Towards efficient and photorealistic 3D human reconstruction: A brief survey
Reconstructing 3D digital models of humans from sensory data is a long-standing problem in computer vision and graphics with a variety of applications in VR/AR, film production, and human–computer interaction, etc. While a huge amount of effort has been devoted to developing various capture hardware...
Saved in:
| Published in | Visual informatics (Online) Vol. 5; no. 4; pp. 11 - 19 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.12.2021
Elsevier |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Reconstructing 3D digital models of humans from sensory data is a long-standing problem in computer vision and graphics with a variety of applications in VR/AR, film production, and human–computer interaction, etc. While a huge amount of effort has been devoted to developing various capture hardware and reconstruction algorithms, traditional reconstruction pipelines may still suffer from high-cost capture systems and tedious capture processes, which prevent them from being easily accessible. Moreover, the dedicatedly hand-crafted pipelines are prone to reconstruction artifacts, resulting in limited visual quality. To solve these challenges, the recent trend in this area is to use deep neural networks to improve reconstruction efficiency and robustness by learning human priors from existing data. Neural network-based implicit functions have been also shown to be a favorable 3D representation compared to traditional forms like meshes and voxels. Furthermore, neural rendering has emerged as a powerful tool to achieve highly photorealistic modeling and re-rendering of humans by end-to-end optimizing the visual quality of output images. In this article, we will briefly review these advances in this fast-developing field, discuss the advantages and limitations of different approaches, and finally, share some thoughts on future research directions. |
|---|---|
| AbstractList | Reconstructing 3D digital models of humans from sensory data is a long-standing problem in computer vision and graphics with a variety of applications in VR/AR, film production, and human–computer interaction, etc. While a huge amount of effort has been devoted to developing various capture hardware and reconstruction algorithms, traditional reconstruction pipelines may still suffer from high-cost capture systems and tedious capture processes, which prevent them from being easily accessible. Moreover, the dedicatedly hand-crafted pipelines are prone to reconstruction artifacts, resulting in limited visual quality. To solve these challenges, the recent trend in this area is to use deep neural networks to improve reconstruction efficiency and robustness by learning human priors from existing data. Neural network-based implicit functions have been also shown to be a favorable 3D representation compared to traditional forms like meshes and voxels. Furthermore, neural rendering has emerged as a powerful tool to achieve highly photorealistic modeling and re-rendering of humans by end-to-end optimizing the visual quality of output images. In this article, we will briefly review these advances in this fast-developing field, discuss the advantages and limitations of different approaches, and finally, share some thoughts on future research directions. |
| Author | Peng, Sida Chen, Lu Zhou, Xiaowei |
