{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:10:41Z","timestamp":1781086241469,"version":"3.54.1"},"publisher-location":"Cham","reference-count":84,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198359","type":"print"},{"value":"9783031198366","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19836-6_7","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T09:04:58Z","timestamp":1666343098000},"page":"106-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":102,"title":["Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-7418","authenticated-orcid":false,"given":"Xian","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2696-9664","authenticated-orcid":false,"given":"Yinghao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8764-6178","authenticated-orcid":false,"given":"Qianyi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2616-923X","authenticated-orcid":false,"given":"Hang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-8151","authenticated-orcid":false,"given":"Wayne","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4030-0684","authenticated-orcid":false,"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"7_CR1","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. In: International Conference on Machine Learning, pp. 173\u2013182. PMLR (2016)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., et al.: Mip-NeRF: a multiscale representation for anti-aliasing neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 187\u2013194 (1999)","DOI":"10.1145\/311535.311556"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Brand, M.: Voice puppetry. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 21\u201328 (1999)","DOI":"10.1145\/311535.311537"},{"key":"7_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58545-7_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Chen","year":"2020","unstructured":"Chen, L., et al.: Talking-head generation with rhythmic head motion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 35\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_3"},{"key":"7_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/978-3-030-01234-2_32","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Chen","year":"2018","unstructured":"Chen, L., Li, Z., Maddox, R.K., Duan, Z., Xu, C.: Lip movements generation at a glance. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 538\u2013553. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_32"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.K., Duan, Z., Xu, C.: Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Wang, X.: Learning continuous image representation with local implicit image function. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8628\u20138638 (2021)","DOI":"10.1109\/CVPR46437.2021.00852"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wu, Q., Zheng, C., Cham, T.J., Cai, J.: Sem2NeRF: converting single-view semantic masks to neural radiance fields. arXiv preprint arXiv:2203.10821 (2022)","DOI":"10.1007\/978-3-031-19781-9_42"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Workshop on Multi-View Lip-Reading. ACCV (2016)","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"7_CR11","unstructured":"Chung, J.S., Jamaludin, A., Zisserman, A.: You said that? arXiv preprint arXiv:1705.02966 (2017)"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"7_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-030-58577-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Das","year":"2020","unstructured":"Das, D., Biswas, S., Sinha, S., Bhowmick, B.: Speech-driven facial animation using cascaded GANs for learning of motion and texture. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 408\u2013424. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_25"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Deng, K., Liu, A., Zhu, J.Y., Ramanan, D.: Depth-supervised NeRF: fewer views and faster training for free. arXiv preprint arXiv:2107.02791 (2021)","DOI":"10.1109\/CVPR52688.2022.01254"},{"issue":"4","key":"7_CR15","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1044\/jshr.1104.796","volume":"11","author":"CG Fisher","year":"1968","unstructured":"Fisher, C.G.: Confusions among visually perceived consonants. J. Speech Hear. Res. 11(4), 796\u2013804 (1968)","journal-title":"J. Speech Hear. Res."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollh\u00f6fer, 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 (CVPR), pp. 8649\u20138658, June 2021","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., Van Der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9224\u20139232 (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"7_CR18","unstructured":"Gropp, A., Yariv, L., Haim, N., Atzmon, M., Lipman, Y.: Implicit geometric regularization for learning shapes. arXiv preprint arXiv:2002.10099 (2020)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, K., Liang, S., Liu, Y., Bao, H., Zhang, J.: AD-NeRF: audio driven neural radiance fields for talking head synthesis. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Ji, X., et al.: EAMM: one-shot emotional talking face via audio-based emotion-aware motion model. In: SIGGRAPH (2022)","DOI":"10.1145\/3528233.3530745"},{"key":"7_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015). https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"7_CR22","unstructured":"Kohli, A., Sitzmann, V., Wetzstein, G.: Inferring semantic information with 3D neural scene representations. arXiv e-prints pp. arXiv-2003 (2020)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Liang, B., et al.: Expressive talking head generation with granular audio-visual control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3387\u20133396, June 2022","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"7_CR25","unstructured":"Liu, L., Gu, J., Lin, K.Z., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. arXiv preprint arXiv:2007.11571 (2020)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Liu, L., Habermann, M., Rudnev, V., Sarkar, K., Gu, J., Theobalt, C.: Neural actor: neural free-view synthesis of human actors with pose control. arXiv preprint arXiv:2106.02019 (2021)","DOI":"10.1145\/3478513.3480528"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, Y., Peng, S., Shi, B., Pollefeys, M., Cui, Z.: DIST: rendering deep implicit signed distance function with differentiable sphere tracing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2019\u20132028 (2020)","DOI":"10.1109\/CVPR42600.2020.00209"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Visual sound localization in the wild by cross-modal interference erasing. arXiv preprint arXiv:2202.06406 2 (2022)","DOI":"10.1609\/aaai.v36i2.20073"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Learning hierarchical cross-modal association for co-speech gesture generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10462\u201310472 (2022)","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137219 (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"issue":"2","key":"7_CR31","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/2945.468400","volume":"1","author":"N Max","year":"1995","unstructured":"Max, N.: Optical models for direct volume rendering. IEEE Trans. Vis. Comput. Graph. 