{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:13:02Z","timestamp":1742911982530,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729065"},{"type":"electronic","value":"9783031729072"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72907-2_8","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"124-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient 3D-Aware Facial Image Editing via\u00a0Attribute-Specific Prompt Learning"],"prefix":"10.1007","author":[{"given":"Amandeep","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Awais","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanath","family":"Narayan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"issue":"3","key":"8_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447648","volume":"40","author":"R Abdal","year":"2021","unstructured":"Abdal, R., Zhu, P., Mitra, N.J., Wonka, P.: StyleFlow: attribute-conditioned exploration of StyleGAN-generated images using conditional continuous normalizing flows. ACM Trans. Graph. (ToG) 40(3), 1\u201321 (2021)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"8_CR2","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS, vol. 35 (2022)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Berg, H., et al.: A prompt array keeps the bias away: debiasing vision-language models with adversarial learning. arXiv preprint arXiv:2203.11933 (2022)","DOI":"10.18653\/v1\/2022.aacl-main.61"},{"key":"8_CR4","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd GANs. arXiv preprint arXiv:1801.01401 (2018)"},{"key":"8_CR5","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cai, S., Obukhov, A., Dai, D., Van\u00a0Gool, L.: Pix2NeRF: unsupervised conditional p-GAN for single image to neural radiance fields translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3981\u20133990 (2022)","DOI":"10.1109\/CVPR52688.2022.00395"},{"key":"8_CR7","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":"8_CR8","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":"8_CR9","doi-asserted-by":"crossref","unstructured":"Collins, E., Bala, R., Price, B., Susstrunk, S.: Editing in style: uncovering the local semantics of GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5771\u20135780 (2020)","DOI":"10.1109\/CVPR42600.2020.00581"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4685\u20134694 (2018)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Maji, S., Wang, R.: 3D shape induction from 2D views of multiple objects. In: 2017 International Conference on 3D Vision (3DV), pp. 402\u2013411. IEEE (2017)","DOI":"10.1109\/3DV.2017.00053"},{"key":"8_CR12","unstructured":"Gal, R., Patashnik, O., Maron, H., Chechik, G., Cohen-Or, D.: StyleGAN-nada: clip-guided domain adaptation of image generators. arXiv abs\/2108.00946 (2021)"},{"issue":"11","key":"8_CR13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"8_CR14","unstructured":"Gu, J., Liu, L., Wang, P., Theobalt, C.: StyleNeRF: a style-based 3d-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985 (2021)"},{"key":"8_CR15","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., Paris, S.: GANSpace: Discovering interpretable GAN controls. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9841\u20139850 (2020)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Henzler, P., Mitra, N.J., Ritschel, T.: Escaping Plato\u2019s cave: 3D shape from adversarial rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9984\u20139993 (2019)","DOI":"10.1109\/ICCV.2019.01008"},{"key":"8_CR17","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. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"8_CR18","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML. PMLR (2021)"},{"key":"8_CR19","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":"8_CR20","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12104\u201312114 (2020)"},{"key":"8_CR21","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":"8_CR22","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":"8_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Kumar, A., et al.: Generative multiplane neural radiance for 3D-aware image generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7388\u20137398 (2023)","DOI":"10.1109\/ICCV51070.2023.00679"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Preim3D: 3D consistent precise image attribute editing from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8549\u20138558 (2023)","DOI":"10.1109\/CVPR52729.2023.00826"},{"key":"8_CR26","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML. PMLR (2022)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Liao, Y., Schwarz, K., Mescheder, L., Geiger, A.: Towards unsupervised learning of generative models for 3D controllable image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5871\u20135880 (2020)","DOI":"10.1109\/CVPR42600.2020.00591"},{"key":"8_CR28","unstructured":"Lin, C.Z., Lindell, D.B., Chan, E.R., Wetzstein, G.: 3D GAN inversion for controllable portrait image animation. arXiv preprint arXiv:2203.13441 (2022)"},{"key":"8_CR29","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"8_CR30","unstructured":"Nguyen-Phuoc, T.H., Richardt, C., Mai, L., Yang, Y., Mitra, N.: BlockGAN: learning 3D object-aware scene representations from unlabelled images. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6767\u20136778 (2020)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of StyleGAN imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2085\u20132094 (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"8_CR32","unstructured":"Qiu, J., et al.: Benchmarking robustness of multimodal image-text models under distribution shift. J. Data-Centric Mach. Learn. Res. (2023)"},{"key":"8_CR33","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML. PMLR (2021)"},{"key":"8_CR34","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"issue":"1","key":"8_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3544777","volume":"42","author":"D Roich","year":"2022","unstructured":"Roich, D., Mokady, R., Bermano, A.H., Cohen-Or, D.: Pivotal tuning for latent-based editing of real images. ACM Trans. Graph. (TOG) 42(1), 1\u201313 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR36","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: GRAF: generative radiance fields for 3D-aware image synthesis. In: Advances in Neural Information Processing Systems, vol. 33, pp. 20154\u201320166 (2020)"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of GANs for semantic face editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9243\u20139252 (2020)","DOI":"10.1109\/CVPR42600.2020.00926"},{"issue":"4","key":"8_CR38","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":"8_CR39","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Flava: a foundational language and vision alignment model. In: Proceedings of the IEEE CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"issue":"6","key":"8_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555506","volume":"41","author":"J Sun","year":"2022","unstructured":"Sun, J., Wang, X., Shi, Y., Wang, L., Wang, J., Liu, Y.: IDE-3D: interactive disentangled editing for high-resolution 3D-aware portrait synthesis. ACM Trans. Graph. (ToG) 41(6), 1\u201310 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"8_CR41","unstructured":"Szab\u00f3, A., Meishvili, G., Favaro, P.: Unsupervised generative 3D shape learning from natural images. arXiv preprint arXiv:1910.00287 (2019)"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Tewari, A., et al.: StyleRig: rigging StyleGAN for 3D control over portrait images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6142\u20136151 (2020)","DOI":"10.1109\/CVPR42600.2020.00618"},{"issue":"4","key":"8_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459838","volume":"40","author":"O Tov","year":"2021","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for StyleGAN image manipulation. ACM Trans. Graph. (TOG) 40(4), 1\u201314 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR44","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., Shechtman, E.: Stylespace analysis: disentangled controls for StyleGAN image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12863\u201312872 (2021)","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Xie, J., Ouyang, H., Piao, J., Lei, C., Chen, Q.: High-fidelity 3D GAN inversion by pseudo-multi-view optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 321\u2013331 (2023)","DOI":"10.1109\/CVPR52729.2023.00039"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Xu, Y., Peng, S., Yang, C., Shen, Y., Zhou, B.: 3D-aware image synthesis via learning structural and textural representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18430\u201318439 (2022)","DOI":"10.1109\/CVPR52688.2022.01788"},{"key":"8_CR48","unstructured":"Yao, L., et al.: Filip: fine-grained interactive language-image pre-training. In: ICLR (2021)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Yu, Y., et al.: Towards counterfactual image manipulation via clip. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3637\u20133645 (2022)","DOI":"10.1145\/3503161.3547935"},{"key":"8_CR50","unstructured":"Yuan, L., et\u00a0al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"8_CR51","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-031-20065-6_2","volume-title":"ECCV 2022","author":"X Zhao","year":"2022","unstructured":"Zhao, X., Ma, F., G\u00fcera, D., Ren, Z., Schwing, A.G., Colburn, A.: Generative multiplane images: making a 2D GAN 3D-aware. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 18\u201335. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_2"},{"key":"8_CR52","unstructured":"Zhou, P., Xie, L., Ni, B., Tian, Q.: CIPS-3D: a 3D-aware generator of GANs based on conditionally-independent pixel synthesis. arXiv preprint arXiv:2110.09788 (2021)"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)","DOI":"10.1145\/3197517.3201323"},{"key":"8_CR54","unstructured":"Zhu, J.Y., et al.: Visual object networks: image generation with disentangled 3D representations. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"}],"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\/978-3-031-72907-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:16:35Z","timestamp":1732976195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72907-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729065","9783031729072"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72907-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}