| Author_xml | – sequence: 1 givenname: Lu surname: Chen fullname: Chen, Lu organization: Taishan College, Shandong University, Qingdao, China – sequence: 2 givenname: Sida orcidid: 0000-0001-6546-4525 surname: Peng fullname: Peng, Sida organization: State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China – sequence: 3 givenname: Xiaowei surname: Zhou fullname: Zhou, Xiaowei email: xwzhou@zju.edu.cn organization: State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China |
| BookMark | eNqFkMtKQzEURYMoWKt_4CA_0JrXfXUgFN9QcKLgLORxoin1piRpxb831yqIAx3lZMPanLOO0H4fekDolJIpJbQ-W063PvneTRlhtERTQvgeGjFRt5OKsKf9H_MhOklpSQhhbWEpHaHFQ3hT0SYMznnjoc9Y9RavX0IOEdTKp-wN5pf4ZfOqehzBhD7luDHZh36G51hHDw6nTdzC-zE6cGqV4OTrHaPH66uHi9vJ4v7m7mK-mBhB2zxpRO0qp3THu8YB08xqQzrqbEdoY1vOTFs-YDUBbmphlSWcNrStGKXEVpyP0d2u1wa1lOvoX1V8l0F5-RmE-CxVLHuvQLYOrGPKiVYLwQF0VwntNGm6ujPcmdI123WZGFKK4KTxWQ3X5aj8SlIiB81yKXea5aB5SIvmAotf8Pcy_2DnOwyKpK2HKNOg3oD1RXAuV_i_Cz4A2EScnw |
| CitedBy_id | crossref_primary_10_1016_j_measurement_2022_112321 crossref_primary_10_1007_s41870_023_01470_w crossref_primary_10_1111_cgf_14971 crossref_primary_10_1109_TPAMI_2023_3298850 crossref_primary_10_1080_00140139_2024_2449113 crossref_primary_10_1109_TVCG_2022_3209352 crossref_primary_10_2478_emj_2024_0020 crossref_primary_10_1109_TBIOM_2023_3276901 crossref_primary_10_1016_j_cag_2023_07_011 crossref_primary_10_1038_s41746_023_00909_5 crossref_primary_10_1360_SSI_2022_0319 crossref_primary_10_3390_electronics12224705 crossref_primary_10_1016_j_neucom_2024_128049 crossref_primary_10_1109_JPROC_2023_3321433 crossref_primary_10_3233_IDT_240458 crossref_primary_10_1016_j_imavis_2023_104782 |
| Cites_doi | 10.1109/CVPR46437.2021.01018 10.1109/CVPR.2018.00411 10.1109/CVPR.2019.00798 10.1145/3355089.3356571 10.1109/CVPR46437.2021.00894 10.1109/TPAMI.2019.2954885 10.1109/CVPR42600.2020.00813 10.1109/CVPR46437.2021.00466 10.1109/CVPR.2019.00461 10.1109/CVPR42600.2020.00530 10.1007/978-3-030-01234-2_2 10.1109/CVPR46437.2021.00741 10.1109/CVPR42600.2020.00016 10.1109/CVPR46437.2021.00150 10.1109/CVPR42600.2020.00140 10.1109/CVPR.2019.00453 10.1109/CVPR46437.2021.00616 10.1109/CVPR.2014.196 10.1016/j.cviu.2019.102897 10.1109/CVPR42600.2020.00510 10.1109/CVPR46437.2021.00291 10.1145/2816795.2818013 10.1007/978-3-030-01252-6_35 10.1109/CVPR46437.2021.00287 10.1109/CVPR.2019.00576 10.1109/ICCV48922.2021.00581 10.1109/CVPR46437.2021.01308 10.1109/CVPR42600.2020.00700 10.1145/3450626.3459783 10.1007/978-3-030-01270-0_21 10.1109/CVPR46437.2021.00060 10.1145/3181973 10.1109/CVPR46437.2021.00455 10.1109/ICCV.2019.00780 10.1109/ICCV.2019.00239 10.1145/2766945 10.1109/CVPR46437.2021.00643 10.1109/CVPR42600.2020.00316 10.1016/j.patcog.2017.08.003 10.1016/j.cviu.2021.103275 10.1109/ICCV.2019.00783 10.1109/ICCV.2019.00238 10.1145/3311970 10.1145/2897824.2925969 10.1109/CVPR42600.2020.00491 |
| ContentType | Journal Article |
| Copyright | 2021 The Author(s) |
| Copyright_xml | – notice: 2021 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.visinf.2021.10.003 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2468-502X |
| EndPage | 19 |
| ExternalDocumentID | oai_doaj_org_article_8fedf2af48b443eeb954bfb07969c3fc 10_1016_j_visinf_2021_10_003 S2468502X21000413 |
| GroupedDBID | 0SF 6I. AACTN AAEDW AAFTH AALRI AAXUO ABMAC ACGFS ADBBV AEXQZ AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ BCNDV EBS EJD FDB GROUPED_DOAJ M~E NCXOZ OK1 ROL SSZ 0R~ AAYWO AAYXX ACVFH ADCNI ADVLN AEUPX AFPUW AIGII AKBMS AKRWK AKYEP CITATION |
| ID | FETCH-LOGICAL-c418t-746f5fab9397fe2b2dbc091fd9017d832c81fdedb0e3c64dad03171852110d533 |
| IEDL.DBID | DOA |
| ISSN | 2468-502X |