1(2), 99\u2013108 (1995)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: Learning 3D reconstruction in function space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4460\u20134470 (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Meshry, M., Suri, S., Davis, L.S., Shrivastava, A.: Learned spatial representations for few-shot talking-head synthesis. arXiv preprint arXiv:2104.14557 (2021)","DOI":"10.1109\/ICCV48922.2021.01357"},{"key":"7_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","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. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Narvekar, N.D., Karam, L.J.: A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection. In: 2009 International Workshop on Quality of Multimedia Experience, pp. 87\u201391. IEEE (2009)","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11453\u201311464 (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.: Differentiable volumetric rendering: Learning implicit 3d representations without 3D supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3504\u20133515 (2020)","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Noguchi, A., Sun, X., Lin, S., Harada, T.: Neural articulated radiance field. arXiv preprint arXiv:2104.03110 (2021)","DOI":"10.1109\/ICCV48922.2021.00571"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Palafox, P., Bozic, A., Thies, J., Nie\u00dfner, M., Dai, A.: Neural parametric models for 3D deformable shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), vol. 3 (2021)","DOI":"10.1109\/ICCV48922.2021.01246"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5865\u20135874 (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: HyperNeRF: a higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228 (2021)","DOI":"10.1145\/3478513.3480487"},{"key":"7_CR42","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8026\u20138037 (2019)"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Animatable neural radiance fields for human body modeling. arXiv preprint arXiv:2105.02872 (2021)","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Neural body: implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9054\u20139063 (2021)","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"7_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/978-3-030-58580-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Peng","year":"2020","unstructured":"Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part III. LNCS, vol. 12348, pp. 523\u2013540. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_31"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Pham, H.X., Cheung, S., Pavlovic, V.: Speech-driven 3D facial animation with implicit emotional awareness: a deep learning approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 80\u201388 (2017)","DOI":"10.1109\/CVPRW.2017.287"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.: A lip sync expert is all you need for speech to lip generation in the wild. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 484\u2013492 (2020)","DOI":"10.1145\/3394171.3413532"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10318\u201310327 (2021)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Raj, A., et al.: PVA: pixel-aligned volumetric avatars. arXiv preprint arXiv:2101.02697 (2021)","DOI":"10.1109\/CVPR46437.2021.01156"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Ren, D., et al.: CSG-stump: a learning friendly CSG-like representation for interpretable shape parsing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12478\u201312487 (2021)","DOI":"10.1109\/ICCV48922.2021.01225"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Richard, A., Lea, C., Ma, S., Gall, J., De la Torre, F., Sheikh, Y.: Audio-and gaze-driven facial animation of codec avatars. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 41\u201350 (2021)","DOI":"10.1109\/WACV48630.2021.00009"},{"key":"7_CR52","unstructured":"R\u00f6ssler, A., et al.: FaceForensics: a large-scale video dataset for forgery detection in human faces. arXiv preprint arXiv:1803.09179 (2018)"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Rossler, A., et al.: FaceForensics++: learning to detect manipulated facial images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1\u201311 (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PIFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"7_CR55","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: Continuous 3D-structure-aware neural scene representations. arXiv preprint arXiv:1906.01618 (2019)"},{"key":"7_CR56","unstructured":"Song, L., Wu, W., Qian, C., He, R., Loy, C.C.: Everybody\u2019s talkin\u2019: Let me talk as you want. arXiv preprint arXiv:2001.05201 (2020)"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhu, J., Li, D., Wang, X., Qi, H.: Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786 (2018)","DOI":"10.24963\/ijcai.2019\/129"},{"key":"7_CR58","unstructured":"Sun, T., Lin, K.E., Bi, S., Xu, Z., Ramamoorthi, R.: Nelf: neural light-transport field for portrait view synthesis and relighting. arXiv preprint arXiv:2107.12351 (2021)"},{"issue":"4","key":"7_CR59","doi-asserted-by":"publisher","first-page":"1","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), 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"7_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1007\/978-3-030-58517-4_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Thies","year":"2020","unstructured":"Thies, J., Elgharib, M., Tewari, A., Theobalt, C., Nie\u00dfner, M.: Neural voice puppetry: audio-driven facial reenactment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 716\u2013731. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_42"},{"key":"7_CR61","doi-asserted-by":"crossref","unstructured":"Tretschk, E., Tewari, A., Golyanik, V., Zollhofer, M., Lassner, C., Theobalt, C.: Non-rigid neural radiance fields: Reconstruction and novel view synthesis of a dynamic scene from monocular video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12959\u201312970 (2021)","DOI":"10.1109\/ICCV48922.2021.01272"},{"issue":"5","key":"7_CR62","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1007\/s11263-019-01251-8","volume":"128","author":"K Vougioukas","year":"2020","unstructured":"Vougioukas, K., Petridis, S., Pantic, M.: Realistic speech-driven facial animation with GANs. Int. J. Comput. Vis. 128(5), 1398\u20131413 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1007\/978-3-030-58589-1_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Wang","year":"2020","unstructured":"Wang, K., et al.: MEAD: a large-scale audio-visual dataset for emotional talking-face generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 700\u2013717. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_42"},{"key":"7_CR64","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. In: NeurIPS (2021)"},{"key":"7_CR65","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, L., Ding, Y., Fan, C., Yu, X.: Audio2Head: audio-driven one-shot talking-head generation with natural head motion. arXiv preprint arXiv:2107.09293 (2021)","DOI":"10.24963\/ijcai.2021\/152"},{"key":"7_CR66","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Mallya, A., Liu, M.Y.: One-shot free-view neural talking-head synthesis for video conferencing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10039\u201310049 (2021)","DOI":"10.1109\/CVPR46437.2021.00991"},{"issue":"4","key":"7_CR67","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-030-01261-8_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"O Wiles","year":"2018","unstructured":"Wiles, O., Koepke, A.S., Zisserman, A.: X2Face: a network for controlling face generation using images, audio, and pose codes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 690\u2013706. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_41"},{"key":"7_CR69","doi-asserted-by":"crossref","unstructured":"Wu, H., Jia, J., Wang, H., Dou, Y., Duan, C., Deng, Q.: Imitating arbitrary talking style for realistic audio-driven talking face synthesis. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1478\u20131486 (2021)","DOI":"10.1145\/3474085.3475280"},{"key":"7_CR70","doi-asserted-by":"crossref","unstructured":"Wu, Q., et al.: Object-compositional neural implicit surfaces. arXiv preprint arXiv:2207.09686 (2022)","DOI":"10.1109\/ICCV51070.2023.01989"},{"key":"7_CR71","unstructured":"Xu, X., Pan, X., Lin, D., Dai, B.: Generative occupancy fields for 3D surface-aware image synthesis. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"issue":"10","key":"7_CR72","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"7_CR73","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Learning object-compositional neural radiance field for editable scene rendering. In: International Conference on Computer Vision (ICCV), October 2021","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"7_CR74","unstructured":"Yariv, L., Gu, J., Kasten, Y., Lipman, Y.: Volume rendering of neural implicit surfaces. arXiv preprint arXiv:2106.12052 (2021)"},{"key":"7_CR75","unstructured":"Yariv, L., et al: Multiview neural surface reconstruction by disentangling geometry and appearance. In: Advances in Neural Information Processing Systems 33 (2020)"},{"key":"7_CR76","unstructured":"Yi, R., Ye, Z., Zhang, J., Bao, H., Liu, Y.J.: Audio-driven talking face video generation with learning-based personalized head pose. arXiv preprint arXiv:2002.10137 (2020)"},{"key":"7_CR77","doi-asserted-by":"crossref","unstructured":"Zakharov, E., Shysheya, A., Burkov, E., Lempitsky, V.: Few-shot adversarial learning of realistic neural talking head models. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00955"},{"key":"7_CR78","unstructured":"Zhang, J.Y., Yang, G., Tulsiani, S., Ramanan, D.: NeRS: neural reflectance surfaces for sparse-view 3D reconstruction in the wild. In: Conference on Neural Information Processing Systems (2021)"},{"issue":"1","key":"7_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3446328","volume":"40","author":"X Zhang","year":"2021","unstructured":"Zhang, X., et al.: Neural light transport for relighting and view synthesis. ACM Trans. Graph. (TOG) 40(1), 1\u201317 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"7_CR80","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.: In-place scene labelling and understanding with implicit scene representation. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"7_CR81","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Y., Liu, Z., Luo, P., Wang, X.: Talking face generation by adversarially disentangled audio-visual representation. In: AAAI Conference on Artificial Intelligence (AAAI) (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"7_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, H., Sun, Y., Wu, W., Loy, C.C., Wang, X., Liu, Z.: Pose-controllable talking face generation by implicitly modularized audio-visual representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4176\u20134186 (2021)","DOI":"10.1109\/CVPR46437.2021.00416"},{"issue":"6","key":"7_CR83","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Han, X., Shechtman, E., Echevarria, J., Kalogerakis, E., Li, D.: MakeltTalk: speaker-aware talking-head animation. ACM Trans. Graph. (TOG) 39(6), 1\u201315 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"7_CR84","unstructured":"Zhu, H., Huang, H., Li, Y., Zheng, A., He, R.: Arbitrary talking face generation via attentional audio-visual coherence learning. arXiv preprint arXiv:1812.06589 (2018)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19836-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T08:42:07Z","timestamp":1728204127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19836-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198359","9783031198366"],"references-count":84,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19836-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}