{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:06:14Z","timestamp":1774915574354,"version":"3.50.1"},"reference-count":217,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"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":[[2025,4]]},"DOI":"10.1007\/s00371-024-03641-7","type":"journal-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T20:23:50Z","timestamp":1727382230000},"page":"3973-4000","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Innovative AI techniques for photorealistic 3D clothed human reconstruction from monocular images or videos: a survey"],"prefix":"10.1007","volume":"41","author":[{"given":"Shuo","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoling","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenzhong","family":"Kuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feiwei","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizhao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"key":"3641_CR1","doi-asserted-by":"publisher","unstructured":"Salagean, A., Crellin, E., Parsons, M., Cosker, D., Fraser, D.S.: Meeting your virtual twin: effects of photorealism and personalization on embodiment, self-identification and perception of self-avatars in virtual reality. In: CHI, pp. 499\u2013149916 (2023). https:\/\/doi.org\/10.1145\/3544548.3581182","DOI":"10.1145\/3544548.3581182"},{"key":"3641_CR2","doi-asserted-by":"publisher","unstructured":"Panda, P., Nicholas, M.J., Gonz\u00e1lez-Franco, M., Inkpen, K., Ofek, E., Cutler, R., Hinckley, K., Lanier, J.: AllTogether: effect of avatars in mixed-modality conferencing environments. In: CHIWORK, pp. 8\u20131810 (2022). https:\/\/doi.org\/10.1145\/3533406.3539658","DOI":"10.1145\/3533406.3539658"},{"issue":"4","key":"3641_CR3","doi-asserted-by":"publisher","first-page":"76","DOI":"10.3390\/JIMAGING9040076","volume":"9","author":"G Manfredi","year":"2023","unstructured":"Manfredi, G., Gilio, G., Baldi, V., Youssef, H., Erra, U.: VICO-DR: a collaborative virtual dressing room for image consulting. J. Imaging 9(4), 76 (2023). https:\/\/doi.org\/10.3390\/JIMAGING9040076","journal-title":"J. Imaging"},{"issue":"5\u20136","key":"3641_CR4","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1080\/07370024.2022.2103419","volume":"38","author":"K Szolin","year":"2023","unstructured":"Szolin, K., Kuss, D.J., Nuyens, F.M., Griffiths, M.D.: Exploring the user-avatar relationship in videogames: a systematic review of the Proteus effect. Hum. Comput. Interact. 38(5\u20136), 374\u2013399 (2023). https:\/\/doi.org\/10.1080\/07370024.2022.2103419","journal-title":"Hum. Comput. Interact."},{"issue":"6","key":"3641_CR5","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1145\/3355089.3356571","volume":"38","author":"K Guo","year":"2019","unstructured":"Guo, K., Lincoln, P., Davidson, P.L., Busch, J., Yu, X., Whalen, M., Harvey, G., Orts-Escolano, S., Pandey, R., Dourgarian, J., Tang, D., Tkach, A., Kowdle, A., Cooper, E., Dou, M., Fanello, S.R., Fyffe, G., Rhemann, C., Taylor, J., Debevec, P.E., Izadi, S.: The relightables: volumetric performance capture of humans with realistic relighting. ACM Trans. Graph. 38(6), 217\u2013121719 (2019). https:\/\/doi.org\/10.1145\/3355089.3356571","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"3641_CR6","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1145\/2766945","volume":"34","author":"A Collet","year":"2015","unstructured":"Collet, A., Chuang, M., Sweeney, P., Gillett, D., Evseev, D., Calabrese, D., Hoppe, H., Kirk, A.G., Sullivan, S.: High-quality streamable free-viewpoint video. ACM Trans. Graph. 34(4), 69\u201316913 (2015). https:\/\/doi.org\/10.1145\/2766945","journal-title":"ACM Trans. Graph."},{"key":"3641_CR7","doi-asserted-by":"publisher","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Li, H., Kanazawa, A.: PIFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: ICCV, pp. 2304\u20132314 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00239","DOI":"10.1109\/ICCV.2019.00239"},{"key":"3641_CR8","doi-asserted-by":"publisher","unstructured":"Saito, S., Simon, T., Saragih, J.M., Joo, H.: PIFuHD: multi-level pixel-aligned implicit function for high-resolution 3D human digitization. In: CVPR, pp. 81\u201390 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00016","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"3641_CR9","doi-asserted-by":"publisher","unstructured":"Xiu, Y., Yang, J., Tzionas, D., Black, M.J.: ICON: implicit clothed humans obtained from normals. In: CVPR, pp. 13286\u201313296 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01294","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"3641_CR10","doi-asserted-by":"publisher","unstructured":"Weng, C., Curless, B., Srinivasan, P.P., Barron, J.T., Kemelmacher-Shlizerman, I.: HumanNeRF: free-viewpoint rendering of moving people from monocular video. In: CVPR, pp. 16189\u201316199 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01573","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"3641_CR11","doi-asserted-by":"crossref","unstructured":"Hu, S., Liu, Z.: GauHuman: articulated Gaussian splatting from monocular human videos. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01930"},{"issue":"6","key":"3641_CR12","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1145\/2816795.2818013","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. 34(6), 248\u2013124816 (2015). https:\/\/doi.org\/10.1145\/2816795.2818013","journal-title":"ACM Trans. Graph."},{"key":"3641_CR13","doi-asserted-by":"publisher","unstructured":"Feng, Y., Choutas, V., Bolkart, T., Tzionas, D., Black, M.J.: Collaborative regression of expressive bodies using moderation. In: 3DV, pp. 792\u2013804 (2021). https:\/\/doi.org\/10.1109\/3DV53792.2021.00088","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"3641_CR14","doi-asserted-by":"publisher","unstructured":"Alldieck, T., Magnor, M.A., Bhatnagar, B.L., Theobalt, C., Pons-Moll, G.: Learning to reconstruct people in clothing from a single RGB camera. In: CVPR, pp. 1175\u20131186 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00127","DOI":"10.1109\/CVPR.2019.00127"},{"key":"3641_CR15","doi-asserted-by":"publisher","unstructured":"Alldieck, T., Pons-Moll, G., Theobalt, C., Magnor, M.A.: Tex2Shape: detailed full human body geometry from a single image. In: ICCV, pp. 2293\u20132303 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00238","DOI":"10.1109\/ICCV.2019.00238"},{"key":"3641_CR16","doi-asserted-by":"publisher","unstructured":"Xiu, Y., Yang, J., Cao, X., Tzionas, D., Black, M.J.: ECON: explicit clothed humans optimized via normal integration. In: CVPR, pp. 512\u2013523 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00057","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"3641_CR17","doi-asserted-by":"publisher","unstructured":"Corona, E., Hodan, T., Vo, M., Moreno-Noguer, F., Sweeney, C., Newcombe, R.A., Ma, L.: LISA: learning implicit shape and appearance of hands. In: CVPR, pp. 20501\u201320511 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01988","DOI":"10.1109\/CVPR52688.2022.01988"},{"key":"3641_CR18","doi-asserted-by":"publisher","unstructured":"Chen, X., Wang, B., Shum, H.: Hand Avatar: free-pose hand animation and rendering from monocular video. In: CVPR, pp. 8683\u20138693 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00839","DOI":"10.1109\/CVPR52729.2023.00839"},{"key":"3641_CR19","doi-asserted-by":"crossref","unstructured":"Chen, Z., Moon, G., Guo, K., Cao, C., Pidhorskyi, S., Simon, T., Joshi, R., Dong, Y., Xu, Y., Pires, B., Wen, H., Evans, L., Peng, B., Buffalini, J., Trimble, A., McPhail, K., Schoeller, M., Yu, S.-I., Romero, J., Zollh\u00f6fer, M., Sheikh, Y., Liu, Z., Saito, S.: URHand: universal relightable hands. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00020"},{"key":"3641_CR20","doi-asserted-by":"crossref","unstructured":"Saito, S., Schwartz, G., Simon, T., Li, J., Nam, G.: Relightable Gaussian codec avatars. