{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:37:32Z","timestamp":1784644652449,"version":"3.55.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012601","type":"print"},{"value":"9783030012618","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01261-8_41","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T16:14:51Z","timestamp":1539015291000},"page":"690-706","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":292,"title":["X2Face: A Network for Controlling Face Generation Using Images, Audio, and Pose Codes"],"prefix":"10.1007","author":[{"given":"Olivia","family":"Wiles","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. Sophia","family":"Koepke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"issue":"6","key":"41_CR1","first-page":"196","volume":"36","author":"H Averbuch-Elor","year":"2017","unstructured":"Averbuch-Elor, H., Cohen-Or, D., Kopf, J., Cohen, M.F.: Bringing portraits to life. ACM Trans. Graph. (Proceeding of SIGGRAPH Asia 2017) 36(6), 196 (2017)","journal-title":"ACM Trans. Graph. (Proceeding of SIGGRAPH Asia 2017)"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Bas, A., Smith, W.A.P., Awais, M., Kittler, J.: 3D morphable models as spatial transformer networks. In: Proceedings of ICCV Workshop on Geometry Meets Deep Learning (2017)","DOI":"10.1109\/ICCVW.2017.110"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of ACM SIGGRAPH (1999)","DOI":"10.1145\/311535.311556"},{"issue":"2\u20134","key":"41_CR4","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s11263-017-1009-7","volume":"126","author":"J Booth","year":"2018","unstructured":"Booth, J., Roussos, A., Ponniah, A., Dunaway, D., Zafeiriou, S.: Large scale 3D morphable models. IJCV 126(2\u20134), 233\u2013254 (2018)","journal-title":"IJCV"},{"key":"41_CR5","unstructured":"Cao, J., Hu, Y., Yu, B., He, R., Sun, Z.: Load balanced GANs for multi-view face image synthesis. arXiv preprint arXiv:1802.07447 (2018)"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.168"},{"key":"41_CR7","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: NIPS (2016)"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"41_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"issue":"6","key":"41_CR10","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1145\/2070781.2024164","volume":"30","author":"K Dale","year":"2011","unstructured":"Dale, K., Sunkavalli, K., Johnson, M.K., Vlasic, D., Matusik, W., Pfister, H.: Video face replacement. ACM Trans. Graph. (TOG) 30(6), 130 (2011)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR11","unstructured":"Denton, E.L., Birodkar, V.: Unsupervised learning of disentangled representations from video. In: NIPS (2017)"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Ding, H., Sricharan, K., Chellappa, R.: ExprGAN: facial expression editing with controllable expression intensity. In: Proceedings of AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12277"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Hassner, T., Harel, S., Paz, E., Enbar, R.: Effective face frontalization in unconstrained images. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299058"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"issue":"4","key":"41_CR16","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/3072959.3073658","volume":"36","author":"T Karras","year":"2017","unstructured":"Karras, T., Aila, T., Laine, S., Herva, A., Lehtinen, J.: Audio-driven facial animation by joint end-to-end learning of pose and emotion. ACM Trans. Graph. (TOG) 36(4), 94 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Kim, H., et al.: Deep video portraits. In: Proceedings of ACM SIGGRAPH (2018)","DOI":"10.1145\/3197517.3201283"},{"key":"41_CR18","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King, D.E.: Dlib-ml: a machine learning toolkit. J. Mach. Learn. Res. 10, 1755\u20131758 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Koestinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: Proceedings of First IEEE International Workshop on Benchmarking Facial Image Analysis Technologies (2011)","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Korshunova, I., Shi, W., Dambre, J., Theis, L.: Fast face-swap using convolutional neural networks. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.397"},{"key":"41_CR21","unstructured":"Kulkarni, T.D., Whitney, W.F., Kohli, P., Tenenbaum, J.: Deep convolutional inverse graphics network. In: NIPS (2015)"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Kumar, A., Alavi, A., Chellappa, R.: KEPLER: keypoint and pose estimation of unconstrained faces by learning efficient H-CNN regressors. In: Proceedings of the International Conference on Automatic Face and Gesture Recognition (2017)","DOI":"10.1109\/FG.2017.149"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Masi, I., Tran, A.T., Hassner, T., Medioni, G.: On face segmentation, face swapping, and face perception. In: Proceedings of International Conference on Automatic Face and Gesture Recognition (2018)","DOI":"10.1109\/FG.2018.00024"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Olszewski, K., et al.: Realistic dynamic facial textures from a single image using GANs. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.580"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: Proceedings of BMVC (2015)","DOI":"10.5244\/C.29.41"},{"key":"41_CR27","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"issue":"3","key":"41_CR28","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1145\/882262.882269","volume":"22","author":"P P\u00e9rez","year":"2003","unstructured":"P\u00e9rez, P., Gangnet, M., Blake, A.: Poisson image editing. ACM Trans. Graph. (TOG) 22(3), 313\u2013318 (2003)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR29","unstructured":"P\u0103tr\u0103ucean, V., Handa, A., Cipolla, R.: Spatio-temporal video autoencoder with differentiable memory. In: NIPS (2016)"},{"key":"41_CR30","unstructured":"Qiao, F., Yao, N., Jiao, Z., Li, Z., Chen, H., Wang, H.: Geometry-contrastive generative adversarial network for facial expression synthesis. arXiv preprint arXiv:1802.01822 (2018)"},{"issue":"3","key":"41_CR31","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1145\/1360612.1360616","volume":"27","author":"A Rav-Acha","year":"2008","unstructured":"Rav-Acha, A., Kohli, P., Rother, C., Fitzgibbon, A.: Unwrap mosaics: a new representation for video editing. ACM Trans. Graph. (TOG) 27(3), 17 (2008)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR32","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":"41_CR33","doi-asserted-by":"crossref","unstructured":"Roth, J., Tong, Y., Liu, X.: Adaptive 3D face reconstruction from unconstrained photo collections. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.455"},{"key":"41_CR34","doi-asserted-by":"crossref","unstructured":"Saito, S., Wei, L., Hu, L., Nagano, K., Li, H.: Photorealistic facial texture inference using deep neural networks. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.250"},{"key":"41_CR35","doi-asserted-by":"crossref","unstructured":"Saragih, J.M., Lucey, S., Cohn, J.F.: Real-time avatar animation from a single image. In: Proceedings of International Conference on Automatic Face and Gesture Recognition (2011)","DOI":"10.1109\/FG.2011.5771400"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Shlizerman, E., Dery, L., Schoen, H., Kemelmacher-Shlizerman, I.: Audio to body dynamics. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00790"},{"key":"41_CR37","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"issue":"4","key":"41_CR38","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/3072959.3073640","volume":"36","author":"S Suwajanakorn","year":"2017","unstructured":"Suwajanakorn, S., Seitz, S.M., Kemelmacher-Shlizerman, I.: Synthesizing Obama: learning lip sync from audio. ACM Trans. Graph. (TOG) 36(4), 95 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Tewari, A., et al.: Mofa: model-based deep convolutional face autoencoder for unsupervised monocular reconstruction. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.401"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Thies, J., Zollh\u00f6fer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: Face2Face: real-time face capture and reenactment of RGB videos. In: Proceedings of CVPR (2016)","DOI":"10.1145\/2929464.2929475"},{"key":"41_CR41","doi-asserted-by":"crossref","unstructured":"Tran, A.T., Hassner, T., Masi, I., Paz, E., Nirkin, Y., Medioni, G.: Extreme 3D face reconstruction: Seeing through occlusions. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00414"},{"key":"41_CR42","doi-asserted-by":"crossref","unstructured":"Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.141"},{"issue":"3","key":"41_CR43","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1145\/1073204.1073209","volume":"24","author":"D Vlasic","year":"2005","unstructured":"Vlasic, D., Brand, M., Pfister, H., Popovi\u0107, J.: Face transfer with multilinear models. ACM Trans. Graph. (TOG) 24(3), 426\u2013433 (2005)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR44","doi-asserted-by":"crossref","unstructured":"Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J.: Interpretable transformations with encoder-decoder networks. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.611"},{"key":"41_CR45","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"41_CR46","doi-asserted-by":"crossref","unstructured":"Zollh\u00f6fer, M., Thies, J., Garrido, P., Bradley, D., Beeler, T., P\u00e9rez, P., Stamminger, M., Nie\u00dfner, M., Theobalt, C.: State of the art on monocular 3D face reconstruction, tracking, and applications. In: Proceedings of Eurographics (2018)","DOI":"10.1111\/cgf.13382"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01261-8_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:44:20Z","timestamp":1665189860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01261-8_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012601","9783030012618"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01261-8_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}