{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:53:24Z","timestamp":1784904804516,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,23]],"date-time":"2023-07-23T00:00:00Z","timestamp":1690070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"German Research Foundation (DFG)"},{"name":"Sony Semiconductor Solutions Corporation"},{"name":"Bavarian State Ministry of Science and the Arts"},{"name":"Bavarian Research Institute for Digital Transformation"},{"name":"ERC Starting Grant Scan2CAD","award":["804724"],"award-info":[{"award-number":["804724"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,23]]},"DOI":"10.1145\/3588432.3591566","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T13:34:52Z","timestamp":1689773692000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":43,"title":["ClipFace: Text-guided Editing of Textured 3D Morphable Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4479-7328","authenticated-orcid":false,"given":"Shivangi","family":"Aneja","sequence":"first","affiliation":[{"name":"Technical University of Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0056-9825","authenticated-orcid":false,"given":"Justus","family":"Thies","sequence":"additional","affiliation":[{"name":"Max Planck Institue for Intelligent Systems, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6241-8782","authenticated-orcid":false,"given":"Angela","family":"Dai","sequence":"additional","affiliation":[{"name":"Technical University Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6093-5199","authenticated-orcid":false,"given":"Matthias","family":"Niessner","sequence":"additional","affiliation":[{"name":"Technical University Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,23]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530747"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","DOI":"10.1145\/3447648","article-title":"StyleFlow: Attribute-Conditioned Exploration of StyleGAN-Generated Images Using Conditional Continuous Normalizing Flows. ACM","author":"Abdal Rameen","year":"2021","unstructured":"Rameen Abdal , Peihao Zhu , Niloy\u00a0 J. Mitra , and Peter Wonka . 2021 . StyleFlow: Attribute-Conditioned Exploration of StyleGAN-Generated Images Using Conditional Continuous Normalizing Flows. ACM Trans. Graph. ( May 2021). https:\/\/doi.org\/10.1145\/3447648 10.1145\/3447648 Rameen Abdal, Peihao Zhu, Niloy\u00a0J. Mitra, and Peter Wonka. 2021. StyleFlow: Attribute-Conditioned Exploration of StyleGAN-Generated Images Using Conditional Continuous Normalizing Flows. ACM Trans. Graph. (May 2021). https:\/\/doi.org\/10.1145\/3447648","journal-title":"Trans. Graph."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18208\u201318218","author":"Avrahami Omri","year":"2022","unstructured":"Omri Avrahami , Dani Lischinski , and Ohad Fried . 2022 . Blended diffusion for text-driven editing of natural images . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18208\u201318218 . Omri Avrahami, Dani Lischinski, and Ohad Fried. 2022. Blended diffusion for text-driven editing of natural images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18208\u201318218."},{"key":"e_1_3_2_2_4_1","unstructured":"David Bau Alex Andonian Audrey Cui YeonHwan Park Ali Jahanian Aude Oliva and Antonio Torralba. 2021. Paint by Word. arXiv:arXiv:2103.10951 David Bau Alex Andonian Audrey Cui YeonHwan Park Ali Jahanian Aude Oliva and Antonio Torralba. 2021. Paint by Word. arXiv:arXiv:2103.10951"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"#cr-split#-e_1_3_2_2_6_1.1","doi-asserted-by":"crossref","unstructured":"Zehranaz Canfes M.\u00a0Furkan Atasoy Alara Dirik and Pinar Yanardag. 2022. Text and Image Guided 3D Avatar Generation and Manipulation. https:\/\/doi.org\/10.48550\/ARXIV.2202.06079 10.48550\/ARXIV.2202.06079","DOI":"10.1109\/WACV56688.2023.00440"},{"key":"#cr-split#-e_1_3_2_2_6_1.2","doi-asserted-by":"crossref","unstructured":"Zehranaz Canfes M.\u00a0Furkan Atasoy Alara Dirik and Pinar Yanardag. 