{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T12:31:42Z","timestamp":1769517102812,"version":"3.49.0"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730207","type":"print"},{"value":"9783031730214","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73021-4_11","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:17:38Z","timestamp":1732094258000},"page":"177-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Instant 3D Human Avatar Generation Using Image Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4885-4876","authenticated-orcid":false,"given":"Nikos","family":"Kolotouros","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9107-4173","authenticated-orcid":false,"given":"Thiemo","family":"Alldieck","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-1868","authenticated-orcid":false,"given":"Enric","family":"Corona","sequence":"additional","affiliation":[]},{"given":"Eduard Gabriel","family":"Bazavan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5256-886X","authenticated-orcid":false,"given":"Cristian","family":"Sminchisescu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"11_CR1","unstructured":"https:\/\/renderpeople.com\/"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Abdal, R., et al.: Gaussian shell maps for efficient 3d human generation. arXiv preprint arXiv:2311.17857 (2023)","DOI":"10.1109\/CVPR52733.2024.00902"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"AlBahar, B., Saito, S., Tseng, H.Y., Kim, C., Kopf, J., Huang, J.B.: Single-image 3D human digitization with shape-guided diffusion. In: SIGGRAPH Asia (2023)","DOI":"10.1145\/3610548.3618153"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Bhatnagar, B.L., Theobalt, C., Pons-Moll, G.: Learning to reconstruct people in clothing from a single RGB camera. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00127"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Xu, W., Theobalt, C., Pons-Moll, G.: Detailed human avatars from monocular video. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00022"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Xu, W., Theobalt, C., Pons-Moll, G.: Video based reconstruction of 3D people models. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00875"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Pons-Moll, G., Theobalt, C., Magnor, M.: Tex2shape: detailed full human body geometry from a single image. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00238"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Zanfir, M., Sminchisescu, C.: Photorealistic monocular 3D reconstruction of humans wearing clothing. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"11_CR9","unstructured":"Bar-Tal, O., et\u00a0al.: Lumiere: a space-time diffusion model for video generation. arXiv preprint arXiv:2401.12945 (2024)"},{"key":"11_CR10","unstructured":"Bazavan, E.G., Zanfir, A., Zanfir, M., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Hspace: synthetic parametric humans animated in complex environments. arXiv (2021)"},{"key":"11_CR11","unstructured":"Blender Online Community: Blender - a 3D modelling and rendering package. Blender Foundation, Blender Institute, Amsterdam (2020). http:\/\/www.blender.org"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Chen, X., et al.: Pali: a jointly-scaled multilingual language-image model (2022). https:\/\/doi.org\/10.48550\/ARXIV.2209.06794, https:\/\/arxiv.org\/abs\/2209.06794","DOI":"10.48550\/ARXIV.2209.06794"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Corona, E., Zanfir, M., Alldieck, T., Bazavan, E.G., Zanfir, A., Sminchisescu, C.: Structured 3D features for reconstructing relightable and animatable avatars. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01626"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"11_CR15","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advance in Neural Information Processing System, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Dong, Z., Xu\u00a0Chen, J.Y., J.Black, M., Hilliges, O., Geiger, A.: AG3D: learning to generate 3D avatars from 2D image collections. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01370"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Franco, J.S., Martin, X., Schmid, C., Rogez, G.: Moulding humans: non-parametric 3D human shape estimation from single images. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00232"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Gong, C., et al.: Text2avatar: text to 3D human avatar generation with codebook-driven body controllable attribute. arXiv preprint arXiv:2401.00711 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446237"},{"key":"11_CR19","unstructured":"Han, X., et al.: Headsculpt: crafting 3D head avatars with text. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S.: Viton: an image-based virtual try-on network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7543\u20137552 (2018)","DOI":"10.1109\/CVPR.2018.00787"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"He, T., Xu, Y., Saito, S., Soatto, S., Tung, T.: Arch++: animation-ready clothed human reconstruction revisited. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.01086"},{"key":"11_CR22","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"11_CR23","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"11_CR24","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. arXiv preprint arxiv:2006.11239 (2020)"},{"key":"11_CR25","unstructured":"Hong, F., Chen, Z., Lan, Y., Pan, L., Liu, Z.: EVA3d: compositional 3D human generation from 2D image collections. In: International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=g7U9jD_2CUr"},{"issue":"4","key":"11_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530094","volume":"41","author":"F Hong","year":"2022","unstructured":"Hong, F., Zhang, M., Pan, L., Cai, Z., Yang, L., Liu, Z.: AvatarCLIP: zero-shot text-driven generation and animation of 3D avatars. ACM Trans. Graph. (TOG) 41(4), 1\u201319 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: TeCH: text-guided reconstruction of lifelike clothed humans. In: International Conference on 3D Vision (3DV) (2024)","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Huang, Z., Xu, Y., Lassner, C., Li, H., Tung, T.: Arch: animatable reconstruction of clothed humans. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"11_CR29","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":"11_CR30","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) (2023)","DOI":"10.1145\/3592433"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Kim, B., et al.: Chupa: carving 3D clothed humans from skinned shape priors using 2D diffusion probabilistic models. arXiv preprint arXiv:2305.11870 (2023)","DOI":"10.1109\/ICCV51070.2023.01463"},{"key":"11_CR32","unstructured":"Kolotouros, N., Alldieck, T., Zanfir, A., Bazavan, E., Fieraru, M., Sminchisescu, C.: Dreamhuman: animatable 3D avatars from text. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"11_CR34","unstructured":"Kondratyuk, D., et\u00a0al.: Videopoet: a large language model for zero-shot video generation. arXiv preprint arXiv:2312.14125 (2023)"},{"key":"11_CR35","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/978-3-031-19790-1_13","volume-title":"ECCV 2022","author":"S Lee","year":"2022","unstructured":"Lee, S., Gu, G., Park, S., Choi, S., Choo, J.: High-resolution virtual try-on with misalignment and occlusion-handled conditions. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 204\u2013219. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_13"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Lei, B., Yu, K., Feng, M., Cui, M., Xie, X.: Diffusiongan3d: boosting text-guided 3D generation and domain adaption by combining 3D GANs and diffusion priors. arXiv preprint arXiv:2312.16837 (2023)","DOI":"10.1109\/CVPR52733.2024.00998"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Liao, T., et al.: Tada! text to animatable digital avatars. In: 3DV (2023)","DOI":"10.1109\/3DV62453.2024.00150"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3D content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"11_CR39","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":"11_CR40","unstructured":"Liu, M., et al.: One-2-3-45: any single image to 3D mesh in 45 seconds without per-shape optimization. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3d object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"11_CR42","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":"11_CR43","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ToG (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. In: SIGGRAPH (1987)","DOI":"10.1145\/37401.37422"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Lorraine, J., et al.: Att3d: amortized text-to-3d object synthesis. arXiv preprint arXiv:2306.07349 (2023)","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"11_CR47","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: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Onizuka, H., Hayirci, Z., Thomas, D., Sugimoto, A., Uchiyama, H., Taniguchi, R.I.: TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shell. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00605"},{"key":"11_CR49","unstructured":"Oord, A.V.D., et al.: Wavenet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"11_CR51","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. In: International Conference on Learning Representation (2022)"},{"key":"11_CR52","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Raj, A., et al.: Dreambooth3d: subject-driven text-to-3d generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"11_CR54","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"11_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: IEEE Conference on Computer Vision Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR56","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR57","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS, vol.\u00a035, pp. 36479\u201336494 (2022)"},{"key":"11_CR58","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advance in Neural Information Processing System, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"11_CR59","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":"11_CR60","doi-asserted-by":"crossref","unstructured":"Saito, S., Simon, T., Saragih, J., Joo, H.: PIFuHD: multi-level pixel-aligned implicit function for high-resolution 3D human digitization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"11_CR61","doi-asserted-by":"crossref","unstructured":"Sengupta, A., Alldieck, T., Kolotouros, N., Corona, E., Zanfir, A., Sminchisescu, C.: Diffhuman: probabilistic photorealistic 3D reconstruction of humans. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00143"},{"key":"11_CR62","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":"11_CR63","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representation (2020)"},{"key":"11_CR64","unstructured":"Sun, J., et al.: Dreamcraft3d: hierarchical 3D generation with bootstrapped diffusion prior. arXiv preprint arXiv:2310.16818 (2023)"},{"key":"11_CR65","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3D content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"11_CR66","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: Bodynet: volumetric inference of 3D human body shapes. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_2"},{"key":"11_CR67","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual description. arXiv preprint arXiv:2210.02399 (2022)"},{"key":"11_CR68","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Disentangled clothed avatar generation from text descriptions. arXiv preprint arXiv:2312.05295 (2023)","DOI":"10.1007\/978-3-031-72943-0_22"},{"key":"11_CR69","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Yang, J., Cao, X., Tzionas, D., Black, M.J.: ECON: explicit clothed humans optimized via normal integration. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"11_CR70","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Yang, J., Tzionas, D., Black, M.J.: Icon: implicit clothed humans obtained from normals. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"11_CR71","doi-asserted-by":"crossref","unstructured":"Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Ghum & ghuml: generative 3D human shape and articulated pose models. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"11_CR72","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":"11_CR73","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: S3: neural shape, skeleton, and skinning fields for 3D human modeling. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01308"},{"key":"11_CR74","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/978-3-031-20086-1_19","volume-title":"ECCV 2022","author":"K Yanting Chan","year":"2022","unstructured":"Yanting Chan, K., Lin, G., Zhao, H., Lin, W.: IntegratedPIFu: integrated pixel aligned implicit function for single-view human reconstruction. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 328\u2013344. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_19"},{"key":"11_CR75","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: Make pixels dance: high-dynamic video generation. arXiv preprint arXiv:2311.10982 (2023)","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"11_CR76","unstructured":"Zhang, C., et al.: Audio diffusion model for speech synthesis: a survey on text to speech and speech enhancement in generative AI. arXiv preprint arXiv:2303.13336 (2023)"},{"key":"11_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, H., Feng, Y., Kulits, P., Wen, Y., Thies, J., Black, M.J.: Text-guided generation and editing of compositional 3D avatars. arXiv preprint arXiv:2309.07125 (2023)","DOI":"10.1109\/3DV62453.2024.00151"},{"key":"11_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Avatarverse: high-quality & stable 3D avatar creation from text and pose. arXiv preprint arXiv:2308.03610 (2023)","DOI":"10.1609\/aaai.v38i7.28540"},{"key":"11_CR79","unstructured":"Zhang, J., et al.: Avatarstudio: high-fidelity and animatable 3d avatar creation from text. arXiv preprint arXiv:2311.17917 (2023)"},{"key":"11_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. IEEE International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"11_CR81","unstructured":"Zhao, Z., Bao, Z., Li, Q., Qiu, G., Liu, K.: Psavatar: a point-based morphable shape model for real-time head avatar creation with 3D gaussian splatting. arXiv preprint arXiv:2401.12900 (2024)"},{"key":"11_CR82","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yu, T., Liu, Y., Dai, Q.: Pamir: parametric model-conditioned implicit representation for image-based human reconstruction. PAMI (2021)","DOI":"10.1109\/TPAMI.2021.3050505"},{"key":"11_CR83","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y.: Deephuman: 3D human reconstruction from a single image. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00783"},{"key":"11_CR84","doi-asserted-by":"crossref","unstructured":"Zhu, H., Zuo, X., Wang, S., Cao, X., Yang, R.: Detailed human shape estimation from a single image by hierarchical mesh deformation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00462"},{"key":"11_CR85","doi-asserted-by":"crossref","unstructured":"Zhu, L., et al.: Tryondiffusion: a tale of two unets. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4606\u20134615 (2023)","DOI":"10.1109\/CVPR52729.2023.00447"}],"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\/978-3-031-73021-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T16:21:26Z","timestamp":1733070086000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73021-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730207","9783031730214"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73021-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 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"}}]}}