xuaner Zhang, Paul Yoo, Ricardo Martin-Brualla, Jason Lawrence, and Steven M. Seitz. 2020b. Time-Travel Rephotography. arXiv preprint arXiv:2012.12261 (2020)."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00251"},{"key":"e_1_2_2_29_1","volume-title":"Freeze the discriminator: a simple baseline for fine-tuning GANs. arXiv preprint arXiv:2002.10964","author":"Mo Sangwoo","year":"2020","unstructured":"Sangwoo Mo, Minsu Cho, and Jinwoo Shin. 2020. Freeze the discriminator: a simple baseline for fine-tuning GANs. arXiv preprint arXiv:2002.10964 (2020)."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417826"},{"key":"e_1_2_2_31_1","volume-title":"Eli Shechtman, and Richard Zhang.","author":"Ojha Utkarsh","year":"2021","unstructured":"Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A Efros, Yong Jae Lee, Eli Shechtman, and Richard Zhang. 2021. Few-shot Image Generation via Cross-domain Correspondence. arXiv preprint arXiv:2104.06820 (2021)."},{"key":"e_1_2_2_32_1","volume-title":"Chen Change Loy, and Ping Luo","author":"Pan Xingang","year":"2021","unstructured":"Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, and Ping Luo. 2021. Exploiting deep generative prior for versatile image restoration and manipulation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"e_1_2_2_33_1","volume-title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery. arXiv preprint arXiv:2103.17249","author":"Patashnik Or","year":"2021","unstructured":"Or Patashnik, Zongze Wu, Eli Shechtman, Daniel Cohen-Or, and Dani Lischinski. 2021. StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery. arXiv preprint arXiv:2103.17249 (2021)."},{"key":"e_1_2_2_34_1","volume-title":"Resolution Dependant GAN Interpolation for Controllable Image Synthesis Between Domains. arXiv preprint arXiv:2010.05334","author":"Pinkney Justin NM","year":"2020","unstructured":"Justin NM Pinkney and Doron Adler. 2020. Resolution Dependant GAN Interpolation for Controllable Image Synthesis Between Domains. arXiv preprint arXiv:2010.05334 (2020)."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_2_2_36_1","volume-title":"Pivotal Tuning for Latent-based Editing of Real Images. arXiv preprint arXiv:2106.05744","author":"Roich Daniel","year":"2021","unstructured":"Daniel Roich, Ron Mokady, Amit H Bermano, and Daniel Cohen-Or. 2021. Pivotal Tuning for Latent-based Editing of Real Images. arXiv preprint arXiv:2106.05744 (2021)."},{"key":"e_1_2_2_37_1","volume-title":"InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs. arXiv preprint arXiv:2005.09635","author":"Shen Yujun","year":"2020","unstructured":"Yujun Shen, Ceyuan Yang, Xiaoou Tang, and Bolei Zhou. 2020. InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs. arXiv preprint arXiv:2005.09635 (2020)."},{"key":"e_1_2_2_38_1","volume-title":"arXiv preprint arXiv:2012.05328","author":"Spingarn-Eliezer Nurit","year":"2020","unstructured":"Nurit Spingarn-Eliezer, Ron Banner, and Tomer Michaeli. 2020. GAN\" Steerability\" without optimization. arXiv preprint arXiv:2012.05328 (2020)."},{"key":"e_1_2_2_39_1","volume-title":"Designing an Encoder for StyleGAN Image Manipulation. arXiv preprint arXiv:2102.02766","author":"Tov Omer","year":"2021","unstructured":"Omer Tov, Yuval Alaluf, Yotam Nitzan, Or Patashnik, and Daniel Cohen-Or. 2021. Designing an Encoder for StyleGAN Image Manipulation. arXiv preprint arXiv:2102.02766 (2021)."},{"key":"e_1_2_2_40_1","volume-title":"Unsupervised Discovery of Interpretable Directions in the GAN Latent Space. arXiv preprint arXiv:2002.03754","author":"Voynov Andrey","year":"2020","unstructured":"Andrey Voynov and Artem Babenko. 2020. Unsupervised Discovery of Interpretable Directions in the GAN Latent Space. arXiv preprint arXiv:2002.03754 (2020)."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201329"},{"key":"e_1_2_2_42_1","volume-title":"Proceedings of the Asian Conference on Computer Vision.","author":"Wang Kaili","year":"2020","unstructured":"Kaili Wang, Jose Oramas, and Tinne Tuytelaars. 2020. Multiple exemplars-based hallucination for face super-resolution and editing. In Proceedings of the Asian Conference on Computer Vision."},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"e_1_2_2_44_1","volume-title":"StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation. arXiv:2011.12799","author":"Wu Zongze","year":"2020","unstructured":"Zongze Wu, Dani Lischinski, and Eli Shechtman. 2020. StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation. arXiv:2011.12799 (2020)."},{"key":"e_1_2_2_45_1","volume-title":"StyleAlign: Analysis and Applications of Aligned StyleGAN Models. arXiv preprint arXiv:2110.11323","author":"Wu Zongze","year":"2021","unstructured":"Zongze Wu, Yotam Nitzan, Eli Shechtman, and Dani Lischinski. 2021. StyleAlign: Analysis and Applications of Aligned StyleGAN Models. arXiv preprint arXiv:2110.11323 (2021)."},{"key":"e_1_2_2_46_1","volume-title":"Data-Efficient Instance Generation from Instance Discrimination. arXiv preprint arXiv:2106.04566","author":"Yang Ceyuan","year":"2021","unstructured":"Ceyuan Yang, Yujun Shen, Yinghao Xu, and Bolei Zhou. 2021b. Data-Efficient Instance Generation from Instance Discrimination. arXiv preprint arXiv:2106.04566 (2021)."},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00073"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_2_49_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Zhao Shengyu","year":"2021","unstructured":"Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I Chang, and Yan Xu. 2021. Large Scale Image Completion via Co-Modulated Generative Adversarial Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_2_50_1","volume-title":"Differentiable augmentation for data-efficient gan training. arXiv preprint arXiv:2006.10738","author":"Zhao Shengyu","year":"2020","unstructured":"Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu, and Song Han. 2020. Differentiable augmentation for data-efficient gan training. arXiv preprint arXiv:2006.10738 (2020)."},{"key":"e_1_2_2_51_1","volume-title":"Identity preserving face completion for large ocular region occlusion. arXiv preprint arXiv:1807.08772","author":"Zhao Yajie","year":"2018","unstructured":"Yajie Zhao, Weikai Chen, Jun Xing, Xiaoming Li, Zach Bessinger, Fuchang Liu, Wangmeng Zuo, and Ruigang Yang. 2018. Identity preserving face completion for large ocular region occlusion. arXiv preprint arXiv:1807.08772 (2018)."},{"key":"e_1_2_2_52_1","volume-title":"WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose. arXiv preprint arXiv:2005.10353","author":"Zhou Yijun","year":"2020","unstructured":"Yijun Zhou and James Gregson. 2020. WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose. arXiv preprint arXiv:2005.10353 (2020)."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555436","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550454.3555436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:11Z","timestamp":1750182551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555436"}},"subtitle":["A Personalized Generative Prior"],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1145\/3550454.3555436"],"URL":"https:\/\/doi.org\/10.1145\/3550454.3555436","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"assertion":[{"value":"2022-11-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}