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00021"},{"issue":"4","key":"3641_CR21","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1145\/3450626.3459829","volume":"40","author":"S Bi","year":"2021","unstructured":"Bi, S., Lombardi, S., Saito, S., Simon, T., Wei, S., McPhail, K., Ramamoorthi, R., Sheikh, Y., Saragih, J.M.: Deep relightable appearance models for animatable faces. ACM Trans. Graph. 40(4), 89\u201318915 (2021). https:\/\/doi.org\/10.1145\/3450626.3459829","journal-title":"ACM Trans. Graph."},{"key":"3641_CR22","doi-asserted-by":"publisher","unstructured":"Li, X., Sheng, B., Li, P., Kim, J., Feng, D.D.: Voxelized facial reconstruction using deep neural network. In: CGI, pp. 1\u20134 (2018). https:\/\/doi.org\/10.1145\/3208159.3208170","DOI":"10.1145\/3208159.3208170"},{"key":"3641_CR23","doi-asserted-by":"publisher","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P.V., Romero, J., Black, M.J.: Keep It SMPL: automatic estimation of 3D human pose and shape from a single image. In: ECCV, pp. 561\u2013578 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"3641_CR24","doi-asserted-by":"publisher","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: CVPR, pp. 7122\u20137131 (2018).https:\/\/doi.org\/10.1109\/CVPR.2018.00744","DOI":"10.1109\/CVPR.2018.00744"},{"key":"3641_CR25","doi-asserted-by":"publisher","unstructured":"Yu, T., Zheng, Z., Guo, K., Liu, P., Dai, Q., Liu, Y.: Function4D: real-time human volumetric capture from very sparse consumer RGBD sensors. In: CVPR, pp. 5746\u20135756 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00569","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"3641_CR26","doi-asserted-by":"publisher","unstructured":"Wang, L., Zhao, X., Yu, T., Wang, S., Liu, Y.: NormalGAN: learning detailed 3D human from a single RGB-D image. In: ECCV, vol. 12365, pp. 430\u2013446 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_26","DOI":"10.1007\/978-3-030-58565-5_26"},{"issue":"12","key":"3641_CR27","doi-asserted-by":"publisher","first-page":"15406","DOI":"10.1109\/TPAMI.2023.3298850","volume":"45","author":"Y Tian","year":"2023","unstructured":"Tian, Y., Zhang, H., Liu, Y., Wang, L.: Recovering 3D human mesh from monocular images: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15406\u201315425 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3298850","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3641_CR28","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/J.VISINF.2021.10.003","volume":"5","author":"L Chen","year":"2021","unstructured":"Chen, L., Peng, S., Zhou, X.: Towards efficient and photorealistic 3D human reconstruction: a brief survey. Vis. Inform. 5(4), 11\u201319 (2021). https:\/\/doi.org\/10.1016\/J.VISINF.2021.10.003","journal-title":"Vis. Inform."},{"key":"3641_CR29","doi-asserted-by":"crossref","unstructured":"Sun, M., Yang, D., Kou, D., Jiang, Y., Shan, W., Yan, Z., Zhang, L.: Human 3D avatar modeling with implicit neural representation: a brief survey. In: 2022 14th International Conference on Signal Processing Systems (ICSPS), pp. 818\u2013827. IEEE (2022)","DOI":"10.1109\/ICSPS58776.2022.00148"},{"key":"3641_CR30","doi-asserted-by":"publisher","unstructured":"Ma, Q., Saito, S., Yang, J., Tang, S., Black, M.J.: SCALE: modeling clothed humans with a surface codec of articulated local elements. In: CVPR, pp. 16082\u201316093 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01582","DOI":"10.1109\/CVPR46437.2021.01582"},{"key":"3641_CR31","doi-asserted-by":"publisher","unstructured":"Ma, Q., Yang, J., Tang, S., Black, M.J.: The power of points for modeling humans in clothing. In: ICCV, pp. 10954\u201310964 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01079","DOI":"10.1109\/ICCV48922.2021.01079"},{"key":"3641_CR32","doi-asserted-by":"publisher","unstructured":"Manfredi, G., Capece, N., Erra, U., Gilio, G., Baldi, V., Domenico, S.G.D.: TryItOn: a virtual dressing room with motion tracking and physically based garment simulation. In: XR, vol. 13445, pp. 63\u201376 (2022). https:\/\/doi.org\/10.1007\/978-3-031-15546-8_5","DOI":"10.1007\/978-3-031-15546-8_5"},{"key":"3641_CR33","doi-asserted-by":"publisher","unstructured":"Fan, T., Yang, B., Bao, C., Wang, L., Zhang, G., Cui, Z.: HybridAvatar: efficient mesh-based human avatar generation from few-shot monocular images with implicit mesh displacement. In: IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR 2023, Sydney, Australia, October 16\u201320, 2023, pp. 371\u2013376 (2023).https:\/\/doi.org\/10.1109\/ISMAR-ADJUNCT60411.2023.00080","DOI":"10.1109\/ISMAR-ADJUNCT60411.2023.00080"},{"key":"3641_CR34","doi-asserted-by":"publisher","unstructured":"Varol, G., Ceylan, D., Russell, B.C., Yang, J., Yumer, E., Laptev, I., Schmid, C.: BodyNet: volumetric inference of 3D human body shapes. In: ECCV, pp. 20\u201338 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_2","DOI":"10.1007\/978-3-030-01234-2_2"},{"key":"3641_CR35","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y.: DeepHuman: 3D human reconstruction from a single image. In: ICCV, pp. 7738\u20137748 (2019).https:\/\/doi.org\/10.1109\/ICCV.2019.00783","DOI":"10.1109\/ICCV.2019.00783"},{"key":"3641_CR36","doi-asserted-by":"publisher","unstructured":"Tang, S., Tan, F., Cheng, K., Li, Z., Zhu, S., Tan, P.: A neural network for detailed human depth estimation from a single image. In: ICCV, pp. 7749\u20137758 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00784","DOI":"10.1109\/ICCV.2019.00784"},{"key":"3641_CR37","doi-asserted-by":"publisher","unstructured":"Smith, D., Loper, M., Hu, X., Mavroidis, P., Romero, J.: FACSIMILE: fast and accurate scans from an image in less than a second. In: ICCV, pp. 5329\u20135338 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00543","DOI":"10.1109\/ICCV.2019.00543"},{"issue":"4","key":"3641_CR38","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\u2013113914 (2023). https:\/\/doi.org\/10.1145\/3592433","journal-title":"ACM Trans. Graph."},{"key":"3641_CR39","doi-asserted-by":"publisher","unstructured":"Park, J.J., Florence, P.R., Straub, J., Newcombe, R.A., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: CVPR, pp. 165\u2013174 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00025","DOI":"10.1109\/CVPR.2019.00025"},{"key":"3641_CR40","doi-asserted-by":"publisher","unstructured":"Mescheder, L.M., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: CVPR, pp. 4460\u20134470 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00459","DOI":"10.1109\/CVPR.2019.00459"},{"key":"3641_CR41","doi-asserted-by":"publisher","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, pp. 405\u2013421 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24","DOI":"10.1007\/978-3-030-58452-8_24"},{"issue":"2","key":"3641_CR42","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1111\/CGF.14507","volume":"41","author":"A Tewari","year":"2022","unstructured":"Tewari, A., Thies, J., Mildenhall, B., Srinivasan, P.P., Tretschk, E., Wang, Y., Lassner, C., Sitzmann, V., Martin-Brualla, R., Lombardi, S., Simon, T., Theobalt, C., Nie\u00dfner, M., Barron, J.T., Wetzstein, G., Zollh\u00f6fer, M., Golyanik, V.: Advances in neural rendering. Comput. Graph. Forum 41(2), 703\u2013735 (2022). https:\/\/doi.org\/10.1111\/CGF.14507","journal-title":"Comput. Graph. Forum"},{"key":"3641_CR43","doi-asserted-by":"publisher","unstructured":"Pfister, H., Zwicker, M., Baar, J., Gross, M.H.: Surfels: surface elements as rendering primitives. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH, pp. 335\u2013342 (2000). https:\/\/doi.org\/10.1145\/344779.344936","DOI":"10.1145\/344779.344936"},{"issue":"3","key":"3641_CR44","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1145\/1073204.1073207","volume":"24","author":"D Anguelov","year":"2005","unstructured":"Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: SCAPE: shape completion and animation of people. ACM Trans. Graph. 24(3), 408\u2013416 (2005). https:\/\/doi.org\/10.1145\/1073204.1073207","journal-title":"ACM Trans. Graph."