{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T04:06:46Z","timestamp":1751947606765,"version":"3.41.2"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T00:00:00Z","timestamp":1748044800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T00:00:00Z","timestamp":1748044800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Scientific Research Start-up Fund of Jimei University","award":["ZQ2021002","ZQ2021002","ZQ2021002"],"award-info":[{"award-number":["ZQ2021002","ZQ2021002","ZQ2021002"]}]},{"name":"Fujian Provincial Natural Science Foundation General Fund","award":["2024J01118","2024J01118","2024J01118"],"award-info":[{"award-number":["2024J01118","2024J01118","2024J01118"]}]},{"name":"the Guangdong Provincial Key Laboratory of IRADS","award":["2022B1212010006","2022B1212010006","2022B1212010006"],"award-info":[{"award-number":["2022B1212010006","2022B1212010006","2022B1212010006"]}]},{"name":"Guangdong Higher Education Upgrading Plan","award":["2023KQNCX091","2023KQNCX091","2023KQNCX091"],"award-info":[{"award-number":["2023KQNCX091","2023KQNCX091","2023KQNCX091"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00371-025-03966-x","type":"journal-article","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:48:44Z","timestamp":1748090924000},"page":"6657-6670","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GenericAvatar: generic human modeling from monocular video based on mesh-guided Gaussians"],"prefix":"10.1007","volume":"41","author":[{"given":"Sen","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihang","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runjie","family":"Miu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baorong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,24]]},"reference":[{"key":"3966_CR1","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Xu, W., Theobalt, C., Pons-Moll, G.: Video based reconstruction of 3d people models. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8387\u20138397 (2018)","DOI":"10.1109\/CVPR.2018.00875"},{"key":"3966_CR2","first-page":"19900","volume":"35","author":"A Bergman","year":"2022","unstructured":"Bergman, A., Kellnhofer, P., Yifan, W., Chan, E., Lindell, D., Wetzstein, G.: Generative neural articulated radiance fields. Adv. Neural Inf. Process. Syst. 35, 19900\u201319916 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"3966_CR3","doi-asserted-by":"publisher","first-page":"204:1","DOI":"10.1145\/3618401","volume":"42","author":"S Bharadwaj","year":"2023","unstructured":"Bharadwaj, S., Zheng, Y., Hilliges, O., Black, M.J., Fernandez-Abrevaya, V.: Flare: fast learning of animatable and relightable mesh avatars. ACM Trans. Graph. 42(6), 204:1-204:15 (2023)","journal-title":"ACM Trans. Graph."},{"key":"3966_CR4","unstructured":"Chen, J., Zhang, Y., Kang, D., Zhe, X., Bao, L., Jia, X., Lu, H.: Animatable neural radiance fields from monocular rgb videos. arXiv preprint arXiv:2106.13629 (2021)"},{"issue":"10","key":"3966_CR5","doi-asserted-by":"publisher","first-page":"11796","DOI":"10.1109\/TPAMI.2023.3271569","volume":"45","author":"X Chen","year":"2023","unstructured":"Chen, X., Jiang, T., Song, J., Rietmann, M., Geiger, A., Black, M.J., Hilliges, O.: Fast-snarf: a fast deformer for articulated neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 11796\u201311809 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3966_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, L., Li, Q., Xiao, H., Zhang, S., Yao, H., Liu, Y.: Monogaussianavatar: monocular Gaussian point-based head avatar. In: Proc. of Siggraph 2024, pp. 58:1\u201358:9 (2024)","DOI":"10.1145\/3641519.3657499"},{"issue":"8","key":"3966_CR7","first-page":"88:1","volume":"40","author":"Y Feng","year":"2021","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), 88:1-88:13 (2021)","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH)"},{"key":"3966_CR8","unstructured":"Feng, Y., Liu, W., Bolkart, T., Yang, J., Pollefeys, M., Black, M.J.: Learning disentangled avatars with hybrid 3d representations. arXiv preprint arXiv:2309.06441 (2023)"},{"key":"3966_CR9","doi-asserted-by":"crossref","unstructured":"Feng, Y., Yang, J., Pollefeys, M., Black, M.J., Bolkart, T.: Capturing and animation of body and clothing from monocular video. In: Proc. of ACM Siggraph Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, pp. 45:1\u201345:9 (2022)","DOI":"10.1145\/3550469.3555423"},{"key":"3966_CR10","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: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8649\u20138658 (2021)","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"3966_CR11","doi-asserted-by":"publisher","first-page":"5719","DOI":"10.1109\/TVCG.2023.3305433","volume":"30","author":"Q Gao","year":"2023","unstructured":"Gao, Q., Wang, Y., Liu, L., Liu, L., Theobalt, C., Chen, B.: Neural novel actor: learning a generalized animatable neural representation for human actors. IEEE Trans. Vis. Comput. Graph. 30, 5719\u20135732 (2023)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"3966_CR12","doi-asserted-by":"crossref","unstructured":"Grassal, P.W., Prinzler, M., Leistner, T., Rother, C., NieSSner, M., Thies, J.: Neural head avatars from monocular rgb videos. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 18,653\u201318,664 (2022)","DOI":"10.1109\/CVPR52688.2022.01810"},{"key":"3966_CR13","unstructured":"Ho, H.I., Xue, L., Song, J., Hilliges, O.: Learning locally editable virtual humans. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21,024\u201321,035 (2023)"},{"key":"3966_CR14","unstructured":"Hong, Y., Peng, B., Xiao, H., Liu, L., Zhang, J.: Headnerf: A real-time nerf-based parametric head model. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 20,374\u201320,384 (2022)"},{"key":"3966_CR15","doi-asserted-by":"crossref","unstructured":"Hu, L., Zhang, H., Zhang, Y., Zhou, B., Liu, B., Zhang, S., Nie, L.: Gaussianavatar: Towards realistic human avatar modeling from a single video via animatable 3d gaussians. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 634\u2013644 (2024)","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"3966_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, T., Chen, X., Song, J., Hilliges, O.: Instantavatar: learning avatars from monocular video in 60 seconds. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16,922\u201316,932 (2023)","DOI":"10.1109\/CVPR52729.2023.01623"},{"issue":"4","key":"3966_CR17","doi-asserted-by":"publisher","first-page":"139:1","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), 139:1-139:14 (2023)","journal-title":"ACM Trans. Graph."},{"key":"3966_CR18","doi-asserted-by":"crossref","unstructured":"Lei, J., Wang, Y., Pavlakos, G., Liu, L., Daniilidis, K.: Gart: Gaussian articulated template models. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 19,876\u201319,887 (2024)","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"3966_CR19","doi-asserted-by":"crossref","unstructured":"Li, R., Tanke, J., Vo, M., Zollh\u00f6fer, M., Gall, J., Kanazawa, A., Lassner, C.: Tava: Template-free animatable volumetric actors. In: Proc. of the European Conference on Computer Vision, pp. 419\u2013436 (2022)","DOI":"10.1007\/978-3-031-19824-3_25"},{"issue":"6","key":"3966_CR20","doi-asserted-by":"publisher","first-page":"194:1","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. (Proc. SIGGRAPH Asia) 36(6), 194:1-194:17 (2017). https:\/\/doi.org\/10.1145\/3130800.3130813","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH Asia)"},{"key":"3966_CR21","doi-asserted-by":"crossref","unstructured":"Lin, S., Yang, L., Saleemi, I., Sengupta, S.: Robust high-resolution video matting with temporal guidance. In: Proc. of the 2022 IEEE Winter Conference on Applications of Computer Vision, pp. 3132\u20133141 (2021)","DOI":"10.1109\/WACV51458.2022.00319"},{"issue":"6","key":"3966_CR22","first-page":"248:1","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (Proc. Siggraph Asia) 34(6), 248:1-248:16 (2015)","journal-title":"ACM Trans. Graph. (Proc. Siggraph Asia)"},{"key":"3966_CR23","doi-asserted-by":"crossref","unstructured":"Ma, S., Simon, T., Saragih, J., Wang, D., Li, Y., De\u00a0La\u00a0Torre, F., Sheikh, Y.: Pixel codec avatars. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 64\u201373 (2021)","DOI":"10.1109\/CVPR46437.2021.00013"},{"issue":"1","key":"3966_CR24","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":"3966_CR25","doi-asserted-by":"crossref","unstructured":"Moreau, A., Song, J., Dhamo, H., Shaw, R., Zhou, Y., P\u00e9rez-Pellitero, E.: Human gaussian splatting: real-time rendering of animatable avatars. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 788\u2013798 (2024)","DOI":"10.1109\/CVPR52733.2024.00081"},{"issue":"8","key":"3966_CR26","doi-asserted-by":"publisher","first-page":"9895","DOI":"10.1109\/TPAMI.2023.3245815","volume":"45","author":"S Peng","year":"2023","unstructured":"Peng, S., Geng, C., Zhang, Y., Xu, Y., Wang, Q., Shuai, Q., Zhou, X., Bao, H.: Implicit neural representations with structured latent codes for human body modeling. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9895\u20139907 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3966_CR27","doi-asserted-by":"crossref","unstructured":"Peng, S., Zhang, Y., Xu, Y., Wang, Q., Shuai, Q., Bao, H., Zhou, X.: Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9054\u20139063 (2021)","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"3966_CR28","doi-asserted-by":"crossref","unstructured":"Prokudin, S., Black, M.J., Romero, J.: Smplpix: Neural avatars from 3d human models. In: Proc. of the IEEE Winter Conference on Applications of Computer Vision, pp. 1810\u20131819 (2021)","DOI":"10.1109\/WACV48630.2021.00185"},{"key":"3966_CR29","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. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 20,299\u201320,309 (2024)","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"3966_CR30","doi-asserted-by":"crossref","unstructured":"Qian, Z., Wang, S., Mihajlovic, M., Geiger, A., Tang, S.: 3dgs-avatar: animatable avatars via deformable 3d gaussian splatting. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5020\u20135030 (2024)","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"3966_CR31","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: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 84\u201393 (2020)","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"3966_CR32","doi-asserted-by":"crossref","unstructured":"Shao, Z., Wang, Z., Li, Z., Wang, D., Lin, X., Zhang, Y., Fan, M., Wang, Z.: Splattingavatar: Realistic real-time human avatars with mesh-embedded gaussian splatting. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1606\u20131616 (2024)","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"3966_CR33","unstructured":"Shen, K., Guo, C., Kaufmann, M., Zarate, J.J., Valentin, J., Song, J., Hilliges, O.: X-avatar: expressive human avatars. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16,911\u201316,921 (2023)"},{"key":"3966_CR34","doi-asserted-by":"crossref","unstructured":"Wang, S., Schwarz, K., Geiger, A., Tang, S.: Arah: Animatable volume rendering of articulated human sdfs. In: Proc. of the European Conference on Computer Vision, pp. 1\u201319 (2022)","DOI":"10.1007\/978-3-031-19824-3_1"},{"key":"3966_CR35","doi-asserted-by":"crossref","unstructured":"Wen, J., Zhao, X., Ren, Z., Schwing, A.G., Wang, S.: Gomaavatar: efficient animatable human modeling from monocular video using gaussians-on-mesh. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2059\u20132069 (2024)","DOI":"10.1109\/CVPR52733.2024.00201"},{"key":"3966_CR36","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: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16,210\u201316,220 (2022)","DOI":"10.1109\/CVPR52688.2022.01573"},{"issue":"6","key":"3966_CR37","doi-asserted-by":"publisher","first-page":"199:1","DOI":"10.1145\/3478513.3480545","volume":"40","author":"D Xiang","year":"2021","unstructured":"Xiang, D., Prada, F., Bagautdinov, T., Xu, W., Dong, Y., Wen, H., Hodgins, J., Wu, C.: Modeling clothing as a separate layer for an animatable human avatar. ACM Trans. Graph. 40(6), 199:1-199:15 (2021)","journal-title":"ACM Trans. Graph."},{"key":"3966_CR38","doi-asserted-by":"crossref","unstructured":"Xu, Y., Chen, B., Li, Z., Zhang, H., Wang, L., Zheng, Z., Liu, Y.: Gaussian head avatar: ultra high-fidelity head avatar via dynamic gaussians. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1931\u20131941 (2024)","DOI":"10.1109\/CVPR52733.2024.00189"},{"key":"3966_CR39","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2020","unstructured":"Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vis. 129, 3051\u20133068 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"3966_CR40","unstructured":"Yu, Z., Cheng, W., Liu, X., Wu, W., Lin, K.Y.: Monohuman: animatable human neural field from monocular video. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16,943\u201316,953 (2023)"},{"issue":"4","key":"3966_CR41","doi-asserted-by":"publisher","first-page":"149:1","DOI":"10.1145\/3450626.3459756","volume":"40","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Liu, X., Ye, X., Zhao, F., Zhang, Y., Wu, M., Zhang, Y., Xu, L., Yu, J.: Editable free-viewpoint video using a layered neural representation. ACM Trans. Graph. 40(4), 149:1-149:18 (2021)","journal-title":"ACM Trans. Graph."},{"key":"3966_CR42","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: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 13,545\u201313,555 (2022)"},{"key":"3966_CR43","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: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21,057\u201321,067 (2023)","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"3966_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhao, Q., Yang, G., Yifan, W., Xiang, D., Dubost, F., Lagun, D., Beeler, T., Tombari, F., Guibas, L., et\u00a0al.: Physavatar: learning the physics of dressed 3d avatars from visual observations. In: Proc. of the European Conference on Computer Vision, pp. 262\u2013284 (2024)","DOI":"10.1007\/978-3-031-72913-3_15"},{"key":"3966_CR45","doi-asserted-by":"crossref","unstructured":"Zielonka, W., Bolkart, T., Thies, J.: Instant volumetric head avatars. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4574\u20134584 (2023)","DOI":"10.1109\/CVPR52729.2023.00444"},{"key":"3966_CR46","doi-asserted-by":"crossref","unstructured":"Zwicker, M., Pfister, H., Van\u00a0Baar, J., Gross, M.: Ewa volume splatting. In: Proc. of the IEEE Conference on Visualization, pp. 29\u2013538 (2001)","DOI":"10.1145\/383259.383300"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03966-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03966-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03966-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T11:04:59Z","timestamp":1751886299000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03966-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,24]]},"references-count":46,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["3966"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03966-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,5,24]]},"assertion":[{"value":"24 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2025","order":2,"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"}}]}}