2022. Text and Image Guided 3D Avatar Generation and Manipulation. https:\/\/doi.org\/10.48550\/ARXIV.2202.06079","DOI":"10.1109\/WACV56688.2023.00440"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Eric\u00a0R. Chan Connor\u00a0Z. Lin Matthew\u00a0A. Chan Koki Nagano Boxiao Pan Shalini\u00a0De Mello Orazio Gallo Leonidas Guibas Jonathan Tremblay Sameh Khamis Tero Karras and Gordon Wetzstein. 2021. Efficient Geometry-aware 3D Generative Adversarial Networks. In arXiv. Eric\u00a0R. Chan Connor\u00a0Z. Lin Matthew\u00a0A. Chan Koki Nagano Boxiao Pan Shalini\u00a0De Mello Orazio Gallo Leonidas Guibas Jonathan Tremblay Sameh Khamis Tero Karras and Gordon Wetzstein. 2021. Efficient Geometry-aware 3D Generative Adversarial Networks. In arXiv.","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_2_8_1","unstructured":"Katherine Crowson. 2021. VQGAN-CLIP. https:\/\/github.com\/nerdyrodent\/VQGAN-CLIP Katherine Crowson. 2021. VQGAN-CLIP. https:\/\/github.com\/nerdyrodent\/VQGAN-CLIP"},{"key":"#cr-split#-e_1_3_2_2_9_1.1","unstructured":"Boris Dayma Suraj Patil Pedro Cuenca Khalid Saifullah Tanishq Abraham Phuc Le\u00a0Khac Luke Melas and Ritobrata Ghosh. 2021. DALL\u00b7E Mini. https:\/\/doi.org\/10.5281\/zenodo.5146400 10.5281\/zenodo.5146400"},{"key":"#cr-split#-e_1_3_2_2_9_1.2","unstructured":"Boris Dayma Suraj Patil Pedro Cuenca Khalid Saifullah Tanishq Abraham Phuc Le\u00a0Khac Luke Melas and Ritobrata Ghosh. 2021. DALL\u00b7E Mini. https:\/\/doi.org\/10.5281\/zenodo.5146400"},{"key":"e_1_3_2_2_10_1","volume-title":"Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning","author":"Deng Yu","unstructured":"Yu Deng , Jiaolong Yang , Dong Chen , Fang Wen , and Xin Tong . 2020. Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning . In IEEE Computer Vision and Pattern Recognition . Yu Deng, Jiaolong Yang, Dong Chen, Fang Wen, and Xin Tong. 2020. Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning. In IEEE Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_11_1","unstructured":"Haven Feng. 2019. Photometric FLAME Fitting. https:\/\/github.com\/HavenFeng\/photometric_optimization. Haven Feng. 2019. Photometric FLAME Fitting. https:\/\/github.com\/HavenFeng\/photometric_optimization."},{"key":"e_1_3_2_2_12_1","first-page":"4","article-title":"Learning an Animatable Detailed 3D Face Model from In-the-Wild Images. ACM Transactions on Graphics (ToG)","volume":"40","author":"Feng Yao","year":"2021","unstructured":"Yao Feng , Haiwen Feng , Michael\u00a0 J. Black , and Timo Bolkart . 2021 . Learning an Animatable Detailed 3D Face Model from In-the-Wild Images. ACM Transactions on Graphics (ToG) , Proc. SIGGRAPH 40 , 4 (Aug. 2021), 88:1\u201388:13. Yao Feng, Haiwen Feng, Michael\u00a0J. Black, and Timo Bolkart. 2021. Learning an Animatable Detailed 3D Face Model from In-the-Wild Images. ACM Transactions on Graphics (ToG), Proc. SIGGRAPH 40, 4 (Aug. 2021), 88:1\u201388:13.","journal-title":"Proc. SIGGRAPH"},{"key":"e_1_3_2_2_13_1","unstructured":"Rinon Gal Or Patashnik Haggai Maron Gal Chechik and Daniel Cohen-Or. 2021. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators. arxiv:2108.00946\u00a0[cs.CV] Rinon Gal Or Patashnik Haggai Maron Gal Chechik and Daniel Cohen-Or. 2021. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators. arxiv:2108.00946\u00a0[cs.CV]"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7628\u20137638","author":"Gecer Baris","year":"2021","unstructured":"Baris Gecer , Jiankang Deng , and Stefanos Zafeiriou . 2021 a. OSTeC: One-Shot Texture Completion . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7628\u20137638 . Baris Gecer, Jiankang Deng, and Stefanos Zafeiriou. 2021a. OSTeC: One-Shot Texture Completion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7628\u20137638."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the European conference on computer vision (ECCV). Springer.","author":"Gecer Baris","year":"2020","unstructured":"Baris Gecer , Alexander Lattas , Stylianos Ploumpis , Jiankang Deng , Athanasios Papaioannou , Stylianos Moschoglou , and Stefanos Zafeiriou . 