| IngestDate | Wed Aug 27 01:17:10 EDT 2025 Tue Jul 01 03:37:20 EDT 2025 Thu Apr 24 23:00:32 EDT 2025 Thu Jul 20 20:10:56 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | Neural representation Differentiable rendering 3D human reconstruction |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. https://www.elsevier.com/tdm/userlicense/1.0 http://creativecommons.org/licenses/by-nc-nd/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c418t-746f5fab9397fe2b2dbc091fd9017d832c81fdedb0e3c64dad03171852110d533 |
| ORCID | 0000-0001-6546-4525 |
| OpenAccessLink | https://doaj.org/article/8fedf2af48b443eeb954bfb07969c3fc |
| PageCount | 9 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_8fedf2af48b443eeb954bfb07969c3fc crossref_citationtrail_10_1016_j_visinf_2021_10_003 crossref_primary_10_1016_j_visinf_2021_10_003 elsevier_sciencedirect_doi_10_1016_j_visinf_2021_10_003 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | December 2021 2021-12-00 2021-12-01 |
| PublicationDateYYYYMMDD | 2021-12-01 |
| PublicationDate_xml | – month: 12 year: 2021 text: December 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Visual informatics (Online) |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | Lombardi, Simon, Saragih, Schwartz, Lehrmann, Sheikh (b47) 2019 Kanazawa, Black, Jacobs, Malik (b34) 2018 Yu, A., Ye, V., Tancik, M., Kanazawa, A., 2021. pixelnerf: Neural radiance fields from one or few images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578–4587. Xu, Chatterjee, Zollhöfer, Rhodin, Mehta, Seidel, Theobalt (b78) 2018; 37 Gilbert, A., Volino, M., Collomosse, J., Hilton, A., 2018. Volumetric performance capture from minimal camera viewpoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 566–581. Jiang, Kolotouros, Pavlakos, Zhou, Daniilidis (b32) 2020 Collet, Chuang, Sweeney, Gillett, Evseev, Calabrese, Hoppe, Kirk, Sullivan (b13) 2015 Dong, Shuai, Zhang, Liu, Zhou, Bao (b18) 2020 Deng, Lewis, Jeruzalski, Pons-Moll, Hinton, Norouzi, Tagliasacchi (b15) 2020 Zheng, Shao, Zhang, Yu, Zheng, Dai, Liu (b89) 2021 Xiang, Prada, Bagautdinov, Xu, Dong, Wen, Hodgins, Wu (b77) 2021 Yu, Li, Tancik, Li, Ng, Kanazawa (b82) 2021 Bozic, A., Palafox, P., Zollhofer, M., Thies, J., Dai, A., Nieß ner, M., 2021. Neural deformation graphs for globally-consistent non-rigid reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1450–1459. Joo, Simon, Sheikh (b33) 2018 Chibane, J., Alldieck, T., Pons-Moll, G., 2020. Implicit functions in feature space for 3d shape reconstruction and completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6970–6981. Zhang, Srinivasan, Deng, Debevec, Freeman, Barron (b87) 2021 Liu, S., Li, T., Chen, W., Li, H., 2019. Soft rasterizer: A differentiable renderer for image-based 3d reasoning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7708–7717. Li, Z., Niklaus, S., Snavely, N., Wang, O., 2021. Neural scene flow fields for space-time view synthesis of dynamic scenes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6498–6508. Zhou, Tucker, Flynn, Fyffe, Snavely (b92) 2018 Berretti, Daoudi, Turaga, Basu (b3) 2018; 14 Genova, K., Cole, F., Sud, A., Sarna, A., Funkhouser, T., 2020. Local deep implicit functions for 3d shape. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4857–4866. Schönberger, Zheng, Frahm, Pollefeys (b65) 2016 Pavlakos, Choutas, Ghorbani, Bolkart, Osman, Tzionas, Black (b56) 2019 Yariv, Gu, Kasten, Lipman (b80) 2021 Zhang, Liu, Ye, Zhao, Zhang, Wu, Zhang, Xu, Yu (b86) 2021; 40 Kocabas, M., Athanasiou, N., Black, M.J., 2020. Vibe: Video inference for human body pose and shape estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253–5263. Karras, T., Laine, S., Aila, T., 2019. A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410. Varol, G., Ceylan, D., Russell, B., Yang, J., Yumer, E., Laptev, I., Schmid, C., 2018. Bodynet: Volumetric inference of 3d human body shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20–36. Dou, Khamis, Degtyarev, Davidson, Fanello, Kowdle, Escolano, Rhemann, Kim, Taylor (b19) 2016 Han, Laga, Bennamoun (b27) 2019; 43 Sun, Chen, Chen, Pang, Lin, Jiang, Xu, Wang, Yu (b71) 2021 Loper, Mahmood, Romero, Pons-Moll, Black (b48) 2015; 34 Schonberger, Frahm (b64) 2016 Yu, Guibas, Wu (b81) 2021 Newcombe, Fox, Seitz (b52) 2015 Peng, Dong, Wang, Zhang, Shuai, Bao, Zhou (b58) 2021 Soltanpour, Boufama, Wu (b66) 2017; 72 Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y., 2019. Deephuman: 3d human reconstruction from a single image. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7739–7749. Zheng, E., Dunn, E., Jojic, V., Frahm, J.-M., 2014. Patchmatch based joint view selection and depthmap estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1510–1517. Bhatnagar, Sminchisescu, Theobalt, Pons-Moll (b4) 2020 Alldieck, Magnor, Xu, Theobalt, Pons-Moll (b1) 2018 He, Collomosse, Jin, Soatto (b28) 2020 Kato, H., Ushiku, Y., Harada, T., 2018. Neural 3d mesh renderer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3907–3916. Bi, Xu, Srinivasan, Mildenhall, Sunkavalli, Hašan, Hold-Geoffroy, Kriegman, Ramamoorthi (b5) 2020 Dong, J., Jiang, W., Huang, Q., Bao, H., Zhou, X., 2019. Fast and robust multi-person 3d pose estimation from multiple views. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7792–7801. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T., 2020. Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110–8119. Su, Xu, Zheng, Yu, Liu (b68) 2020 Bogo, Kanazawa, Lassner, Gehler, Romero, Black (b7) 2016 Natsume, R., Saito, S., Huang, Z., Chen, W., Ma, C., Li, H., Morishima, S., 2019. Siclope: Silhouette-based clothed people. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4480–4490. Zhu, Rematas, Curless, Seitz, Kemelmacher-Shlizerman (b93) 2020 Huang, Z., Xu, Y., Lassner, C., Li, H., Tung, T., 2020. Arch: Animatable reconstruction of clothed humans. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3093–3102. Lior, Yoni, Dror, Meirav, Matan, Ronen, Yaron (b43) 2020 Garbin, Kowalski, Johnson, Shotton, Valentin (b20) 2021 Graham, van der Maaten (b23) 2017 Park, K., Sinha, U., Barron, J.T., Bouaziz, S., Goldman, D.B., Seitz, S.M., Martin-Brualla, R., 2021. Nerfies: Deformable neural radiance fields. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5865–5874. Kolotouros, Pavlakos, Daniilidis (b40) 2019 Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F., 2021. D-nerf: Neural radiance fields for dynamic scenes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10318–10327. Suo, X., Jiang, Y., Lin, P., Zhang, Y., Wu, M., Guo, K., Xu, L., 2021. NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6226–6237. Yang, Z., Wang, S., Manivasagam, S., Huang, Z., Ma, W.-C., Yan, X., Yumer, E., Urtasun, R., 2021. S3: Neural shape, skeleton, and skinning fields for 3D human modeling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13284–13293. Hong, Y., Zhang, J., Jiang, B., Guo, Y., Liu, L., Bao, H., 2021. StereoPIFu: Depth aware clothed human digitization via stereo vision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 535–545. Park, Sinha, Hedman, Barron, Bouaziz, Goldman, Martin-Brualla, Seitz (b55) 2021 Li, Xiu, Saito, Huang, Olszewski, Li (b42) 2020 Wang, Liu, Liu, Theobalt, Komura, Wang (b75) 2021 