{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T15:56:15Z","timestamp":1775577375160,"version":"3.50.1"},"publisher-location":"Cham","reference-count":81,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734106","type":"print"},{"value":"9783031734113","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-73411-3_9","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T20:07:28Z","timestamp":1732306048000},"page":"145-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["HeadStudio: Text to\u00a0Animatable Head Avatars with\u00a03D Gaussian Splatting"],"prefix":"10.1007","author":[{"given":"Zhenglin","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Fan","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"9_CR1","unstructured":"Controlnetmediapipeface. https:\/\/huggingface.co\/CrucibleAI\/ControlNetMediaPipeFace"},{"key":"9_CR2","unstructured":"Playht. https:\/\/play.ht\/"},{"key":"9_CR3","unstructured":"Realistic vision 5.1. https:\/\/huggingface.co\/stablediffusionapi\/realistic-vision-51"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"An, S., Xu, H., Shi, Y., Song, G., Ogras, U.Y., Luo, L.: Panohead: geometry-aware 3d full-head synthesis in 360$$^{\\circ } $$. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20950\u201320959 (June 2023)","DOI":"10.1109\/CVPR52729.2023.02007"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"9_CR6","unstructured":"Bergman, A.W., Yifan, W., Wetzstein, G.: Articulated 3d head avatar generation using text-to-image diffusion models. arXiv preprint arXiv:2307.04859 (2023)"},{"key":"9_CR7","doi-asserted-by":"publisher","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: SIGGRAPH (1999). https:\/\/doi.org\/10.1145\/311535.311556","DOI":"10.1145\/311535.311556"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Cao, A., Johnson, J.: Hexplane: a fast representation for dynamic scenes. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Cao, Y., Cao, Y.P., Han, K., Shan, Y., Wong, K.Y.K.: Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models. arXiv preprint arXiv:2304.00916 (2023)","DOI":"10.1109\/CVPR52733.2024.00097"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-gan: periodic implicit generative adversarial networks for 3d-aware image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5799\u20135809 (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"9_CR13","unstructured":"Chen, G., Wang, W.: A survey on 3D Gaussian splatting. arXiv preprint arXiv:2401.03890 (2024)"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3d: disentangling geometry and appearance for high-quality text-to-3d content creation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (October 2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Cohen-Bar, D., Richardson, E., Metzer, G., Giryes, R., Cohen-Or, D.: Set-the-scene: Global-local training for generating controllable nerf scenes. arXiv preprint arXiv:2303.13450 (2023)","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"9_CR16","doi-asserted-by":"publisher","unstructured":"Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3D face model from in-the-wild images. ACM Trans. Graph. (Proc. SIGGRAPH) 40(8) (2021). https:\/\/doi.org\/10.1145\/3450626.3459936","DOI":"10.1145\/3450626.3459936"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Meanti, G., Warburg, F.R., Recht, B., Kanazawa, A.: K-planes: Explicit radiance fields in space, time, and appearance. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"9_CR18","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Gao, C., Saraf, A., Kopf, J., Huang, J.B.: Dynamic view synthesis from dynamic monocular video. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"9_CR20","unstructured":"Guo, Y.C., et al.: threestudio: A unified framework for 3d content generation. https:\/\/github.com\/threestudio-project\/threestudio (2023)"},{"key":"9_CR21","unstructured":"Han, X., et al.: Headsculpt: Crafting 3d head avatars with text. arXiv preprint arXiv:2306.03038 (2023)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A., Holynski, A., Kanazawa, A.: Instruct-nerf2nerf: Editing 3d scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"He, S., et al.: Speech4mesh: Speech-assisted monocular 3d facial reconstruction for speech-driven 3d facial animation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14192\u201314202 (2023)","DOI":"10.1109\/ICCV51070.2023.01305"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Hertz, A., Aberman, K., Cohen-Or, D.: Delta denoising score. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2328\u20132337 (2023)","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"9_CR26","unstructured":"Ho, J., et\u00a0al.: Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"9_CR27","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inform. Process. Syst. (NeurIPS) 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)"},{"key":"9_CR28","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J., Nie\u00dfner, M.: Text2room: Extracting textured 3d meshes from 2d text-to-image models. arXiv preprint arXiv:2303.11989 (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"9_CR30","unstructured":"Hong, S., Ahn, D., Kim, S.: Debiasing scores and prompts of 2d diffusion for robust text-to-3d generation. arXiv preprint arXiv:2303.15413 (2023)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, R., et al.: Avatarcraft: Transforming text into neural human avatars with parameterized shape and pose control. arXiv preprint arXiv:2303.17606 (2023)","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"9_CR33","unstructured":"Kamata, H., Sakuma, Y., Hayakawa, A., Ishii, M., Narihira, T.: Instruct 3d-to-3d: Text instruction guided 3d-to-3d conversion. arXiv preprint arXiv:2303.15780 (2023)"},{"key":"9_CR34","unstructured":"Katzir, O., Patashnik, O., Cohen-Or, D., Lischinski, D.: Noise-free score distillation. arXiv preprint arXiv:2310.17590 (2023)"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (July 2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"9_CR36","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Kirschstein, T., Giebenhain, S., Nie\u00dfner, M.: Diffusionavatars: Deferred diffusion for high-fidelity 3d head avatars. arXiv preprint arXiv:2311.18635 (2023)","DOI":"10.1109\/CVPR52733.2024.00524"},{"key":"9_CR38","unstructured":"Li, C., et al.: Generative ai meets 3d: A survey on text-to-3d in aigc era. arXiv preprint arXiv:2305.06131 (2023)"},{"issue":"6","key":"9_CR39","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1145\/3130800.3130813","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), 194\u20131 (2017)","journal-title":"ACM Trans. Graph."},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Liang, C., Ma, F., Zhu, L., Deng, Y., Yang, Y.: Caphuman: capture your moments in parallel universes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6400\u20136409 (2024)","DOI":"10.1109\/CVPR52733.2024.00612"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Liao, T., Yi, H., Xiu, Y., Tang, J., Huang, Y., Thies, J., Black, M.J.: Tada! text to animatable digital avatars. arXiv preprint arXiv:2308.10899 (2023)","DOI":"10.1109\/3DV62453.2024.00150"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Headartist: Text-conditioned 3d head generation with self score distillation. arXiv preprint arXiv:2312.07539 (2023)","DOI":"10.1145\/3641519.3657512"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Humangaussian: Text-driven 3d human generation with gaussian splatting. arXiv preprint arXiv:2311.17061 (2023)","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: A skinned multi-person linear model. ACM Trans. Graph. 34(6), 248:1\u2013248:16 (Oct 2015)","DOI":"10.1145\/2816795.2818013"},{"key":"9_CR45","unstructured":"Lugaresi, C., et\u00a0al.: Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)"},{"key":"9_CR46","unstructured":"Ma, F., Jin, X., Wang, H., Xian, Y., Feng, J., Yang, Y.: Vista-llama: reliable video narrator via equal distance to visual tokens (2023)"},{"key":"9_CR47","unstructured":"Ma, Y., Lin, Z., Ji, J., Fan, Y., Sun, X., Ji, R.: X-oscar: A progressive framework for high-quality text-guided 3d animatable avatar generation. arXiv preprint arXiv:2405.00954 (2024)"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-nerf for shape-guided generation of 3d shapes and textures. arXiv preprint arXiv:2211.07600 (2022)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"9_CR49","doi-asserted-by":"crossref","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: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"9_CR50","unstructured":"Nichol, A., et al: Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"9_CR51","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10975\u201310985 (Jun 2019). http:\/\/smpl-x.is.tue.mpg.de","DOI":"10.1109\/CVPR.2019.01123"},{"key":"9_CR52","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"9_CR53","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":"9_CR54","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 8748\u20138763 (2021)"},{"key":"9_CR55","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. arXiv preprint arxiv:2208.12242 (2022)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"9_CR57","first-page":"20154","volume":"33","author":"K Schwarz","year":"2020","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: Graf: generative radiance fields for 3D-aware image synthesis. Adv. Neural. Inf. Process. Syst. 33, 20154\u201320166 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR58","first-page":"6087","volume":"34","author":"T Shen","year":"2021","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. Adv. Neural. Inf. Process. Syst. 34, 6087\u20136101 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR59","doi-asserted-by":"crossref","unstructured":"Shen, X., Ma, J., Zhou, C., Yang, Z.: