{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T22:07:24Z","timestamp":1789769244497,"version":"4.0.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00371-025-04195-y","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T14:44:00Z","timestamp":1759848240000},"page":"12953-12966","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["GaPTalk: precision-controlled 3D Gaussian rendering for personalized talking-head synthesis"],"prefix":"10.1007","volume":"41","author":[{"given":"Xiaoli","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangyi","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuhui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"key":"4195_CR1","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9299\u20139306 (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"4195_CR2","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7832\u20137841 (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"4195_CR3","doi-asserted-by":"publisher","unstructured":"Prajwal, K.R., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.V.: 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. MM \u201920, Association for Computing Machinery, New York, NY, USA (2020), pp. 484\u2013492. https:\/\/doi.org\/10.1145\/3394171.3413532","DOI":"10.1145\/3394171.3413532"},{"key":"4195_CR4","unstructured":"Zhang, Y., Liu, M., Chen, Z., Wu, B., Zeng, Y., Zhan, C., He, Y., Huang, J., Zhou, W.: Musetalk: real-time high quality lip synchronization with latent space inpainting. arXiv preprint arXiv:2410.10122 (2024)"},{"issue":"7","key":"4195_CR5","doi-asserted-by":"publisher","first-page":"4913","DOI":"10.1007\/s00371-024-03490-4","volume":"40","author":"H Fang","year":"2024","unstructured":"Fang, H., Weng, D., Tian, Z., Ma, Y.: Manitalk: manipulable talking head generation from single image in the wild. Vis. Comput. 40(7), 4913\u20134925 (2024)","journal-title":"Vis. Comput."},{"key":"4195_CR6","doi-asserted-by":"crossref","unstructured":"Ying, T., Yazhi, L., Xiong, L., Wei, L.: Adaptive diffusion landmark dynamic rendering for realistic talking face video generation. Vis. Comput. pp. 1\u201311 (2025)","DOI":"10.1007\/s00371-025-03907-8"},{"key":"4195_CR7","doi-asserted-by":"crossref","unstructured":"Tian, L., Wang, Q., Zhang, B., Bo, L.: Emo: emote portrait alive generating expressive portrait videos with audio2video diffusion model under weak conditions. In: European Conference on Computer Vision, pp. 244\u2013260. Springer (2024)","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"4195_CR8","doi-asserted-by":"crossref","unstructured":"Shen, S., Zhao, W., Meng, Z., Li, W., Zhu, Z., Zhou, J., Lu, J.: Difftalk: crafting diffusion models for generalized audio-driven portraits animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1982\u20131991 (2023)","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"4195_CR9","doi-asserted-by":"crossref","unstructured":"Stypu\u0142kowski, M., Vougioukas, K., He, S., Zi\u0119ba, M., Petridis, S., Pantic, M.: Diffused heads: diffusion models beat gans on talking-face generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5091\u20135100 (2024)","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"4195_CR10","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":"4195_CR11","doi-asserted-by":"crossref","unstructured":"Huang, R., Lai, P., Qin, Y., Li, G.: Parametric implicit face representation for audio-driven facial reenactment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12759\u201312768 (2023)","DOI":"10.1109\/CVPR52729.2023.01227"},{"key":"4195_CR12","doi-asserted-by":"crossref","unstructured":"Thies, J., Elgharib, M., Tewari, A., Theobalt, C., Nie\u00dfner, M.: Neural voice puppetry: audio-driven facial reenactment. In: European Conference on Computer Vision, pp. 716\u2013731. Springer (2020)","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"4195_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhao, Y., Huang, Y., Zeng, M., Ni, S., : Facial: synthesizing dynamic talking face with implicit attribute learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3867\u20133876 (2021)","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"4195_CR14","doi-asserted-by":"crossref","unstructured":"Ye, Z., Xia, M., Yi, R., Zhang, J., Lai, Y.-K., et al.: Audio-driven talking face video generation with dynamic convolution kernels. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3142387"},{"issue":"6","key":"4195_CR15","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)"},{"issue":"6","key":"4195_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480484","volume":"40","author":"Y Lu","year":"2021","unstructured":"Lu, Y., Chai, J., Cao, X.: Live speech portraits: real-time photorealistic talking-head animation. ACM Trans. Graph. (TOG) 40(6), 1\u201317 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4195_CR17","doi-asserted-by":"crossref","unstructured":"Liang, B., Pan, Y., Guo, Z., Zhou, H., Hong, Z., : Expressive talking head generation with granular audio-visual control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3387\u20133396 (2022)","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"4195_CR18","doi-asserted-by":"crossref","unstructured":"Zhong, W., Fang, C., Cai, Y., Wei, P., Zhao, G., Lin, L., Li, G.: Identity-preserving talking face generation with landmark and appearance priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9729\u20139738 (2023)","DOI":"10.1109\/CVPR52729.2023.00938"},{"issue":"9","key":"4195_CR19","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1109\/TPAMI.2003.1227983","volume":"25","author":"V Blanz","year":"2003","unstructured":"Blanz, V., Vetter, T.: Face recognition based on fitting a 3D morphable model. IEEE Trans. Pattern Anal. Mach. Intell. 25(9), 1063\u20131074 (2003)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4195_CR20","doi-asserted-by":"crossref","unstructured":"Dong, B., Zhang, L.: Enhanced temporal representation and spatial alignment for high-fidelity talking video generation. Vis. Comput. pp. 1\u201312 (2025)","DOI":"10.1007\/s00371-025-03999-2"},{"key":"4195_CR21","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":"4195_CR22","doi-asserted-by":"crossref","unstructured":"Cui, J., Li, H., Zhan, Y., Shang, H., Cheng, K., Ma, Y., Mu, S., Zhou, H., Wang, J., Zhu, S.: Hallo3: highly dynamic and realistic portrait image animation with video diffusion transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21086\u201321095 (2025)","DOI":"10.1109\/CVPR52734.2025.01964"},{"issue":"1","key":"4195_CR23","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.vrih.2023.08.006","volume":"6","author":"L Niu","year":"2024","unstructured":"Niu, L., Xie, W., Wang, D., Cao, Z., Liu, X.: Audio2ab: audio-driven collaborative generation of virtual character animation. Virtual Real. Intell. Hardw. 