Bi, Xu, Sunkavalli, Hašan, Hold-Geoffroy, Kriegman, Ramamoorthi (b6) 2020 Masi, Wu, Hassner, Natarajan (b49) 2018 Habermann, Xu, Zollhoefer, Pons-Moll, Theobalt (b25) 2019; 38 Niemeyer, Mescheder, Oechsle, Geiger (b53) 2020 Pavlakos, Zhu, Zhou, Daniilidis (b57) 2018 Su, Yu, Zollhoefer, Rhodin (b69) 2021 Liu, Habermann, Rudnev, Sarkar, Gu, Theobalt (b44) 2021 Chen, Tian, He (b10) 2020; 192 Habermann, M., Xu, W., Zollhofer, M., Pons-Moll, G., Theobalt, C., 2020. Deepcap: Monocular human performance capture using weak supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5052–5063. Srinivasan, P.P., Deng, B., Zhang, X., Tancik, M., Mildenhall, B., Barron, J.T., 2021. Nerv: Neural reflectance and visibility fields for relighting and view synthesis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7495–7504. Yu, Zheng, Guo, Zhao, Dai, Li, Pons-Moll, Liu (b84) 2018 Saito, S., Simon, T., Saragih, J., Joo, H., 2020. Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 84–93. Zheng, Yu, Liu, Dai (b90) 2021 Su, Yu, Zollhöfer, Rhodin (b70) 2021 Boss, Braun, Jampani, Barron, Liu, Lensch (b8) 2020 Liu, Zhang, Peng, Shi, Pollefeys, Cui (b46) 2020 Peng, S., Zhang, Y., Xu, Y., Wang, Q., Shuai, Q., Bao, H., Zhou, X., 2021. Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9054–9063. Mildenhall, Srinivasan, Tancik, Barron, Ramamoorthi, Ng (b50) 2020 Tancik, M., Mildenhall, B., Wang, T., Schmidt, D., Srinivasan, P.P., Barron, J.T., Ng, R., 2021. Learned initializations for optimizing coordinate-based neural representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2846–2855. Zhang, Y., An, L., Yu, T., Li, X., Li, K., Liu, Y., 2020. 4D association graph for realtime multi-person motion capture using multiple video cameras. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1324–1333. Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H., 2019. Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2304–2314. Guo, Lincoln, Davidson, Busch, Yu, Whalen, Harvey, Orts-Escolano, Pandey, Dourgarian (b24) 2019 Alldieck, T., Pons-Moll, G., Theobalt, C., Magnor, M., 2019. Tex2shape: Detailed full human body geometry from a single image. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2293–2303. Wang, Q., Wang, Z., Genova, K., Srinivasan, P.P., Zhou, H., Barron, J.T., Martin-Brualla, R., Snavely, N., Funkhouser, T., 2021. Ibrnet: Learning Chen (10.1016/j.visinf.2021.10.003_b10) 2020; 192 Park (10.1016/j.visinf.2021.10.003_b55) 2021 Chen (10.1016/j.visinf.2021.10.003_b11) 2021 Guo (10.1016/j.visinf.2021.10.003_b24) 2019 10.1016/j.visinf.2021.10.003_b60 10.1016/j.visinf.2021.10.003_b61 10.1016/j.visinf.2021.10.003_b62 Yu (10.1016/j.visinf.2021.10.003_b84) 2018 Lior (10.1016/j.visinf.2021.10.003_b43) 2020 10.1016/j.visinf.2021.10.003_b63 10.1016/j.visinf.2021.10.003_b21 Newcombe (10.1016/j.visinf.2021.10.003_b52) 2015 10.1016/j.visinf.2021.10.003_b22 Li (10.1016/j.visinf.2021.10.003_b42) 2020 Garbin (10.1016/j.visinf.2021.10.003_b20) 2021 10.1016/j.visinf.2021.10.003_b67 Zhu (10.1016/j.visinf.2021.10.003_b93) 2020 Graham (10.1016/j.visinf.2021.10.003_b23) 2017 10.1016/j.visinf.2021.10.003_b26 Loper (10.1016/j.visinf.2021.10.003_b48) 2015; 34 Debevec (10.1016/j.visinf.2021.10.003_b14) 2000 10.1016/j.visinf.2021.10.003_b29 Xiang (10.1016/j.visinf.2021.10.003_b77) 2021 Yu (10.1016/j.visinf.2021.10.003_b81) 2021 Zheng (10.1016/j.visinf.2021.10.003_b89) 2021 Desmarais (10.1016/j.visinf.2021.10.003_b16) 2021 Bi (10.1016/j.visinf.2021.10.003_b6) 2020 10.1016/j.visinf.2021.10.003_b2 Kanazawa (10.1016/j.visinf.2021.10.003_b34) 2018 