{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:46:36Z","timestamp":1779295596867,"version":"3.51.4"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729195","type":"print"},{"value":"9783031729201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-72920-1_1","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:02:57Z","timestamp":1727683377000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Tri$$^{2}$$-plane: Thinking Head Avatar via\u00a0Feature Pyramid"],"prefix":"10.1007","author":[{"given":"Luchuan","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lele","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guojun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2StyleGAN: how to embed images into the StyleGAN latent space? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4432\u20134441 (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Y., et al.: High-fidelity facial avatar reconstruction from monocular video with generative priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4541\u20134551 (2023)","DOI":"10.1109\/CVPR52729.2023.00441"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Seminal Graphics Papers: Pushing the Boundaries, vol. 2, pp. 157\u2013164 (2023)","DOI":"10.1145\/3596711.3596730"},{"key":"1_CR4","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":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Wang, X., Yu, K., Dong, C., Loy, C.C.: BasicVSR: the search for essential components in video super-resolution and beyond. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4947\u20134956 (2021)","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Zhou, S., Xu, X., Loy, C.C.: BasicVSR++: improving video super-resolution with enhanced propagation and alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5972\u20135981 (2022)","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., Li, Z., Maddox, R.K., Duan, Z., Xu, C.: Lip movements generation at a glance. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 520\u2013535 (2018)","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Xu, S., Chen, D., Jia, Y., Tong, X.: Accurate 3D face reconstruction with weakly-supervised learning: from single image to image set. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00038"},{"issue":"2","key":"1_CR10","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2015","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295\u2013307 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollhofer, M., Nie\u00dfner, M.: Dynamic neural radiance fields for monocular 4d facial avatar reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8649\u20138658 (2021)","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Gao, X., Zhong, C., Xiang, J., Hong, Y., Guo, Y., Zhang, J.: Reconstructing personalized semantic facial nerf models from monocular video. ACM Trans. Graph. (Proceedings of SIGGRAPH Asia) 41(6) (2022). https:\/\/doi.org\/10.1145\/3550454.3555501","DOI":"10.1145\/3550454.3555501"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Gerig, T., et al.: Morphable face models-an open framework. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 75\u201382. IEEE (2018)","DOI":"10.1109\/FG.2018.00021"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"issue":"11","key":"1_CR15","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"},{"issue":"6","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1294","DOI":"10.1109\/TPAMI.2018.2837742","volume":"41","author":"Y Guo","year":"2018","unstructured":"Guo, Y., Cai, J., Jiang, B., Zheng, J., et al.: CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images. IEEE Trans. Pattern Anal. Mach. Intell. 41(6), 1294\u20131307 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR17","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":"1_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Hu, W., et al.: Tri-MipRF: Tri-mip representation for efficient anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19774\u201319783 (2023)","DOI":"10.1109\/ICCV51070.2023.01811"},{"key":"1_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1007\/978-3-031-44195-0_30","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2023","author":"Y Huang","year":"2023","unstructured":"Huang, Y., et al.: Boosting video super resolution with patch-based temporal redundancy optimization. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds.) ICANN 2023. LNCS, vol. 14260, pp. 362\u2013375. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-44195-0_30"},{"key":"1_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part II. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"1_CR22","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":"1_CR23","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"},{"issue":"4","key":"1_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201283","volume":"37","author":"H Kim","year":"2018","unstructured":"Kim, H., et al.: Deep video portraits. ACM Trans. Graph. (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"1_CR26","doi-asserted-by":"publisher","unstructured":"Kirschstein, T., Qian, S., Giebenhain, S., Walter, T., Nie\u00dfner, M.: NeRSemble: multi-view radiance field reconstruction of human heads. ACM Trans. Graph. 42(4) (2023). https:\/\/doi.org\/10.1145\/3592455","DOI":"10.1145\/3592455"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Tan, C., Liu, H., Huang, W.: Deep feature pyramid reconfiguration for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 169\u2013185 (2018)","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, J., Bai, X., Zhou, J., Gu, L.: Efficient region-aware neural radiance fields for high-fidelity talking portrait synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7568\u20137578 (2023)","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"1_CR29","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":"1_CR30","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: One-shot high-fidelity talking-head synthesis with deformable neural radiance field. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17969\u201317978 (2023)","DOI":"10.1109\/CVPR52729.2023.01723"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1_CR34","unstructured":"Lugaresi, C., et\u00a0al.: MediaPipe: a framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Ma, Z., Zhu, X., Qi, G.J., Lei, Z., Zhang, L.: OTAvatar: one-shot talking face avatar with controllable tri-plane rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16901\u201316910 (2023)","DOI":"10.1109\/CVPR52729.2023.01621"},{"key":"1_CR36","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440 (2015)"},{"issue":"1","key":"1_CR37","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"1_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"Nagrani, A., Chung, J.S., Xie, W., Zisserman, A.: VoxCeleb: large-scale speaker verification in the wild. Comput. Speech Lang. 60, 101027 (2020)","journal-title":"Comput. Speech Lang."},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 821\u2013830 (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Qian, S., Kirschstein, T., Schoneveld, L., Davoli, D., Giebenhain, S., Nie\u00dfner, M.: GaussianAvatars: photorealistic head avatars with rigged 3D gaussians. arXiv preprint arXiv:2312.02069 (2023)","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: Encoding in style: a StyleGAN encoder for image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2287\u20132296 (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"issue":"1","key":"1_CR42","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":"1_CR43","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, Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Saito, S., Schwartz, G., Simon, T., Li, J., Nam, G.: Relightable gaussian codec avatars. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00021"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Shen, Y., Zhou, B.: Closed-form factorization of latent semantics in GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1532\u20131540 (2021)","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"1_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/978-3-031-19787-1_23","volume-title":"Computer Vision - ECCV 2022","author":"Z Shi","year":"2022","unstructured":"Shi, Z., Shen, Y., Zhu, J., Yeung, D.Y., Chen, Q.: 3D-aware indoor scene synthesis with depth priors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13676, pp. 406\u2013422. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_23"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Song, L., Liu, B., Yin, G., Dong, X., Zhang, Y., Bai, J.X.: TACR-net: editing on deep video and voice portraits. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 478\u2013486 (2021)","DOI":"10.1145\/3474085.3475196"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Song, L., Liu, P., Yin, G., Xu, C.: Adaptive super resolution for one-shot talking-head generation. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4115\u20134119. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446837"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Song, L., Yin, G., Jin, Z., Dong, X., Xu, C.: Emotional listener portrait: neural listener head generation with emotion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20839\u201320849 (2023)","DOI":"10.1109\/ICCV51070.2023.01905"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Song, L., Yin, G., Liu, B., Zhang, Y., Yu, N.: FSFT-net: face transfer video generation with few-shot views. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3582\u20133586. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506512"},{"issue":"6","key":"1_CR51","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":"1_CR52","doi-asserted-by":"crossref","unstructured":"Sun, J., Wang, X., Wang, L., Li, X., Zhang, Y., Zhang, H., Liu, Y.: Next3D: generative neural texture rasterization for 3D-aware head avatars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20991\u201321002 (2023)","DOI":"10.1109\/CVPR52729.2023.02011"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Sun, J., Wang, X., Zhang, Y., Li, X., Zhang, Q., Liu, Y., Wang, J.: FENeRF: face editing in neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7672\u20137682 (2022)","DOI":"10.1109\/CVPR52688.2022.00752"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1_CR55","unstructured":"Tang, J., et al.: Real-time neural radiance talking portrait synthesis via audio-spatial decomposition. arXiv preprint arXiv:2211.12368 (2022)"},{"key":"1_CR56","doi-asserted-by":"crossref","unstructured":"Teotia, K., et\u00a0al.: HQ3DAvatar: high quality controllable 3D head avatar. arXiv preprint arXiv:2303.14471 (2023)","DOI":"10.1145\/3649889"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Trevithick, A., Chan, M., et al.: Real-time radiance fields for single-image portrait view synthesis. ACM Trans. Graph. (SIGGRAPH) (2023)","DOI":"10.1145\/3592460"},{"key":"1_CR58","unstructured":"Voynov, A., Babenko, A.: Unsupervised discovery of interpretable directions in the GAN latent space. In: International Conference on Machine Learning, pp. 9786\u20139796. PMLR (2020)"},{"key":"1_CR59","unstructured":"Wang, J., Xie, J.C., Li, X., Xu, F., Pun, C.M., Gao, H.: GaussianHead: high-fidelity head avatars with learnable Gaussian derivation (2024)"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Wang, L., Chen, Z., Yu, T., Ma, C., Li, L., Liu, Y.: 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, pp. 20333\u201320342 (2022)","DOI":"10.1109\/CVPR52688.2022.01969"},{"key":"1_CR61","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: StyleAvatar: real-time photo-realistic portrait avatar from a single video. arXiv preprint arXiv:2305.00942 (2023)","DOI":"10.1145\/3588432.3591517"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, H., Wang, L., Zhao, X., Huang, H., Qi, G., Liu, Y.: LatentAvatar: learning latent expression code for expressive neural head avatar. arXiv preprint arXiv:2305.01190 (2023)","DOI":"10.1145\/3588432.3591545"},{"issue":"6","key":"1_CR63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555437","volume":"41","author":"S Yang","year":"2022","unstructured":"Yang, S., Jiang, L., Liu, Z., Loy, C.C.: VToonify: controllable high-resolution portrait video style transfer. ACM Trans. Graph. (TOG) 41(6), 1\u201315 (2022). https:\/\/doi.org\/10.1145\/3550454.3555437","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Yu, W., et\u00a0al.: NOFA: NeRF-based one-shot facial avatar reconstruction. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201312 (2023)","DOI":"10.1145\/3588432.3591555"},{"key":"1_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/978-3-030-58604-1_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Zhang, H., Tang, J., Wang, M., Hua, X., Sun, Q.: Feature pyramid transformer. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXVIII. LNCS, vol. 12373, pp. 323\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_20"},{"key":"1_CR66","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":"1_CR67","doi-asserted-by":"crossref","unstructured":"Zhao, G., Ge, W., Yu, Y.: GraphFPN: graph feature pyramid network for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2763\u20132772 (2021)","DOI":"10.1109\/ICCV48922.2021.00276"},{"key":"1_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, X., Wang, L., Sun, J., Zhang, H., Suo, J., Liu, Y.: HAvatar: high-fidelity head avatar via facial model conditioned neural radiance field. ACM Trans. Graph. (2023)","DOI":"10.1145\/3626316"},{"key":"1_CR69","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Abrevaya, V.F., B\u00fchler, M.C., Chen, X., Black, M.J., Hilliges, O.: IM avatar: Implicit morphable head avatars from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13545\u201313555 (2022)","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Yifan, W., Wetzstein, G., Black, M.J., Hilliges, O.: PointAvatar: deformable point-based head avatars from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21057\u201321067 (2023)","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Zielonka, W., Bolkart, T., Thies, J.: Instant volumetric head avatars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4574\u20134584 (2023)","DOI":"10.1109\/CVPR52729.2023.00444"}],"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\/978-3-031-72920-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:03:50Z","timestamp":1727683430000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72920-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729195","9783031729201"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72920-1_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 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"}}]}}