},{"key":"3641_CR45","doi-asserted-by":"publisher","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, pp. 6183\u20136192 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00622","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"3641_CR46","doi-asserted-by":"publisher","unstructured":"Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: sparse trained articulated human body regressor. In: ECCV, vol. 12351, pp. 598\u2013613 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_36","DOI":"10.1007\/978-3-030-58539-6_36"},{"issue":"6","key":"3641_CR47","doi-asserted-by":"publisher","first-page":"3170","DOI":"10.1109\/TPAMI.2021.3050505","volume":"44","author":"Z Zheng","year":"2022","unstructured":"Zheng, Z., Yu, T., Liu, Y., Dai, Q.: PaMIR: parametric model-conditioned implicit representation for image-based human reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3170\u20133184 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3050505","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3641_CR48","unstructured":"Hong, F., Chen, Z., Lan, Y., Pan, L., Liu, Z.: EVA3D: compositional 3D human generation from 2D image collections. In: ICLR (2023)"},{"key":"3641_CR49","doi-asserted-by":"publisher","unstructured":"Dong, Z., Chen, X., Yang, J., Black, M.J., Hilliges, O., Geiger, A.: AG3D: learning to generate 3D avatars from 2D image collections. In: ICCV, pp. 14870\u201314881 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01370","DOI":"10.1109\/ICCV51070.2023.01370"},{"key":"3641_CR50","doi-asserted-by":"crossref","unstructured":"Huang, Y., Yi, H., Xiu, Y., Liao, T., Tang, J., Cai, D., Thies, J.: TeCH: text-guided reconstruction of lifelike clothed humans. In: 3DV (2024)","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"3641_CR51","doi-asserted-by":"publisher","unstructured":"Albahar, B., Saito, S., Tseng, H., Kim, C., Kopf, J., Huang, J.: Single-image 3D human digitization with shape-guided diffusion. In: SIGGRAPH Asia 2023 Conference Papers, pp. 62\u201316211 (2023). https:\/\/doi.org\/10.1145\/3610548.3618153","DOI":"10.1145\/3610548.3618153"},{"key":"3641_CR52","doi-asserted-by":"publisher","unstructured":"Yao, J., Chen, J., Niu, L., Sheng, B.: Scene-aware human pose generation using transformer. In: MM, pp. 2847\u20132855 (2023). https:\/\/doi.org\/10.1145\/3581783.3612439","DOI":"10.1145\/3581783.3612439"},{"issue":"4\u20135","key":"3641_CR53","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1080\/10447318.2018.1543081","volume":"35","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Liu, B., Li, P., Sheng, B.: An investigation of 3D human pose estimation for learning Tai Chi: a human factor perspective. Int. J. Hum. Comput. Interact. 35(4\u20135), 427\u2013439 (2019). https:\/\/doi.org\/10.1080\/10447318.2018.1543081","journal-title":"Int. J. Hum. Comput. Interact."},{"issue":"5","key":"3641_CR54","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1109\/TSMC.2019.2916896","volume":"51","author":"A Kamel","year":"2021","unstructured":"Kamel, A., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-D joints skeleton coordinates. IEEE Trans. Syst. Man Cybern. Syst. 51(5), 2774\u20132788 (2021). https:\/\/doi.org\/10.1109\/TSMC.2019.2916896","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"6","key":"3641_CR55","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\u2013119417 (2017). https:\/\/doi.org\/10.1145\/3130800.3130813","journal-title":"ACM Trans. Graph."},{"issue":"6","key":"3641_CR56","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1145\/3130800.3130883","volume":"36","author":"J Romero","year":"2017","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. 36(6), 245\u2013124517 (2017). https:\/\/doi.org\/10.1145\/3130800.3130883","journal-title":"ACM Trans. Graph."},{"key":"3641_CR57","doi-asserted-by":"publisher","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A.A., Tzionas, D., Black, M.J.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR, pp. 10975\u201310985 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01123","DOI":"10.1109\/CVPR.2019.01123"},{"key":"3641_CR58","doi-asserted-by":"publisher","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, pp. 4491\u20134500 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00462","DOI":"10.1109\/CVPR.2019.00462"},{"key":"3641_CR59","doi-asserted-by":"publisher","unstructured":"Lazova, V., Insafutdinov, E., Pons-Moll, G.: 360-Degree textures of people in clothing from a single image. In: 3DV, pp. 643\u2013653 (2019). https:\/\/doi.org\/10.1109\/3DV.2019.00076","DOI":"10.1109\/3DV.2019.00076"},{"key":"3641_CR60","doi-asserted-by":"publisher","unstructured":"Ma, Q., Yang, J., Ranjan, A., Pujades, S., Pons-Moll, G., Tang, S., Black, M.J.: Learning to dress 3D people in generative clothing. In: CVPR, pp. 6468\u20136477 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00650","DOI":"10.1109\/CVPR42600.2020.00650"},{"key":"3641_CR61","doi-asserted-by":"publisher","unstructured":"Bhatnagar, B.L., Tiwari, G., Theobalt, C., Pons-Moll, G.: Multi-Garment Net: learning to dress 3D people from images. In: ICCV, pp. 5419\u20135429 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00552","DOI":"10.1109\/ICCV.2019.00552"},{"key":"3641_CR62","doi-asserted-by":"publisher","unstructured":"Jiang, B., Zhang, J., Hong, Y., Luo, J., Liu, L., Bao, H.: BCNet: learning body and cloth shape from a single image. In: ECCV, vol. 12365, pp. 18\u201335 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_2","DOI":"10.1007\/978-3-030-58565-5_2"},{"key":"3641_CR63","doi-asserted-by":"publisher","unstructured":"Patel, C., Liao, Z., Pons-Moll, G.: TailorNet: predicting clothing in 3D as a function of human pose, shape and garment style. In: CVPR, pp. 7363\u20137373 (2020).https:\/\/doi.org\/10.1109\/CVPR42600.2020.00739","DOI":"10.1109\/CVPR42600.2020.00739"},{"key":"3641_CR64","doi-asserted-by":"publisher","unstructured":"Corona, E., Pumarola, A., Aleny\u00e0, G., Pons-Moll, G., Moreno-Noguer, F.: SMPLicit: topology-aware generative model for clothed people. In: CVPR, pp. 11875\u201311885 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01170","DOI":"10.1109\/CVPR46437.2021.01170"},{"key":"3641_CR65","doi-asserted-by":"publisher","unstructured":"Luigi, L.D., Li, R., Guillard, B., Salzmann, M., Fua, P.: DrapeNet: garment generation and self-supervised draping. In: CVPR, pp. 1451\u20131460 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00146","DOI":"10.1109\/CVPR52729.2023.00146"},{"key":"3641_CR66","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1023\/A:1023012723347","volume":"53","author":"I Miki\u0107","year":"2003","unstructured":"Miki\u0107, I., Trivedi, M., Hunter, E., Cosman, P.: Human body model acquisition and tracking using voxel data. Int. J. Comput. Vis. 53, 199\u2013223 (2003)","journal-title":"Int. J. Comput. Vis."},{"key":"3641_CR67","doi-asserted-by":"publisher","unstructured":"Gilbert, A., Volino, M., Collomosse, J.P., Hilton, A.: Volumetric performance capture from minimal camera viewpoints. In: ECCV, vol. 11215, pp. 591\u2013607 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_35","DOI":"10.1007\/978-3-030-01252-6_35"},{"key":"3641_CR68","doi-asserted-by":"publisher","unstructured":"Stoll, C., Hasler, N., Gall, J., Seidel, H., Theobalt, C.: Fast articulated motion tracking using a sums of Gaussians body model. In: ICCV, pp. 951\u2013958 (2011).https:\/\/doi.org\/10.1109\/ICCV.2011.6126338","DOI":"10.1109\/ICCV.2011.6126338"},{"key":"3641_CR69","doi-asserted-by":"publisher","unstructured":"Robertini, N., Casas, D., Rhodin, H., Seidel, H., Theobalt, C.: Model-based outdoor performance capture. In: 3DV, pp. 166\u2013175 (2016). https:\/\/doi.org\/10.1109\/3DV.2016.25","DOI":"10.1109\/3DV.2016.25"},{"key":"3641_CR70","unstructured":"Chen, G., Wang, W.: A survey on 3D Gaussian splatting (2024). arXiv preprint arXiv:2401.03890"},{"key":"3641_CR71","unstructured":"Bai, S., Li, J.: Progress and prospects in 3D generative AI: a technical overview including 3D human (2024). arXiv preprint arXiv:2401.02620"},{"key":"3641_CR72","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0436-y","author":"T Wu","year":"2024","unstructured":"Wu, T., Yuan, Y.