{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:02:01Z","timestamp":1789718521848,"version":"4.0.1"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37174-4_15","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:05:44Z","timestamp":1789715144000},"page":"251-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PHOSA: Photorealistic 3D Sign Avatar Modeling and\u00a0Benchmark"],"prefix":"10.1007","author":[{"given":"Haodong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hezhen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"15_CR1","unstructured":"Easymocap - make human motion capture easier (2021). https:\/\/github.com\/zju3dv\/EasyMocap"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Baltatzis, V., et al.: Neural sign actors: a diffusion model for 3D sign language production from text. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00194"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., et al.: SMPLer-X: scaling up expressive human pose and shape estimation. In: Proceedings of the NeurIPS (2023)","DOI":"10.52202\/075280-0506"},{"key":"15_CR4","unstructured":"Camg\u00f6z, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Rwth-phoenix-weather 2014 t: Parallel corpus of sign language video, gloss and translation. In: Proceedings of the CVPR (2018)"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, W., et\u00a0al.: DNA-rendering: a diverse neural actor repository for high-fidelity human-centric rendering. In: Proceedings of the ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01829"},{"key":"15_CR7","unstructured":"Contributors, M.: Openmmlab pose estimation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmpose"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Danecek, R., Black, M.J., Bolkart, T.: EMOCA: emotion driven monocular face capture and animation. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Duarte, A., et al.: How2Sign: a Large-scale Multimodal Dataset for Continuous American Sign Language. In: Proceedings of the CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Ebling, S., et al.: Smile swiss german sign language dataset. In: Proceedings of the LREC (2018)","DOI":"10.63317\/3ygyk796mmfb"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Fang, S., et al.: Signdiff: diffusion model for American sign language production. In: Proceedings of the 2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG), pp. 1\u201311. IEEE (2025)","DOI":"10.1109\/FG61629.2025.11099440"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Feng, Y., Choutas, V., Bolkart, T., Tzionas, D., Black, M.J.: Collaborative regression of expressive bodies using moderation. In: Proceedings of the 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3D face model from in-the-wild images. ACM TOG (2021)","DOI":"10.1145\/3450626.3459936"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Filntisis, P.P., et al.: Visual speech-aware perceptual 3D facial expression reconstruction from videos. arXiv preprint arXiv:2207.11094 (2022)","DOI":"10.1109\/CVPRW59228.2023.00609"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Forte, M.P., et al.: Reconstructing signing avatars from video using linguistic priors. In: Proceedings of the CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01230"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Guo, Z., Zhou, W., Wang, M., Li, L., Li, H.: Handnerf: neural radiance fields for animatable interacting hands. In: Proceedings of the CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02019"},{"key":"15_CR17","unstructured":"Hanke, T.: Hamnosys-representing sign language data in language resources and language processing contexts. In: Proceedings of the sign-lang@ LREC 2004 (2004)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Hong, Y., Peng, B., Xiao, H., Liu, L., Zhang, J.: Headnerf: a real-time nerf-based parametric head model. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01973"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Hu, H., et al.: Expressive gaussian human avatars from monocular RGB video. In: Proceedings of the NeurIPS (2024)","DOI":"10.52202\/079017-0183"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Hu, L., et al.: Gaussianavatar: towards realistic human avatar modeling from a single video via animatable 3D gaussians. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE TPAMI (2014)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"I\u015f\u0131k, M., R\u00fcnz, M., Georgopoulos, M., Khakhulin, T., Starck, J., Agapito, L., Nie\u00dfner, M.: Humanrf: High-fidelity neural radiance fields for humans in motion. ACM TOG (2023)","DOI":"10.1145\/3592415"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, T., Chen, X., Song, J., Hilliges, O.: Instantavatar: learning avatars from monocular video in 60 seconds. In: Proceedings of the CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, W., Yi, K.M., Samei, G., Tuzel, O., Ranjan, A.: Neuman: neural human radiance field from a single video. In: Proceedings of the ECCV (2022)","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. SIGGRAPH (2023)","DOI":"10.1145\/3592433"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., et al.: Sapiens: foundation for human vision models. In: Proceedings of the ECCV (2024)","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Lei, J., Wang, Y., Pavlakos, G., Liu, L., Daniilidis, K.: Gart: gaussian articulated template models. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Li, Z., Zheng, Z., Wang, L., Liu, Y.: Animatable gaussians: learning pose-dependent gaussian maps for high-fidelity human avatar modeling. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Lin, J., Zeng, A., Wang, H., Zhang, L., Li, Y.: One-stage 3D whole-body mesh recovery with component aware transformer. In: Proceedings of the CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"15_CR32","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. ACM TOG (2021)","DOI":"10.1145\/3478513.3480528"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. SIGGRAPH Asia (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"15_CR34","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. Commun. ACM (2021)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Moon, G., Choi, H., Lee, K.M.: Accurate 3D hand pose estimation for whole-body 3D human mesh estimation. In: Proceedings of the CVPRW (2022)","DOI":"10.1109\/CVPRW56347.2022.00257"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Moon, G., Shiratori, T., Saito, S.: Expressive whole-body 3D gaussian avatar. In: Proceedings of the ECCV (2024)","DOI":"10.1007\/978-3-031-72940-9_2"},{"key":"15_CR37","unstructured":"Ni, L.: Chinese Sign Language Tutorial. Fudan University Press (2020)"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Pang, H., Zhu, H., Kortylewski, A., Theobalt, C., Habermann, M.: Ash: animatable gaussian splats for efficient and photoreal human rendering. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00117"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Reconstructing hands in 3D with transformers. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"15_CR41","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 CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"15_CR42","unstructured":"Peter, E., Hilsmann, A.: Visual sign language dataset (2022). https:\/\/cvg.hhi.fraunhofer.de\/VisualSignLanguageData.htm"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Qi, F., Duan, Y., Zhang, H., Xu, C.: Signgen: end-to-end sign language video generation with latent diffusion. In: Proceedings of the European Conference on Computer Vision, pp. 252\u2013270. Springer (2024)","DOI":"10.1007\/978-3-031-73668-1_15"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Quandt, L.C., Willis, A., Schwenk, M., Weeks, K., Ferster, R.: Attitudes toward signing avatars vary depending on hearing status, age of signed language acquisition, and avatar type. Front. Psychol. (2022)","DOI":"10.31234\/osf.io\/g2wuc"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. SIGGRAPH Asia (2017)","DOI":"10.1145\/3130800.3130883"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Rong, Y., Shiratori, T., Joo, H.: Frankmocap: a monocular 3D whole-body pose estimation system via regression and integration. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Shao, Z., et al.: Splattingavatar: realistic real-time human avatars with mesh-embedded gaussian splatting. In: Proceedings of the CVPR, pp. 1606\u20131616 (2024)","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Wang, J., Karaev, N., Rupprecht, C., Novotny, D.: Vggsfm: visual geometry grounded deep structure from motion. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Styleavatar: real-time photo-realistic portrait avatar from a single video. In: Proceedings of the SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591517"},{"key":"15_CR50","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP (2004)"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Curless, B., Srinivasan, P.P., Barron, J.T., Kemelmacher-Shlizerman, I.: HumanNeRF: free-viewpoint rendering of moving people from monocular video. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Wu, M., Wang, Y., Hu, Q., Yu, J.: Multi-view neural human rendering. In: Proceedings of the CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00175"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Xiong, Z., et\u00a0al.: Mvhumannet: a large-scale dataset of multi-view daily dressing human captures. In: Proceedings of the CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01872"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zeng, A., Yuan, C., Li, Y.: Effective whole-body pose estimation with two-stages distillation. In: Proceedings of the ICCV (2023)","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Yu, Z., Huang, S., Cheng, Y., Birdal, T.: Signavatars: a large-scale 3D sign language holistic motion dataset and benchmark. In: Proceedings of the ECCV (2024)","DOI":"10.1007\/978-3-031-72652-1_1"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Zeng, A., Yang, L., Ju, X., Li, J., Wang, J., Xu, Q.: Smoothnet: a plug-and-play network for refining human poses in videos. In: Proceedings of the ECCV (2022)","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Shao, T., Yang, Y., Zhou, K.: Real-time high-fidelity gaussian human avatars with position-based interpolation of spatially distributed MLPS. In: Proceedings of the CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02449"},{"key":"15_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Pymaf-x: towards well-aligned full-body model regression from monocular images. PAMI (2023)","DOI":"10.1109\/TPAMI.2023.3271691"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. IN: Proceedings of the CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Zhao, F., et al.: Humannerf: efficiently generated human radiance field from sparse inputs. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00759"},{"key":"15_CR61","doi-asserted-by":"crossref","unstructured":"Zheng, Z., et al.: Structured local radiance fields for human avatar modeling. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01543"},{"key":"15_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Qi, W., Pu, J., Li, H.: Improving sign language translation with monolingual data by sign back-translation. In: Proceedings of the CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"15_CR63","doi-asserted-by":"crossref","unstructured":"Zielonka, W., Bagautdinov, T., Saito, S., Zollh\u00f6fer, M., Thies, J., Romero, J.: Drivable 3D gaussian avatars. In: Proceedings of the 3DV (2025)","DOI":"10.1109\/3DV66043.2025.00095"},{"key":"15_CR64","doi-asserted-by":"crossref","unstructured":"Zielonka, W., Bolkart, T., Thies, J.: Towards metrical reconstruction of human faces. In: Proceedings of the ECCV (2022)","DOI":"10.1007\/978-3-031-19778-9_15"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Zuo, R., Wei, F., Chen, Z., Mak, B., Yang, J., Tong, X.: A simple baseline for spoken language to sign language translation with 3D avatars. In: Proceedings of the ECCV (2024)","DOI":"10.1007\/978-3-031-72967-6_3"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37174-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:06:14Z","timestamp":1789715174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"19 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}