2020 . Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks . In Proceedings of the European conference on computer vision (ECCV). Springer. Baris Gecer, Alexander Lattas, Stylianos Ploumpis, Jiankang Deng, Athanasios Papaioannou, Stylianos Moschoglou, and Stefanos Zafeiriou. 2020. Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks. In Proceedings of the European conference on computer vision (ECCV). Springer."},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Gecer Baris","year":"2019","unstructured":"Baris Gecer , Stylianos Ploumpis , Irene Kotsia , and Stefanos Zafeiriou . 2019 . GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Baris Gecer, Stylianos Ploumpis, Irene Kotsia, and Stefanos Zafeiriou. 2019. GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_17_1","volume-title":"Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction","author":"Gecer Baris","year":"2021","unstructured":"Baris Gecer , Stylianos Ploumpis , Irene Kotsia , and Stefanos\u00a0 P Zafeiriou . 2021b. Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2021 ). Baris Gecer, Stylianos Ploumpis, Irene Kotsia, and Stefanos\u00a0P Zafeiriou. 2021b. Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"#cr-split#-e_1_3_2_2_18_1.1","unstructured":"Thomas Gerig Andreas Morel-Forster Clemens Blumer Bernhard Egger Marcel L\u00fcthi Sandro Sch\u00f6nborn and Thomas Vetter. 2017. Morphable Face Models - An Open Framework. https:\/\/doi.org\/10.48550\/ARXIV.1709.08398 10.48550\/ARXIV.1709.08398"},{"key":"#cr-split#-e_1_3_2_2_18_1.2","doi-asserted-by":"crossref","unstructured":"Thomas Gerig Andreas Morel-Forster Clemens Blumer Bernhard Egger Marcel L\u00fcthi Sandro Sch\u00f6nborn and Thomas Vetter. 2017. Morphable Face Models - An Open Framework. https:\/\/doi.org\/10.48550\/ARXIV.1709.08398","DOI":"10.1109\/FG.2018.00021"},{"key":"e_1_3_2_2_19_1","volume-title":"GIF: Generative Interpretable Faces. In International Conference on 3D Vision (3DV). 868\u2013878","author":"Ghosh Partha","year":"2020","unstructured":"Partha Ghosh , Pravir\u00a0Singh Gupta , Roy Uziel , Anurag Ranjan , Michael\u00a0 J. Black , and Timo Bolkart . 2020 . GIF: Generative Interpretable Faces. In International Conference on 3D Vision (3DV). 868\u2013878 . http:\/\/gif.is.tue.mpg.de\/ Partha Ghosh, Pravir\u00a0Singh Gupta, Roy Uziel, Anurag Ranjan, Michael\u00a0J. Black, and Timo Bolkart. 2020. GIF: Generative Interpretable Faces. In International Conference on 3D Vision (3DV). 868\u2013878. http:\/\/gif.is.tue.mpg.de\/"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"#cr-split#-e_1_3_2_2_21_1.1","unstructured":"Nikolay Jetchev. 2021. ClipMatrix: Text-controlled Creation of 3D Textured Meshes. https:\/\/doi.org\/10.48550\/ARXIV.2109.12922 10.48550\/ARXIV.2109.12922"},{"key":"#cr-split#-e_1_3_2_2_21_1.2","unstructured":"Nikolay Jetchev. 2021. ClipMatrix: Text-controlled Creation of 3D Textured Meshes. https:\/\/doi.org\/10.48550\/ARXIV.2109.12922"},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Hk99zCeAb","author":"Karras Tero","year":"2018","unstructured":"Tero Karras , Timo Aila , Samuli Laine , and Jaakko Lehtinen . 2018 . Progressive Growing of GANs for Improved Quality, Stability, and Variation . In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Hk99zCeAb Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2018. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Hk99zCeAb"},{"key":"e_1_3_2_2_23_1","volume-title":"Proc. NeurIPS.","author":"Karras Tero","year":"2020","unstructured":"Tero Karras , Miika Aittala , Janne Hellsten , Samuli Laine , Jaakko Lehtinen , and Timo Aila . 2020 a. Training Generative Adversarial Networks with Limited Data . In Proc. NeurIPS. 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_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_2_26_1","volume-title":"SIGGRAPH Asia 2022 Conference Papers (December","author":"Khalid Nasir\u00a0Mohammad","year":"2022","unstructured":"Nasir\u00a0Mohammad Khalid , Tianhao Xie , Eugene Belilovsky , and Popa Tiberiu . 