-J., Zhang, L.-X., Yang, J., Cao, Y.-P., Yan, L.-Q., Gao, L.: Recent advances in 3D Gaussian Splatting. Comput. Vis. Media (2024). https:\/\/doi.org\/10.1007\/s41095-024-0436-y","journal-title":"Comput. Vis. Media"},{"key":"3641_CR73","doi-asserted-by":"crossref","unstructured":"Xu, Z., Peng, S., Lin, H., He, G., Sun, J., Shen, Y., Bao, H., Zhou, X.: 4K4D: real-time 4D view synthesis at 4K resolution. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01893"},{"key":"3641_CR74","doi-asserted-by":"crossref","unstructured":"Wu, G., Yi, T., Fang, J., Xie, L., Zhang, X., Wei, W., Liu, W., Tian, Q., Xinggang, W.: 4D Gaussian splatting for real-time dynamic scene rendering. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"3641_CR75","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., Ramanan, D.: Dynamic 3D Gaussians: tracking by persistent dynamic view synthesis. In: 3DV (2024)","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"3641_CR76","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"3641_CR77","doi-asserted-by":"publisher","unstructured":"Huang, B., Yu, Z., Chen, A., Geiger, A., Gao, S.: 2D Gaussian splatting for geometrically accurate radiance fields. In: ACM SIGGRAPH 2024 Conference Papers, SIGGRAPH 2024, Denver, CO, USA, 27 July 2024\u20131 August 2024, pp. 32 (2024). https:\/\/doi.org\/10.1145\/3641519.3657428","DOI":"10.1145\/3641519.3657428"},{"key":"3641_CR78","doi-asserted-by":"crossref","unstructured":"Gu\u00e9don, A., Lepetit, V.: Sugar: Surface-aligned gaussian splatting for efficient 3D mesh reconstruction and high-quality mesh rendering. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"3641_CR79","unstructured":"Chen, H., Li, C., Lee, G.H.: NeuSG: neural implicit surface reconstruction with 3D Gaussian splatting guidance (2023). arXiv preprint arXiv:2312.00846"},{"key":"3641_CR80","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Liu, H.: Text-to-3D using Gaussian splatting (2023). arXiv preprint arXiv:2309.16585","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"3641_CR81","unstructured":"Li, X., Wang, H., Tseng, K.-K.: GaussianDiffusion: 3D Gaussian splatting for denoising diffusion probabilistic models with structured noise (2023). arXiv preprint arXiv:2311.11221"},{"key":"3641_CR82","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative Gaussian splatting for efficient 3D content creation (2023). arXiv preprint arXiv:2309.16653"},{"key":"3641_CR83","unstructured":"Zielonka, W., Bagautdinov, T., Saito, S., Zollh\u00f6fer, M., Thies, J., Romero, J.: Drivable 3D Gaussian avatars (2023). arXiv preprint arXiv:2311.13404"},{"key":"3641_CR84","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"3641_CR85","unstructured":"Liu, X., Wu, C., Liu, J., Liu, X., Zhao, C., Feng, H., Ding, E., Wang, J.: GVA: reconstructing Vivid 3D Gaussian avatars from monocular videos. Arxiv (2024)"},{"key":"3641_CR86","doi-asserted-by":"crossref","unstructured":"Svitov, D., Morerio, P., Agapito, L., Del\u00a0Bue, A.: HAHA: highly articulated Gaussian human avatars with textured mesh prior (2024). arXiv preprint arXiv:2404.01053","DOI":"10.1007\/978-981-96-0969-7_7"},{"key":"3641_CR87","doi-asserted-by":"crossref","unstructured":"Wen, J., Zhao, X., Ren, Z., Schwing, A., Wang, S.: GoMAvatar: efficient animatable human modeling from monocular video using Gaussians-on-mesh. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00201"},{"key":"3641_CR88","unstructured":"Jiang, Y., Liao, Q., Li, X., Ma, L., Zhang, Q., Zhang, C., Lu, Z., Shan, Y.: UV Gaussians: joint learning of mesh deformation and gaussian textures for human avatar modeling (2024). arXiv preprint arXiv:2403.11589"},{"key":"3641_CR89","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhan, X., Tang, J., Shan, Y., Zeng, G., Lin, D., Liu, X., Liu, Z.: HumanGaussian: text-driven 3D human generation with Gaussian splatting. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"3641_CR90","doi-asserted-by":"crossref","unstructured":"Abdal, R., Yifan, W., Shi, Z., Xu, Y., Po, R., Kuang, Z., Chen, Q., Yeung, D.-Y., Wetzstein, G.: Gaussian shell maps for efficient 3D human generation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00902"},{"key":"3641_CR91","doi-asserted-by":"publisher","unstructured":"Cheng, W., Chen, R., Fan, S., Yin, W., Chen, K., Cai, Z., Wang, J., Gao, Y., Yu, Z., Lin, Z., Ren, D., Yang, L., Liu, Z., Loy, C.C., Qian, C., Wu, W., Lin, D., Dai, B., Lin, K.: DNA-rendering: a diverse neural actor repository for high-fidelity human-centric rendering. In: ICCV, pp. 19925\u201319936 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01829","DOI":"10.1109\/ICCV51070.2023.01829"},{"key":"3641_CR92","unstructured":"Bonopera, S., Hedman, P., Esnault, J., Prakash, S., Rodriguez, S., Thonat, T., Benadel, M., Chaurasia, G., Philip, J., Drettakis, G.: SIBR: a system for image based rendering (2020). https:\/\/sibr.gitlabpages.inria.fr\/"},{"key":"3641_CR93","doi-asserted-by":"publisher","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. In: Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1987, pp. 163\u2013169 (1987). https:\/\/doi.org\/10.1145\/37401.37422","DOI":"10.1145\/37401.37422"},{"key":"3641_CR94","doi-asserted-by":"publisher","unstructured":"Alldieck, T., Zanfir, M., Sminchisescu, C.: Photorealistic monocular 3D reconstruction of humans wearing clothing. In: CVPR, pp. 1496\u20131505 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00156","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"3641_CR95","doi-asserted-by":"publisher","unstructured":"Corona, E., Zanfir, M., Alldieck, T., Bazavan, E.G., Zanfir, A., Sminchisescu, C.: Structured 3D features for reconstructing controllable avatars. In: CVPR, pp. 16954\u201316964 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01626","DOI":"10.1109\/CVPR52729.2023.01626"},{"issue":"8","key":"3641_CR96","doi-asserted-by":"publisher","first-page":"3609","DOI":"10.1007\/S00371-023-02957-0","volume":"39","author":"L Lin","year":"2023","unstructured":"Lin, L., Zhu, J.: Topology-preserved human reconstruction with details. Vis. Comput. 39(8), 3609\u20133619 (2023). https:\/\/doi.org\/10.1007\/S00371-023-02957-0","journal-title":"Vis. Comput."},{"key":"3641_CR97","doi-asserted-by":"publisher","unstructured":"Hu, S., Hong, F., Pan, L., Mei, H., Yang, L., Liu, Z.: SHERF: generalizable human nerf from a single image. In: ICCV, pp. 9318\u20139330 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00858","DOI":"10.1109\/ICCV51070.2023.00858"},{"key":"3641_CR98","doi-asserted-by":"publisher","unstructured":"Huang, Y., Yi, H., Liu, W., Wang, H., Wu, B., Wang, W., Lin, B., Zhang, D., Cai, D.: One-shot implicit animatable avatars with model-based priors. In: ICCV, pp. 8940\u20138951 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00824","DOI":"10.1109\/ICCV51070.2023.00824"},{"key":"3641_CR99","doi-asserted-by":"publisher","unstructured":"Alldieck, T., Magnor, M.A., Xu, W., Theobalt, C., Pons-Moll, G.: Video based reconstruction of 3D people models. In: CVPR, pp. 8387\u20138397 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00875","DOI":"10.1109\/CVPR.2018.00875"},{"issue":"11","key":"3641_CR100","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020). https:\/\/doi.org\/10.1145\/3422622","journal-title":"Commun. ACM"},{"key":"3641_CR101","doi-asserted-by":"publisher","unstructured":"Zhu, H., Qiu, L., Qiu, Y., Han, X.: Registering explicit to implicit: towards high-fidelity garment mesh reconstruction from single images. In: CVPR, pp. 3835\u20133844 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00382","DOI":"10.1109\/CVPR52688.2022.00382"},{"key":"3641_CR102","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1007\/978-3-031-19769-7_32","volume":"13661","author":"X Cao","year":"2022","unstructured":"Cao, X., Santo, H., Shi, B., Okura, F., Matsushita, Y.: Bilateral normal integration. In: ECCV 13661, 552\u2013567 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_32","journal-title":"Bilateral normal