Controllable 3d face generation with conditional style code diffusion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4811\u20134819 (2024)","DOI":"10.1609\/aaai.v38i5.28283"},{"key":"9_CR60","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"9_CR61","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591560"},{"key":"9_CR62","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score jacobian chaining: lifting pretrained 2d diffusion models for 3d generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"9_CR63","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: Rodin: A generative model for sculpting 3d digital avatars using diffusion. arXiv preprint arXiv:2212.06135 (2022)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"9_CR64","unstructured":"Wang, Z., et al.: Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. arXiv preprint arXiv:2305.16213 (2023)"},{"key":"9_CR65","doi-asserted-by":"publisher","unstructured":"Wu, Y., et al.: Portrait3d: text-guided high-quality 3d portrait generation using pyramid representation and gans prior. ACM Trans. Graph. 43(4) (Jul 2024). https:\/\/doi.org\/10.1145\/3658162","DOI":"10.1145\/3658162"},{"key":"9_CR66","unstructured":"Xu, Y., Yang, Z., Yang, Y.: Seeavatar: Photorealistic text-to-3d avatar generation with constrained geometry and appearance. arXiv preprint arXiv:2312.08889 (2023)"},{"key":"9_CR67","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, L., Zhao, X., Zhang, H., Liu, Y.: Avatarmav: Fast 3d head avatar reconstruction using motion-aware neural voxels. In: ACM SIGGRAPH 2023 Conference Proceedings (2023)","DOI":"10.1145\/3588432.3591567"},{"key":"9_CR68","unstructured":"Yang, Z., Chen, G., Li, X., Wang, W., Yang, Y.: Doraemongpt: toward understanding dynamic scenes with large language models (exemplified as a video agent). In: ICML (2024)"},{"key":"9_CR69","doi-asserted-by":"crossref","unstructured":"Yi, H., et al.: Generating holistic 3d human motion from speech. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"9_CR70","unstructured":"Zhang, C., Zhang, C., Zhang, M., Kweon, I.S.: Text-to-image diffusion model in generative AI: a survey. arXiv preprint arXiv:2303.07909 (2023)"},{"key":"9_CR71","unstructured":"Zhang, J., et al.: Avatarstudio: High-fidelity and animatable 3d avatar creation from text. arXiv preprint arXiv:2311.17917 (2023)"},{"key":"9_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: Dreamface: Progressive generation of animatable 3d faces under text guidance. arXiv preprint arXiv:2304.03117 (2023)","DOI":"10.1145\/3592094"},{"key":"9_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"issue":"8","key":"9_CR74","doi-asserted-by":"publisher","first-page":"2219","DOI":"10.1007\/s11263-023-01805-x","volume":"131","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Zheng, Z., Gao, D., Zhang, B., Yang, Y., Chua, T.S.: Multi-view consistent generative adversarial networks for compositional 3d-aware image synthesis. Int. J. Comput. Vision 131(8), 2219\u20132242 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR75","unstructured":"Zhang, Y., Fan, H., Yang, Y.: Prompt-aware adapter: Towards learning adaptive visual tokens for multimodal large language models. arXiv preprint arXiv:2405.15684 (2024)"},{"key":"9_CR76","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Abrevaya, V.F., B\u00fchler, M.C., Chen, X., Black, M.J., Hilliges, O.: I M Avatar: implicit morphable head avatars from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"9_CR77","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) (2023)","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"9_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, D., Li, Y., Ma, F., Zhang, X., Yang, Y.: Migc: multi-instance generation controller for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6818\u20136828 (2024)","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"9_CR79","doi-asserted-by":"crossref","unstructured":"Zhuo, W., Ma, F., Fan, H., Yang, Y.: Vividdreamer: invariant score distillation for hyper-realistic text-to-3d generation. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73223-2_8"},{"key":"9_CR80","doi-asserted-by":"crossref","unstructured":"Zielonka, W., Bolkart, T., Thies, J.: Towards metrical reconstruction of human faces. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19778-9_15"},{"key":"9_CR81","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 (CVPR) (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\/978-3-031-73411-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T21:24:22Z","timestamp":1732310662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73411-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031734106","9783031734113"],"references-count":81,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73411-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 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"}}]}}