2022 . CLIP-Mesh: Generating textured meshes from text using pretrained image-text models . SIGGRAPH Asia 2022 Conference Papers (December 2022). Nasir\u00a0Mohammad Khalid, Tianhao Xie, Eugene Belilovsky, and Popa Tiberiu. 2022. CLIP-Mesh: Generating textured meshes from text using pretrained image-text models. SIGGRAPH Asia 2022 Conference Papers (December 2022)."},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). 895\u2013904","author":"Kocasari Umut","year":"2022","unstructured":"Umut Kocasari , Alara Dirik , Mert Tiftikci , and Pinar Yanardag . 2022 . StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation . In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). 895\u2013904 . Umut Kocasari, Alara Dirik, Mert Tiftikci, and Pinar Yanardag. 2022. StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). 895\u2013904."},{"key":"e_1_3_2_2_28_1","volume-title":"CONFIG: Controllable Neural Face Image Generation. In European Conference on Computer Vision (ECCV).","author":"Kowalski Marek","year":"2020","unstructured":"Marek Kowalski , Stephan\u00a0 J. Garbin , Virginia Estellers , Tadas Baltru\u0161aitis , Matthew Johnson , and Jamie Shotton . 2020 . CONFIG: Controllable Neural Face Image Generation. In European Conference on Computer Vision (ECCV). Marek Kowalski, Stephan\u00a0J. Garbin, Virginia Estellers, Tadas Baltru\u0161aitis, Matthew Johnson, and Jamie Shotton. 2020. CONFIG: Controllable Neural Face Image Generation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00084"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125598"},{"key":"e_1_3_2_2_32_1","volume-title":"StyleUV: Diverse and High-fidelity UV Map Generative Model. ArXiv abs\/2011.12893","author":"Lee Myunggi","year":"2020","unstructured":"Myunggi Lee , Wonwoong Cho , Moonheum Kim , David\u00a0 I. Inouye , and Nojun Kwak . 2020. StyleUV: Diverse and High-fidelity UV Map Generative Model. ArXiv abs\/2011.12893 ( 2020 ). Myunggi Lee, Wonwoong Cho, Moonheum Kim, David\u00a0I. Inouye, and Nojun Kwak. 2020. StyleUV: Diverse and High-fidelity UV Map Generative Model. ArXiv abs\/2011.12893 (2020)."},{"key":"e_1_3_2_2_33_1","volume-title":"Learning Formation of Physically-Based Face Attributes. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Li Ruilong","year":"2020","unstructured":"Ruilong Li , Karl Bladin , Yajie Zhao , Chinmay Chinara , Owen Ingraham , Pengda Xiang , Xinglei Ren , Pratusha Prasad , Bipin Kishore , Jun Xing , and Hao Li . 2020 . Learning Formation of Physically-Based Face Attributes. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Ruilong Li, Karl Bladin, Yajie Zhao, Chinmay Chinara, Owen Ingraham, Pengda Xiang, Xinglei Ren, Pratusha Prasad, Bipin Kishore, Jun Xing, and Hao Li. 2020. Learning Formation of Physically-Based Face Attributes. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_34_1","volume-title":"Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6","author":"Li Tianye","year":"2017","unstructured":"Tianye Li , Timo Bolkart , Michael.\u00a0 J. Black , Hao Li , and Javier Romero . 2017. Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6 ( 2017 ), 194:1\u2013194:17. Tianye Li, Timo Bolkart, Michael.\u00a0J. Black, Hao Li, and Javier Romero. 2017. Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics, (Proc. SIGGRAPH Asia) 36, 6 (2017), 194:1\u2013194:17."},{"key":"e_1_3_2_2_35_1","volume-title":"3D-FM GAN: Towards 3D-Controllable Face Manipulation. ArXiv abs\/2208.11257","author":"Liu Yuchen","year":"2022","unstructured":"Yuchen Liu , Zhixin Shu , Yijun Li , Zhe Lin , Richard Zhang , and S.\u00a0 Y. Kung . 2022. 3D-FM GAN: Towards 3D-Controllable Face Manipulation. ArXiv abs\/2208.11257 ( 2022 ). Yuchen Liu, Zhixin Shu, Yijun Li, Zhe Lin, Richard Zhang, and S.\u00a0Y. Kung. 2022. 