integration. In: ECCV"},{"key":"3641_CR103","doi-asserted-by":"publisher","unstructured":"Han, S., Park, M., Yoon, J.H., Kang, J., Park, Y., Jeon, H.: High-fidelity 3D human digitization from single 2K resolution images. In: CVPR, pp. 12869\u201312879 (2023).https:\/\/doi.org\/10.1109\/CVPR52729.2023.01237","DOI":"10.1109\/CVPR52729.2023.01237"},{"key":"3641_CR104","doi-asserted-by":"publisher","unstructured":"Huang, Z., Xu, Y., Lassner, C., Li, H., Tung, T.: ARCH: animatable reconstruction of clothed humans. In: CVPR, pp. 3090\u20133099 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00316","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"3641_CR105","doi-asserted-by":"publisher","unstructured":"He, T., Xu, Y., Saito, S., Soatto, S., Tung, T.: ARCH++: animation-ready clothed human reconstruction revisited. In: ICCV, pp. 11026\u201311036 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01086","DOI":"10.1109\/ICCV48922.2021.01086"},{"key":"3641_CR106","doi-asserted-by":"publisher","unstructured":"Liao, T., Zhang, X., Xiu, Y., Yi, H., Liu, X., Qi, G., Zhang, Y., Wang, X., Zhu, X., Lei, Z.: High-fidelity clothed avatar reconstruction from a single image. In: CVPR, pp. 8662\u20138672 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00837","DOI":"10.1109\/CVPR52729.2023.00837"},{"key":"3641_CR107","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: ICLR (2023)"},{"key":"3641_CR108","unstructured":"Chen, M., Chen, J., Ye, X., Gao, H.-a., Chen, X., Fan, Z., Zhao, H.: Ultraman: single image 3D human reconstruction with ultra speed and detail. arXiv preprint arXiv:2403.12028 (2024)"},{"key":"3641_CR109","doi-asserted-by":"publisher","unstructured":"Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 5967\u20135976 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"key":"3641_CR110","doi-asserted-by":"publisher","unstructured":"Moon, G., Nam, H., Shiratori, T., Lee, K.M.: 3D clothed human reconstruction in the wild. In: ECCV, vol. 13662, pp. 184\u2013200 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_11","DOI":"10.1007\/978-3-031-20086-1_11"},{"key":"3641_CR111","doi-asserted-by":"publisher","unstructured":"Gabeur, V., Franco, J., Martin, X., Schmid, C., Rogez, G.: Moulding humans: non-parametric 3D human shape estimation from single images. In: ICCV, pp. 2232\u20132241 (2019).https:\/\/doi.org\/10.1109\/ICCV.2019.00232","DOI":"10.1109\/ICCV.2019.00232"},{"key":"3641_CR112","doi-asserted-by":"publisher","unstructured":"Kazhdan, M.M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Proceedings of the Fourth Eurographics Symposium on Geometry Processing, Cagliari, Sardinia, Italy, June 26\u201328, 2006. ACM International Conference Proceeding Series, vol. 256, pp. 61\u201370 (2006). https:\/\/doi.org\/10.2312\/SGP\/SGP06\/061-070","DOI":"10.2312\/SGP\/SGP06\/061-070"},{"key":"3641_CR113","doi-asserted-by":"publisher","unstructured":"Chibane, J., Alldieck, T., Pons-Moll, G.: Implicit functions in feature space for 3D shape reconstruction and completion. In: CVPR, pp. 6968\u20136979 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00700","DOI":"10.1109\/CVPR42600.2020.00700"},{"issue":"3","key":"3641_CR114","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/2487228.2487237","volume":"32","author":"MM Kazhdan","year":"2013","unstructured":"Kazhdan, M.M., Hoppe, H.: Screened Poisson surface reconstruction. ACM Trans. Graph. 32(3), 29\u201312913 (2013). https:\/\/doi.org\/10.1145\/2487228.2487237","journal-title":"ACM Trans. Graph."},{"key":"3641_CR115","unstructured":"Gao, J., Chen, W., Xiang, T., Jacobson, A., McGuire, M., Fidler, S.: Learning deformable tetrahedral meshes for 3D reconstruction. In: NeurIPS (2020)"},{"key":"3641_CR116","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. In: NeurIPS, pp. 6087\u20136101 (2021)"},{"key":"3641_CR117","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10674\u201310685 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01042","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3641_CR118","doi-asserted-by":"publisher","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3813\u20133824 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00355","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3641_CR119","doi-asserted-by":"publisher","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. In: CVPR, pp. 22500\u201322510 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02155","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"3641_CR120","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, vol. 162, pp. 12888\u201312900 (2022)"},{"key":"3641_CR121","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Ye, Y., Liu, Z., Tzionas, D., Black, M.J.: PuzzleAvatar: assembling 3D avatars from personal albums (2024). arXiv preprint arXiv:2405.14869","DOI":"10.1145\/3687771"},{"key":"3641_CR122","doi-asserted-by":"crossref","unstructured":"Gao, X., Li, X., Zhang, C., Zhang, Q., Cao, Y., Shan, Y., Quan, L.: ConTex-Human: free-view rendering of human from a single image with texture-consistent synthesis (2023). arXiv preprint arXiv:2311.17123","DOI":"10.1109\/CVPR52733.2024.00961"},{"key":"3641_CR123","doi-asserted-by":"publisher","unstructured":"Liu, R., Wu, R., Hoorick, B.V., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: Zero-shot one image to 3D object. In: ICCV, pp. 9264\u20139275 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00853","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"3641_CR124","unstructured":"He, T., Collomosse, J.P., Jin, H., Soatto, S.: Geo-PIFu: geometry and pixel aligned implicit functions for single-view human reconstruction. In: NeurIPS (2020)"},{"key":"3641_CR125","doi-asserted-by":"publisher","unstructured":"Wang, T., Liu, M., Zhu, J., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: CVPR, pp. 8798\u20138807 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00917","DOI":"10.1109\/CVPR.2018.00917"},{"key":"3641_CR126","doi-asserted-by":"publisher","unstructured":"Yang, X., Luo, Y., Xiu, Y., Wang, W., Xu, H., Fan, Z.: D-IF: uncertainty-aware human digitization via implicit distribution field. In: ICCV, pp. 9088\u20139098 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00837","DOI":"10.1109\/ICCV51070.2023.00837"},{"key":"3641_CR127","doi-asserted-by":"publisher","unstructured":"Cao, Y., Han, K., Wong, K.K.: SeSDF: self-evolved signed distance field for implicit 3D clothed human reconstruction. In: CVPR, pp. 4647\u20134657 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00451","DOI":"10.1109\/CVPR52729.2023.00451"},{"key":"3641_CR128","doi-asserted-by":"publisher","unstructured":"Song, D., Lee, H., Seo, J., Cho, D.: DIFu: depth-guided implicit function for clothed human reconstruction. In: CVPR, pp. 8738\u20138747 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00844","DOI":"10.1109\/CVPR52729.2023.00844"},{"key":"3641_CR129","unstructured":"Zhang, Z., Sun, L., Yang, Z., Chen, L., Yang, Y.: Global-correlated 3D-decoupling transformer for clothed avatar reconstruction. In: NeurIPS (2023)"},{"key":"3641_CR130","doi-asserted-by":"publisher","unstructured":"Choi, H., Moon, G., Armando, M., Leroy, V., Lee, K.M., Rogez, G.: MonoNHR: monocular neural human renderer. In: 3DV, pp. 242\u2013251 (2022). https:\/\/doi.org\/10.1109\/3DV57658.2022.00036","DOI":"10.1109\/3DV57658.2022.00036"},{"key":"3641_CR131","unstructured":"Weng, Z., Liu, J., Tan, H., Xu, Z., Zhou, Y., Yeung-Levy, S., Yang, J.: Single-view 3D human digitalization with large reconstruction models. arXiv preprint arXiv:2401.12175 (2024)"},{"key":"3641_CR132","unstructured":"Hong, Y., Zhang, K., Gu, J., Bi, S., Zhou, Y., Liu, D., Liu, F., Sunkavalli, K., Bui, T., Tan, H.: LRM: large reconstruction model for single image to 3D (2023). arXiv preprint arXiv:2311.04400"},{"key":"3641_CR133","doi-asserted-by":"publisher","unstructured":"Xu, X., Loy, C.C.: 3D human texture estimation from a single image with transformers. In: ICCV, pp. 13829\u201313838 