6(1), 56\u201370 (2024)","journal-title":"Virtual Real. Intell. Hardw."},{"key":"4195_CR24","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020)"},{"key":"4195_CR25","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W-N Hsu","year":"2021","unstructured":"Hsu, W.-N., Bolte, B., Tsai, Y.-H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Proces. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Proces."},{"issue":"2","key":"4195_CR26","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1109\/TVCG.2021.3117484","volume":"29","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Ni, S., Fan, Z., Li, H., Zeng, M., Budagavi, M., Guo, X.: 3D talking face with personalized pose dynamics. IEEE Trans. Visual Comput. Graph. 29(2), 1438\u20131449 (2021)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"4195_CR27","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: Faceformer: speech-driven 3d facial animation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18770\u201318780 (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"4195_CR28","doi-asserted-by":"crossref","unstructured":"Chae-Yeon, L., Hyun-Bin, O., EunGi, H., Sung-Bin, K., Nam, S., Oh, T.-H.: Perceptually accurate 3d talking head generation: new definitions, speech-mesh representation, and evaluation metrics. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21065\u201321074 (2025)","DOI":"10.1109\/CVPR52734.2025.01962"},{"key":"4195_CR29","doi-asserted-by":"crossref","unstructured":"Xing, J., Xia, M., Zhang, Y., Cun, X., Wang, J., Wong, T.-T.: Codetalker: speech-driven 3d facial animation with discrete motion prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12780\u201312790 (2023)","DOI":"10.1109\/CVPR52729.2023.01229"},{"issue":"6","key":"4195_CR30","first-page":"1","volume":"36","author":"T Li","year":"2017","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. 36(6), 1\u201317 (2017)","journal-title":"ACM Trans. Graph."},{"key":"4195_CR31","doi-asserted-by":"crossref","unstructured":"Tan, S., Ji, B., Bi, M., Pan, Y.: Edtalk: efficient disentanglement for emotional talking head synthesis. In: European Conference on Computer Vision, pp. 398\u2013416. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_23"},{"issue":"1","key":"4195_CR32","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":"4195_CR33","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, K., Liang, S., Liu, Y.-J., Bao, H., Zhang, J.: Ad-nerf: audio driven neural radiance fields for talking head synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5784\u20135794 (2021)","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"4195_CR34","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":"4195_CR35","doi-asserted-by":"crossref","unstructured":"Tang, J., Wang, K., Zhou, H., Chen, X., He, D., Hu, T., Liu, J., Liu, Z., Zeng, G., Wang, J.: Real-time neural radiance talking portrait synthesis via audio-spatial decomposition. Int. J. Comput. Vision, pp. 1\u201312 (2025)","DOI":"10.1007\/s11263-025-02481-9"},{"key":"4195_CR36","doi-asserted-by":"crossref","unstructured":"Aneja, S., Thies, J., Dai, A., Nie\u00dfner, M.: Facetalk: audio-driven motion diffusion for neural parametric head models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21263\u201321273 (2024)","DOI":"10.1109\/CVPR52733.2024.02009"},{"key":"4195_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Q., Weng, D., Liu, Y.: Utilizing periodic feature-enhanced neural-field modeling for the photorealistic representation of human head avatars. Vis. Comput. pp. 1\u201312 (2024)","DOI":"10.1007\/s00371-024-03299-1"},{"key":"4195_CR38","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Lin, C.Z., Chan, M.A., Nagano, K., Pan, B., De\u00a0Mello, S., : 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"},{"issue":"4","key":"4195_CR39","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139 (2023)","journal-title":"ACM Trans. Graph."},{"key":"4195_CR40","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, X., Zhou, W., Jiao, S., Zhang, Y., Jin, X.: Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20331\u201320341 (2024)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"4195_CR41","doi-asserted-by":"crossref","unstructured":"Cho, K., Lee, J., Yoon, H., Hong, Y., Ko, J., Ahn, S., Kim, S.: Gaussiantalker: real-time talking head synthesis with 3d gaussian splatting. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 10985\u201310994 (2024)","DOI":"10.1145\/3664647.3681627"},{"key":"4195_CR42","unstructured":"Razavi, A., Oord, A., Vinyals, O.: Generating diverse high-fidelity images with vq-vae-2. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"4195_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y., Fan, C.: Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3661\u20133670 (2021)","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"4195_CR44","doi-asserted-by":"crossref","unstructured":"Liu, X., Xu, Y., Wu, Q., Zhou, H., Wu, W., Zhou, B.: Semantic-aware implicit neural audio-driven video portrait generation. In: European Conference on Computer Vision, pp. 106\u2013125, Springer (2022)","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"4195_CR45","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"},{"key":"4195_CR46","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":"4","key":"4195_CR47","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":"4195_CR48","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Asian Conference on Computer Vision, pp. 251\u2013263. Springer (2016)","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"4195_CR49","unstructured":"Paszke, A.: Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)"},{"key":"4195_CR50","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04195-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04195-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04195-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:16:43Z","timestamp":1763644603000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04195-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":50,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4195"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04195-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,7]]},"assertion":[{"value":"30 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}