3D-FM GAN: Towards 3D-Controllable Face Manipulation. ArXiv abs\/2208.11257 (2022)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11662\u201311672","author":"Luo Huiwen","year":"2021","unstructured":"Huiwen Luo , Koki Nagano , Han-Wei Kung , Qingguo Xu , Zejian Wang , Lingyu Wei , Liwen Hu , and Hao Li . 2021 . Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11662\u201311672 . Huiwen Luo, Koki Nagano, Han-Wei Kung, Qingguo Xu, Zejian Wang, Lingyu Wei, Liwen Hu, and Hao Li. 2021. Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11662\u201311672."},{"key":"e_1_3_2_2_38_1","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Marriott T.","year":"2021","unstructured":"Richard\u00a0 T. Marriott , Sami Romdhani , and Liming Chen . 2021 . A 3D GAN for Improved Large-pose Facial Recognition . 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 13440\u201313450. Richard\u00a0T. Marriott, Sami Romdhani, and Liming Chen. 2021. A 3D GAN for Improved Large-pose Facial Recognition. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 13440\u201313450."},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13492\u201313502","author":"Michel Oscar","year":"2022","unstructured":"Oscar Michel , Roi Bar-On , Richard Liu , Sagie Benaim , and Rana Hanocka . 2022 . Text2Mesh: Text-Driven Neural Stylization for Meshes . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13492\u201313502 . Oscar Michel, Roi Bar-On, Richard Liu, Sagie Benaim, and Rana Hanocka. 2022. Text2Mesh: Text-Driven Neural Stylization for Meshes. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13492\u201313502."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_2_41_1","volume-title":"European Conference on Computer Vision (ECCV).","author":"Petrovich Mathis","year":"2022","unstructured":"Mathis Petrovich , Michael\u00a0 J. Black , and G\u00fcl Varol . 2022 . TEMOS: Generating diverse human motions from textual descriptions . In European Conference on Computer Vision (ECCV). Mathis Petrovich, Michael\u00a0J. Black, and G\u00fcl Varol. 2022. TEMOS: Generating diverse human motions from textual descriptions. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139)","author":"Radford Alec","year":"2021","unstructured":"Alec Radford , Jong\u00a0Wook Kim , Chris Hallacy , Aditya Ramesh , Gabriel Goh , Sandhini Agarwal , Girish Sastry , Amanda Askell , Pamela Mishkin , Jack Clark , Gretchen Krueger , and Ilya Sutskever . 2021 . Learning Transferable Visual Models From Natural Language Supervision . In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139) , Marina Meila and Tong Zhang (Eds.). PMLR, 8748\u20138763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748\u20138763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"#cr-split#-e_1_3_2_2_43_1.1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. https:\/\/doi.org\/10.48550\/ARXIV.2204.06125 10.48550\/ARXIV.2204.06125"},{"key":"#cr-split#-e_1_3_2_2_43_1.2","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. https:\/\/doi.org\/10.48550\/ARXIV.2204.06125"},{"key":"#cr-split#-e_1_3_2_2_44_1.1","unstructured":"Aditya Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. https:\/\/doi.org\/10.48550\/ARXIV.2102.12092 10.48550\/ARXIV.2102.12092"},{"key":"#cr-split#-e_1_3_2_2_44_1.2","unstructured":"Aditya Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. https:\/\/doi.org\/10.48550\/ARXIV.2102.12092"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2022. DreamBooth: Fine Tuning Text-to-image Diffusion Models for Subject-Driven Generation. (2022). Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2022. DreamBooth: Fine Tuning Text-to-image Diffusion Models for Subject-Driven Generation. (2022).","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings, Part XIII","author":"Slossberg Ron","year":"2022","unstructured":"Ron Slossberg , Ibrahim Jubran , and Ron Kimmel . 2022 . Unsupervised High-Fidelity Facial Texture Generation and Reconstruction. In Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022 , Proceedings, Part XIII ( Tel Aviv, Israel). Springer-Verlag, Berlin, Heidelberg, 212\u2013229. https:\/\/doi.org\/10.1007\/978-3-031- 19778-9_13 10.1007\/978-3-031-19778-9_13 Ron Slossberg, Ibrahim Jubran, and Ron Kimmel. 