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01359","DOI":"10.1109\/ICCV48922.2021.01359"},{"key":"3641_CR134","doi-asserted-by":"publisher","unstructured":"Svitov, D., Gudkov, D., Bashirov, R., Lempitsky, V.: DINAR: diffusion inpainting of neural textures for one-shot human avatars. In: ICCV, pp. 7039\u20137049 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00650","DOI":"10.1109\/ICCV51070.2023.00650"},{"key":"3641_CR135","doi-asserted-by":"crossref","unstructured":"Zhan, X., Yang, J., Li, Y., Guo, J., Guo, Y., Wang, W.: Semantic human mesh reconstruction with textures (2024). arXiv preprint arXiv:2403.02561","DOI":"10.1109\/CVPR52733.2024.00022"},{"key":"3641_CR136","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, X., Zhang, Q., Cao, Y., Shan, Y., Liao, J.: HumanRef: single image to 3D human generation via reference-guided diffusion. arXiv preprint arXiv:2311.16961 (2023)","DOI":"10.1109\/CVPR52733.2024.00181"},{"key":"3641_CR137","doi-asserted-by":"publisher","unstructured":"Natsume, R., Saito, S., Huang, Z., Chen, W., Ma, C., Li, H., Morishima, S.: SiCloPe: silhouette-based clothed people. In: CVPR, pp. 4480\u20134490 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00461","DOI":"10.1109\/CVPR.2019.00461"},{"key":"3641_CR138","doi-asserted-by":"crossref","unstructured":"Sengupta, A., Alldieck, T., Kolotouros, N., Corona, E., Zanfir, A., Sminchisescu, C.: DiffHuman: probabilistic photorealistic 3D reconstruction of humans (2024). arXiv preprint arXiv:2404.00485","DOI":"10.1109\/CVPR52733.2024.00143"},{"key":"3641_CR139","doi-asserted-by":"publisher","unstructured":"Wang, J., Zhong, Y., Li, Y., Zhang, C., Wei, Y.: Re-identification supervised texture generation. In: CVPR, pp. 11846\u201311856 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01212","DOI":"10.1109\/CVPR.2019.01212"},{"issue":"9","key":"3641_CR140","doi-asserted-by":"publisher","first-page":"4490","DOI":"10.1109\/TPAMI.2021.3070002","volume":"44","author":"X Xu","year":"2022","unstructured":"Xu, X., Chen, H., Moreno-Noguer, F., Jeni, L.A., Torre, F.D.: 3D human pose, shape and texture from low-resolution images and videos. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 4490\u20134504 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3070002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3641_CR141","doi-asserted-by":"crossref","unstructured":"Altindis, S.F., Meric, A., Dalva, Y., Gudukbay, U., Dundar, A.: Refining 3D human texture estimation from a single image (2023). arXiv preprint arXiv:2303.03471","DOI":"10.1109\/TPAMI.2024.3456817"},{"key":"3641_CR142","doi-asserted-by":"publisher","unstructured":"Fang, Q., Shuai, Q., Dong, J., Bao, H., Zhou, X.: Reconstructing 3D human pose by watching humans in the mirror. In: CVPR, pp. 12814\u201312823 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01262","DOI":"10.1109\/CVPR46437.2021.01262"},{"key":"3641_CR143","doi-asserted-by":"publisher","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: CVPR, pp. 9054\u20139063 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00894","DOI":"10.1109\/CVPR46437.2021.00894"},{"issue":"2","key":"3641_CR144","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/3181973","volume":"37","author":"W Xu","year":"2018","unstructured":"Xu, W., Chatterjee, A., Zollh\u00f6fer, M., Rhodin, H., Mehta, D., Seidel, H., Theobalt, C.: MonoPerfCap: human performance capture from monocular video. ACM Trans. Graph. 37(2), 27 (2018). https:\/\/doi.org\/10.1145\/3181973","journal-title":"ACM Trans. Graph."},{"issue":"2","key":"3641_CR145","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1145\/3311970","volume":"38","author":"M Habermann","year":"2019","unstructured":"Habermann, M., Xu, W., Zollh\u00f6fer, M., Pons-Moll, G., Theobalt, C.: LiveCap: real-time human performance capture from monocular video. ACM Trans. Graph. 38(2), 14\u201311417 (2019). https:\/\/doi.org\/10.1145\/3311970","journal-title":"ACM Trans. Graph."},{"key":"3641_CR146","doi-asserted-by":"crossref","unstructured":"Habermann, M., Xu, W., Zollh\u00f6fer, M., Pons-Moll, G., Theobalt, C.: DeepCap: monocular human performance capture using weak supervision. In: CVPR, pp. 5051\u20135062 (2020)","DOI":"10.1109\/CVPR42600.2020.00510"},{"key":"3641_CR147","doi-asserted-by":"publisher","unstructured":"Alldieck, T., Magnor, M.A., Xu, W., Theobalt, C., Pons-Moll, G.: Detailed human avatars from monocular video. In: 3DV, pp. 98\u2013109 (2018). https:\/\/doi.org\/10.1109\/3DV.2018.00022","DOI":"10.1109\/3DV.2018.00022"},{"key":"3641_CR148","doi-asserted-by":"publisher","unstructured":"Jiang, B., Hong, Y., Bao, H., Zhang, J.: SelfRecon: self reconstruction your digital avatar from monocular video. In: CVPR, pp. 5595\u20135605 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00552","DOI":"10.1109\/CVPR52688.2022.00552"},{"key":"3641_CR149","doi-asserted-by":"publisher","unstructured":"Peng, S., Dong, J., Wang, Q., Zhang, S., Shuai, Q., Zhou, X., Bao, H.: Animatable neural radiance fields for modeling dynamic human bodies. In: ICCV, pp. 14294\u201314303 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01405","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"3641_CR150","unstructured":"Chen, J., Zhang, Y., Kang, D., Zhe, X., Bao, L., Jia, X., Lu, H.: Animatable neural radiance fields from monocular RGB videos (2021). arXiv preprint arXiv:2106.13629"},{"key":"3641_CR151","doi-asserted-by":"publisher","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR, pp. 586\u2013595 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3641_CR152","doi-asserted-by":"publisher","unstructured":"Li, R., Tanke, J., Vo, M., Zollh\u00f6fer, M., Gall, J., Kanazawa, A., Lassner, C.: TAVA: template-free animatable volumetric actors. In: ECCV, vol. 13692, pp. 419\u2013436 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_25","DOI":"10.1007\/978-3-031-19824-3_25"},{"key":"3641_CR153","doi-asserted-by":"publisher","unstructured":"Jiang, W., Yi, K.M., Samei, G., Tuzel, O., Ranjan, A.: NeuMan: Neural human radiance field from a single video. In: ECCV, vol. 13692, pp. 402\u2013418 (2022).https:\/\/doi.org\/10.1007\/978-3-031-19824-3_24","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"3641_CR154","doi-asserted-by":"publisher","unstructured":"Yu, Z., Cheng, W., Liu, X., Wu, W., Lin, K.: MonoHuman: animatable human neural field from monocular video. In: CVPR, pp. 16943\u201316953 (2023).https:\/\/doi.org\/10.1109\/CVPR52729.2023.01625","DOI":"10.1109\/CVPR52729.2023.01625"},{"key":"3641_CR155","doi-asserted-by":"publisher","unstructured":"Wang, S., Schwarz, K., Geiger, A., Tang, S.: ARAH: animatable volume rendering of articulated human SDFs. In: ECCV, vol. 13692, pp. 1\u201319 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_1","DOI":"10.1007\/978-3-031-19824-3_1"},{"key":"3641_CR156","unstructured":"Gropp, A., Yariv, L., Haim, N., Atzmon, M., Lipman, Y.: Implicit geometric regularization for learning shapes. In: ICML. Proceedings of Machine Learning Research, vol. 119, pp. 3789\u20133799 (2020)"},{"key":"3641_CR157","doi-asserted-by":"publisher","unstructured":"Jiang, T., Chen, X., Song, J., Hilliges, O.: InstantAvatar: learning avatars from monocular video in 60 seconds. In: CVPR, pp. 16922\u201316932 (2023).https:\/\/doi.org\/10.1109\/CVPR52729.2023.01623","DOI":"10.1109\/CVPR52729.2023.01623"},{"issue":"4","key":"3641_CR158","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution Hash encoding. ACM Trans. Graph. 41(4), 102\u2013110215 (2022). https:\/\/doi.org\/10.1145\/3528223.3530127","journal-title":"ACM Trans. Graph."},{"key":"3641_CR159","doi-asserted-by":"publisher","unstructured":"Feng, Y., Yang, J., Pollefeys, M., Black, M.J., Bolkart, T.: Capturing and animation of body and clothing from monocular video. In: SIGGRAPH Asia 2022 Conference Papers, pp. 45\u20131459 (2022). https:\/\/doi.org\/10.1145\/3550469.3555423","DOI":"10.1145\/3550469.3555423"},{"key":"3641_CR160","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Huang, H., Yu, T., Zhang, H., Guo, Y., Liu, Y.: Structured local radiance fields for human avatar modeling. In: CVPR, pp. 15872\u201315882 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01543","DOI":"10.1109\/CVPR52688.2022.01543"},{"key":"3641_CR161","unstructured":"Su, S., Yu, F., Zollh\u00f6fer, M., Rhodin, H.: A-NeRF: articulated neural radiance fields for learning human shape, appearance, and pose. In: NeurIPS, pp. 12278\u201312291 (2021)"},{"key":"3641_CR162","doi-asserted-by":"publisher","unstructured":"Xu, T., Fujita, Y., Matsumoto, E.: Surface-aligned neural radiance fields for controllable 3D human synthesis. In: CVPR, pp. 15862\u201315871 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01542","DOI":"10.1109\/CVPR52688.2022.01542"},{"issue":"6","key":"3641_CR163","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1145\/3478513.3480528","volume":"40","author":"L Liu","year":"2021","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 Trans. Graph. 40(6), 219\u2013121916 (2021). https:\/\/doi.org\/10.1145\/3478513.3480528","journal-title":"ACM Trans. Graph."},{"key":"3641_CR164","doi-asserted-by":"publisher","unstructured":"Chen, Y., Wang, X., Chen, X., Zhang, Q., Li, X., Guo, Y., Wang, J., Wang, F.: UV volumes for real-time rendering of editable free-view human performance. In: CVPR, pp. 16621\u201316631 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01595","DOI":"10.1109\/CVPR52729.2023.01595"},{"key":"3641_CR165","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"3641_CR166","doi-asserted-by":"crossref","unstructured":"Lei, J., Wang, Y., Pavlakos, G., Liu, L., Daniilidis, K.: GART: Gaussian articulated template models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"3641_CR167","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Chang, J.-H.R., Gabriel, J., Tuzel, O., Ranjan, A.: HUGS: human Gaussian splats. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00055"},{"key":"3641_CR168","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"3641_CR169","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00117"},{"key":"3641_CR170","doi-asserted-by":"publisher","unstructured":"Guo, C., Jiang, T., Chen, X., Song, J., Hilliges, O.: Vid2Avatar: 3D avatar reconstruction from videos in the wild via self-supervised scene decomposition. In: CVPR, pp. 12858\u201312868 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01236","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"3641_CR171","unstructured":"Feng, Y., Liu, W., Bolkart, T., Yang, J., Pollefeys, M., Black, M.J.: Learning disentangled avatars with hybrid 3D representations. arXiv (2023)"},{"key":"3641_CR172","doi-asserted-by":"publisher","unstructured":"Wang, K., Zhang, G., Cong, S., Yang, J.: Clothed human performance capture with a double-layer neural radiance fields. In: CVPR, pp. 21098\u201321107 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02021","DOI":"10.1109\/CVPR52729.2023.02021"},{"key":"3641_CR173","doi-asserted-by":"publisher","unstructured":"Chen, M., Zhang, J., Xu, X., Liu, L., Cai, Y., Feng, J., Yan, S.: Geometry-guided progressive nerf for generalizable and efficient neural human rendering. In: ECCV, vol. 13683, pp. 222\u2013239 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_14","DOI":"10.1007\/978-3-031-20050-2_14"},{"key":"3641_CR174","unstructured":"Peng, B., Hu, J., Zhou, J., Zhang, J.: SelfNeRF: fast training NeRF for human from monocular self-rotating video (2022). arXiv preprint arXiv:2210.01651"},{"key":"3641_CR175","doi-asserted-by":"publisher","unstructured":"Geng, C., Peng, S., Xu, Z., Bao, H., Zhou, X.: Learning neural volumetric representations of dynamic humans in minutes. In: CVPR, pp. 8759\u20138770 (2023).https:\/\/doi.org\/10.1109\/CVPR52729.2023.00846","DOI":"10.1109\/CVPR52729.2023.00846"},{"key":"3641_CR176","unstructured":"Kwon, Y., Kim, D., Ceylan, D., Fuchs, H.: Neural human performer: learning generalizable radiance fields for human performance rendering. In: NeurIPS, pp. 24741\u201324752 (2021)"},{"key":"3641_CR177","unstructured":"Li, C., Lin, J., Lee, G.H.: GHuNeRF: generalizable human NeRF from a monocular video (2023). arXiv preprint arXiv:2308.16576"},{"key":"3641_CR178","doi-asserted-by":"publisher","unstructured":"Chen, X., Zheng, Y., Black, M.J., Hilliges, O., Geiger, A.: SNARF: differentiable forward skinning for animating non-rigid neural implicit shapes. In: ICCV, pp. 11574\u201311584 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01139","DOI":"10.1109\/ICCV48922.2021.01139"},{"issue":"10","key":"3641_CR179","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). https:\/\/doi.org\/10.1109\/TPAMI.2023.3271569","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3641_CR180","doi-asserted-by":"publisher","unstructured":"Zhi, Y., Qian, S., Yan, X., Gao, S.: Dual-space NeRF: learning animatable avatars and scene lighting in separate spaces. In: 3DV, pp. 1\u201310 (2022). https:\/\/doi.org\/10.1109\/3DV57658.2022.00048","DOI":"10.1109\/3DV57658.2022.00048"},{"key":"3641_CR181","doi-asserted-by":"publisher","unstructured":"Mu, J., Sang, S., Vasconcelos, N., Wang, X.: ActorsNeRF: animatable few-shot human rendering with generalizable NeRFs. In: ICCV, pp. 18345\u201318355 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01686","DOI":"10.1109\/ICCV51070.2023.01686"},{"key":"3641_CR182","doi-asserted-by":"publisher","unstructured":"Noguchi, A., Sun, X., Lin, S., Harada, T.: Neural articulated radiance field. In: ICCV, pp. 5742\u20135752 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00571","DOI":"10.1109\/ICCV48922.2021.00571"},{"key":"3641_CR183","doi-asserted-by":"publisher","unstructured":"Te, G., Li, X., Li, X., Wang, J., Hu, W., Lu, Y.: Neural capture of animatable 3D human from monocular video. In: ECCV, vol. 13666, pp. 275\u2013291 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_16","DOI":"10.1007\/978-3-031-20068-7_16"},{"key":"3641_CR184","doi-asserted-by":"publisher","unstructured":"Su, S., Bagautdinov, T.M., Rhodin, H.: DANBO: disentangled articulated neural body representations via graph neural networks. In: ECCV, vol. 13662, pp. 107\u2013124 (2022).https:\/\/doi.org\/10.1007\/978-3-031-20086-1_7","DOI":"10.1007\/978-3-031-20086-1_7"},{"key":"3641_CR185","doi-asserted-by":"publisher","unstructured":"Zhang, R., Chen, J.: NDF: neural deformable fields for dynamic human modelling. In: ECCV, vol. 13692, pp. 37\u201352 (2022).https:\/\/doi.org\/10.1007\/978-3-031-19824-3_3","DOI":"10.1007\/978-3-031-19824-3_3"},{"key":"3641_CR186","unstructured":"Li, M., Tao, J., Yang, Z., Yang, Y.: Human101: Training 100+FPS human Gaussians in 100s from 1 view (2023). arXiv preprint arXiv:2312.15258"},{"key":"3641_CR187","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 (2023). arXiv preprint arXiv:2311.17113","DOI":"10.1109\/CVPR52733.2024.00081"},{"key":"3641_CR188","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"3641_CR189","unstructured":"Li, M., Yao, S., Xie, Z., Chen, K., Jiang, Y.-G.: GaussianBody: clothed human reconstruction via 3D Gaussian splatting (2024). arXiv preprint arXiv:2401.09720"},{"key":"3641_CR190","unstructured":"Jung, H., Brasch, N., Song, J., Perez-Pellitero, E., Zhou, Y., Li, Z., Navab, N., Busam, B.: Deformable 3D Gaussian splatting for animatable human avatars (2023). arXiv preprint arXiv:2312.15059"},{"key":"3641_CR191","unstructured":"Jena, R., Iyer, G.S., Choudhary, S., Smith, B., Chaudhari, P., Gee, J.: SplatArmor: articulated Gaussian splatting for animatable humans from monocular RGB videos (2023). arXiv preprint arXiv:2311.10812"},{"issue":"9","key":"3641_CR192","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TSMC.2018.2850149","volume":"49","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Sheng, B., Yang, P., Li, P., Shen, R., Feng, D.D.: Deep convolutional neural networks for human action recognition using depth maps and postures. IEEE Trans. Syst. Man Cybern. Syst. 49(9), 1806\u20131819 (2019). https:\/\/doi.org\/10.1109\/TSMC.2018.2850149","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"7","key":"3641_CR193","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","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 Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014). https:\/\/doi.org\/10.1109\/TPAMI.2013.248","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3641_CR194","doi-asserted-by":"publisher","unstructured":"Joo, H., Liu, H., Tan, L., Gui, L., Nabbe, B.C., Matthews, I.A., Kanade, T., Nobuhara, S., Sheikh, Y.: Panoptic studio: a massively multiview system for social motion capture. In: ICCV, pp. 3334\u20133342 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.381","DOI":"10.1109\/ICCV.2015.381"},{"key":"3641_CR195","doi-asserted-by":"publisher","unstructured":"Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., Theobalt, C.