2022. Unsupervised High-Fidelity Facial Texture Generation and Reconstruction. In Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XIII (Tel Aviv, Israel). Springer-Verlag, Berlin, Heidelberg, 212\u2013229. https:\/\/doi.org\/10.1007\/978-3-031-19778-9_13"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00618"},{"key":"e_1_3_2_2_48_1","volume-title":"PIE: Portrait Image Embedding for Semantic Control. ACM Trans. Graph.","author":"Tewari Ayush","year":"2020","unstructured":"Ayush Tewari , Mohamed Elgharib , Mallikarjun\u00a0 B R , Florian Bernard , Hans-Peter Seidel , Patrick P\u00e9rez , Michael Zollh\u00f6fer , and Christian Theobalt . 2020 b. PIE: Portrait Image Embedding for Semantic Control. ACM Trans. Graph. (2020). Ayush Tewari, Mohamed Elgharib, Mallikarjun\u00a0B R, Florian Bernard, Hans-Peter Seidel, Patrick P\u00e9rez, Michael Zollh\u00f6fer, and Christian Theobalt. 2020b. PIE: Portrait Image Embedding for Semantic Control. ACM Trans. Graph. (2020)."},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3835\u20133844","author":"Wang Can","year":"2022","unstructured":"Can Wang , Menglei Chai , Mingming He , Dongdong Chen , and Jing Liao . 2022 a. CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3835\u20133844 . Can Wang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. 2022a. CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3835\u20133844."},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20333\u201320342","author":"Wang Lizhen","year":"2022","unstructured":"Lizhen Wang , Zhiyuan Chen , Tao Yu , Chenguang Ma , Liang Li , and Yebin Liu . 2022 b. FaceVerse: A Fine-Grained and Detail-Controllable 3D Face Morphable Model From a Hybrid Dataset . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20333\u201320342 . Lizhen Wang, Zhiyuan Chen, Tao Yu, Chenguang Ma, Liang Li, and Yebin Liu. 2022b. FaceVerse: A Fine-Grained and Detail-Controllable 3D Face Morphable Model From a Hybrid Dataset. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20333\u201320342."},{"key":"e_1_3_2_2_51_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 18072\u201318081","author":"Wei Tianyi","year":"2022","unstructured":"Tianyi Wei , Dongdong Chen , Wenbo Zhou , Jing Liao , Zhentao Tan , Lu Yuan , Weiming Zhang , and Nenghai Yu . 2022 . HairCLIP: Design Your Hair by Text and Reference Image . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 18072\u201318081 . Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Zhentao Tan, Lu Yuan, Weiming Zhang, and Nenghai Yu. 2022. HairCLIP: Design Your Hair by Text and Reference Image. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 18072\u201318081."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Kim Youwang Kim Ji-Yeon and Tae-Hyun Oh. 2022. CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes. In ECCV. Kim Youwang Kim Ji-Yeon and Tae-Hyun Oh. 2022. CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes. In ECCV.","DOI":"10.1007\/978-3-031-20062-5_11"},{"key":"e_1_3_2_2_53_1","unstructured":"zllrunning. 2018. face-parsing.PyTorch. https:\/\/github.com\/zllrunning\/face-parsing.PyTorch. zllrunning. 2018. face-parsing.PyTorch. https:\/\/github.com\/zllrunning\/face-parsing.PyTorch."}],"event":{"name":"SIGGRAPH '23: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Los Angeles CA USA","acronym":"SIGGRAPH '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588432.3591566","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:12Z","timestamp":1750178832000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588432.3591566"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,23]]},"references-count":59,"alternative-id":["10.1145\/3588432.3591566","10.1145\/3588432"],"URL":"https:\/\/doi.org\/10.1145\/3588432.3591566","relation":{},"subject":[],"published":{"date-parts":[[2023,7,23]]},"assertion":[{"value":"2023-07-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}