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 3DV, pp. 506\u2013516 (2017). https:\/\/doi.org\/10.1109\/3DV.2017.00064","DOI":"10.1109\/3DV.2017.00064"},{"key":"3641_CR196","doi-asserted-by":"publisher","unstructured":"Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: ECCV, vol. 11214, pp. 614\u2013631 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_37","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"3641_CR197","unstructured":"Tsuchida, S., Fukayama, S., Hamasaki, M., Goto, M.: AIST dance video database: multi-genre, multi-dancer, and multi-camera database for dance information processing. In: ISMIR, pp. 501\u2013510 (2019)"},{"key":"3641_CR198","doi-asserted-by":"publisher","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST++. In: ICCV, pp. 13381\u201313392 (2021).https:\/\/doi.org\/10.1109\/ICCV48922.2021.01315","DOI":"10.1109\/ICCV48922.2021.01315"},{"issue":"4","key":"3641_CR199","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/3592415","volume":"42","author":"M Isik","year":"2023","unstructured":"Isik, 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 Trans. Graph. 42(4), 160\u2013116012 (2023). https:\/\/doi.org\/10.1145\/3592415","journal-title":"ACM Trans. Graph."},{"key":"3641_CR200","doi-asserted-by":"publisher","unstructured":"Cai, Z., Ren, D., Zeng, A., Lin, Z., Yu, T., Wang, W., Fan, X., Gao, Y., Yu, Y., Pan, L., Hong, F., Zhang, M., Loy, C.C., Yang, L., Liu, Z.: HuMMan: multi-modal 4D human dataset for versatile sensing and modeling. In: ECCV, vol. 13667, pp. 557\u2013577 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20071-7_33","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"3641_CR201","unstructured":"Cheng, W., Xu, S., Piao, J., Qian, C., Wu, W., Lin, K.-Y., Li, H.: Generalizable neural performer: learning robust radiance fields for human novel view synthesis (2022). arXiv preprint arXiv:2204.11798"},{"key":"3641_CR202","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Li, C., Liu, K., Liao, H., Hu, J., Zhu, J., Ning, S., Qiu, L., Wang, C., Wang, S., et\u00a0al.: MVHumanNet: a large-scale dataset of multi-view daily dressing human captures (2023). arXiv preprint arXiv:2312.02963","DOI":"10.1109\/CVPR52733.2024.01872"},{"key":"3641_CR203","doi-asserted-by":"publisher","unstructured":"Zhang, C., Pujades, S., Black, M.J., Pons-Moll, G.: Detailed, accurate, human shape estimation from clothed 3D scan sequences. In: CVPR, pp. 5484\u20135493 (2017).https:\/\/doi.org\/10.1109\/CVPR.2017.582","DOI":"10.1109\/CVPR.2017.582"},{"issue":"2","key":"3641_CR204","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1109\/TPAMI.2022.3168569","volume":"45","author":"Z Su","year":"2023","unstructured":"Su, Z., Yu, T., Wang, Y., Liu, Y.: DeepCloth: neural garment representation for shape and style editing. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1581\u20131593 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3168569","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3641_CR205","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/3450626.3459749","volume":"40","author":"M Habermann","year":"2021","unstructured":"Habermann, M., Liu, L., Xu, W., Zollh\u00f6fer, M., Pons-Moll, G., Theobalt, C.: Real-time deep dynamic characters. ACM Trans. Graph. 40(4), 94\u201319416 (2021). https:\/\/doi.org\/10.1145\/3450626.3459749","journal-title":"ACM Trans. Graph."},{"key":"3641_CR206","doi-asserted-by":"publisher","unstructured":"Yu, Z., Yoon, J.S., Lee, I.K., Venkatesh, P., Park, J., Yu, J., Park, H.S.: HUMBI: a large multiview dataset of human body expressions. In: CVPR, pp. 2987\u20132997 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00306","DOI":"10.1109\/CVPR42600.2020.00306"},{"issue":"1","key":"3641_CR207","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/TPAMI.2021.3138762","volume":"45","author":"JS Yoon","year":"2023","unstructured":"Yoon, J.S., Yu, Z., Park, J., Park, H.S.: HUMBI: a large multiview dataset of human body expressions and benchmark challenge. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 623\u2013640 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2021.3138762","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3641_CR208","unstructured":"Over 4,000 Scanned 3D People Models. https:\/\/renderpeople.com\/"},{"issue":"4","key":"3641_CR209","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). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"3641_CR210","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1145\/3592101","volume":"42","author":"Z Zheng","year":"2023","unstructured":"Zheng, Z., Zhao, X., Zhang, H., Liu, B., Liu, Y.: AvatarReX: real-time expressive full-body avatars. ACM Trans. Graph. 42(4), 158\u2013115819 (2023). https:\/\/doi.org\/10.1145\/3592101","journal-title":"ACM Trans. Graph."},{"key":"3641_CR211","unstructured":"Dong, J., Fang, Q., Guo, Y., Peng, S., Shuai, Q., Zhou, X., Bao, H.: TotalSelfScan: learning full-body avatars from self-portrait videos of faces, hands, and bodies. In: NeurIPS (2022)"},{"key":"3641_CR212","doi-asserted-by":"publisher","unstructured":"Yu, T., Zheng, Z., Guo, K., Zhao, J., Dai, Q., Li, H., Pons-Moll, G., Liu, Y.: DoubleFusion: real-time capture of human performances with inner body shapes from a single depth sensor. In: CVPR, pp. 7287\u20137296 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00761","DOI":"10.1109\/CVPR.2018.00761"},{"key":"3641_CR213","doi-asserted-by":"crossref","unstructured":"Lin, S., Li, Z., Su, Z., Zheng, Z., Zhang, H., Liu, Y.: LayGA: layered Gaussian avatars for animatable clothing transfer (2024). arXiv preprint arXiv:2405.07319","DOI":"10.1145\/3641519.3657501"},{"key":"3641_CR214","doi-asserted-by":"publisher","unstructured":"Khirodkar, R., Tripathi, S., Kitani, K.: Occluded human mesh recovery. In: CVPR, pp. 1705\u20131715 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00176","DOI":"10.1109\/CVPR52688.2022.00176"},{"key":"3641_CR215","doi-asserted-by":"publisher","unstructured":"Wang, J., Yoon, J.S., Wang, T.Y., Singh, K.K., Neumann, U.: Complete 3D human reconstruction from a single incomplete image. In: CVPR, pp. 8748\u20138758 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00845","DOI":"10.1109\/CVPR52729.2023.00845"},{"key":"3641_CR216","doi-asserted-by":"publisher","unstructured":"Xiang, T., Sun, A., Wu, J., Adeli, E., Fei-Fei, L.: Rendering Humans from object-occluded monocular videos. In: ICCV, pp. 3216\u20133227 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00300","DOI":"10.1109\/ICCV51070.2023.00300"},{"key":"3641_CR217","unstructured":"Ye, J., Zhang, Z., Jiang, Y., Liao, Q., Yang, W., Lu, Z.: OccGaussian: 3D Gaussian splatting for occluded human rendering (2024). arXiv preprint arXiv:2404.08449"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03641-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03641-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03641-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T10:23:28Z","timestamp":1744799008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03641-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,26]]},"references-count":217,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3641"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03641-7","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,26]]},"assertion":[{"value":"3 September 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}