10.1016/j.visinf.2021.10.003_b9 Yariv (10.1016/j.visinf.2021.10.003_b80) 2021 Su (10.1016/j.visinf.2021.10.003_b70) 2021 10.1016/j.visinf.2021.10.003_b72 Zhou (10.1016/j.visinf.2021.10.003_b92) 2018 10.1016/j.visinf.2021.10.003_b73 10.1016/j.visinf.2021.10.003_b30 10.1016/j.visinf.2021.10.003_b74 10.1016/j.visinf.2021.10.003_b31 Yu (10.1016/j.visinf.2021.10.003_b82) 2021 10.1016/j.visinf.2021.10.003_b76 10.1016/j.visinf.2021.10.003_b35 10.1016/j.visinf.2021.10.003_b79 10.1016/j.visinf.2021.10.003_b36 10.1016/j.visinf.2021.10.003_b37 10.1016/j.visinf.2021.10.003_b38 10.1016/j.visinf.2021.10.003_b39 Su (10.1016/j.visinf.2021.10.003_b69) 2021 Jiang (10.1016/j.visinf.2021.10.003_b32) 2020 Mildenhall (10.1016/j.visinf.2021.10.003_b50) 2020 Masi (10.1016/j.visinf.2021.10.003_b49) 2018 Sun (10.1016/j.visinf.2021.10.003_b71) 2021 Zheng (10.1016/j.visinf.2021.10.003_b90) 2021 Deng (10.1016/j.visinf.2021.10.003_b15) 2020 10.1016/j.visinf.2021.10.003_b83 10.1016/j.visinf.2021.10.003_b41 10.1016/j.visinf.2021.10.003_b85 Joo (10.1016/j.visinf.2021.10.003_b33) 2018 10.1016/j.visinf.2021.10.003_b88 Alldieck (10.1016/j.visinf.2021.10.003_b1) 2018 10.1016/j.visinf.2021.10.003_b45 Lombardi (10.1016/j.visinf.2021.10.003_b47) 2019 Han (10.1016/j.visinf.2021.10.003_b27) 2019; 43 Collet (10.1016/j.visinf.2021.10.003_b13) 2015 Boss (10.1016/j.visinf.2021.10.003_b8) 2020 Bhatnagar (10.1016/j.visinf.2021.10.003_b4) 2020 Su (10.1016/j.visinf.2021.10.003_b68) 2020 Bogo (10.1016/j.visinf.2021.10.003_b7) 2016 Niemeyer (10.1016/j.visinf.2021.10.003_b53) 2020 Dong (10.1016/j.visinf.2021.10.003_b18) 2020 Pavlakos (10.1016/j.visinf.2021.10.003_b56) 2019 Berretti (10.1016/j.visinf.2021.10.003_b3) 2018; 14 Schonberger (10.1016/j.visinf.2021.10.003_b64) 2016 Wang (10.1016/j.visinf.2021.10.003_b75) 2021 He (10.1016/j.visinf.2021.10.003_b28) 2020 Xu (10.1016/j.visinf.2021.10.003_b78) 2018; 37 Liu (10.1016/j.visinf.2021.10.003_b44) 2021 10.1016/j.visinf.2021.10.003_b91 10.1016/j.visinf.2021.10.003_b51 Liu (10.1016/j.visinf.2021.10.003_b46) 2020 10.1016/j.visinf.2021.10.003_b54 Peng (10.1016/j.visinf.2021.10.003_b58) 2021 Zhang (10.1016/j.visinf.2021.10.003_b87) 2021 Zhang (10.1016/j.visinf.2021.10.003_b86) 2021; 40 10.1016/j.visinf.2021.10.003_b12 Habermann (10.1016/j.visinf.2021.10.003_b25) 2019; 38 Soltanpour (10.1016/j.visinf.2021.10.003_b66) 2017; 72 10.1016/j.visinf.2021.10.003_b59 10.1016/j.visinf.2021.10.003_b17 Pavlakos (10.1016/j.visinf.2021.10.003_b57) 2018 Dou (10.1016/j.visinf.2021.10.003_b19) 2016 Kolotouros (10.1016/j.visinf.2021.10.003_b40) 2019 Bi (10.1016/j.visinf.2021.10.003_b5) 2020 Schönberger (10.1016/j.visinf.2021.10.003_b65) 2016 |
| References_xml | – reference: Tancik, M., Mildenhall, B., Wang, T., Schmidt, D., Srinivasan, P.P., Barron, J.T., Ng, R., 2021. Learned initializations for optimizing coordinate-based neural representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2846–2855. – year: 2017 ident: b23 article-title: Submanifold sparse convolutional networks – reference: Habermann, M., Xu, W., Zollhofer, M., Pons-Moll, G., Theobalt, C., 2020. Deepcap: Monocular human performance capture using weak supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5052–5063. – reference: Genova, K., Cole, F., Sud, A., Sarna, A., Funkhouser, T., 2020. Local deep implicit functions for 3d shape. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4857–4866. – volume: 43 start-page: 1578 year: 2019 end-page: 1604 ident: b27 article-title: Image-based 3D object reconstruction: State-of-the-art and trends in the deep learning era publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Gilbert, A., Volino, M., Collomosse, J., Hilton, A., 2018. Volumetric performance capture from minimal camera viewpoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 566–581. – reference: Huang, Z., Li, T., Chen, W., Zhao, Y., Xing, J., LeGendre, C., Luo, L., Ma, C., Li, H., 2018. Deep volumetric video from very sparse multi-view performance capture. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 336–354. – reference: Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y., 2019. Deephuman: 3d human reconstruction from a single image. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7739–7749. – volume: 192 year: 2020 ident: b10 article-title: Monocular human pose estimation: A survey of deep learning-based methods publication-title: Comput. Vis. Image Underst. – start-page: 471 year: 2018 end-page: 478 ident: b49 article-title: Deep face recognition: A survey publication-title: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) – year: 2021 ident: b70 article-title: A-nerf: A-nerf: Articulated neural radiance fields for learning human shape, appearance, and pose publication-title: Advances in Neural Information Processing Systems – start-page: 49 year: 2020 end-page: 67 ident: b42 article-title: Monocular real-time volumetric performance capture publication-title: European Conference on Computer Vision – reference: Park, K., Sinha, U., Barron, J.T., Bouaziz, S., Goldman, D.B., Seitz, S.M., Martin-Brualla, R., 2021. Nerfies: Deformable neural radiance fields. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5865–5874. – reference: Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J., 2019. Learning 3d human dynamics from video. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5614–5623. – start-page: 294 year: 2020 end-page: 311 ident: b6 article-title: Deep reflectance volumes: Relightable reconstructions from multi-view photometric images publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16 – year: 2015 ident: b52 article-title: Dynamicfusion: Reconstruction and tracking of non-rigid scenes in real-time publication-title: CVPR – year: 2019 ident: b56 article-title: Expressive body capture: 3D hands, face, and body from a single image publication-title: CVPR – reference: Saito, S., Yang, J., Ma, Q., Black, M.J., 2021. SCANimate: Weakly supervised learning of skinned clothed avatar networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2886–2897. – year: 2018 ident: b33 article-title: Total capture: A 3d deformation model for tracking faces, hands, and bodies publication-title: CVPR – start-page: 98 year: 2018 end-page: 109 ident: b1 article-title: Detailed human avatars from monocular video publication-title: 2018 International Conference on 3D Vision (3DV) – reference: Yu, A., Ye, V., Tancik, M., Kanazawa, A., 2021. pixelnerf: Neural radiance fields from one or few images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578–4587. – year: 2016 ident: b65 article-title: Pixelwise view selection for unstructured multi-view stereo publication-title: ECCV – year: 2021 ident: b81 article-title: Unsupervised discovery of object radiance fields – year: 2021 ident: b20 article-title: Fastnerf: High-fidelity neural rendering at 200fps – year: 2021 ident: b44 article-title: Neural actor: Neural free-view synthesis of human actors with pose control – volume: 37 start-page: 1 year: 2018 end-page: 15 ident: b78 article-title: Monoperfcap: Human performance capture from monocular video publication-title: ACM Trans. Graphics (ToG) – volume: 14 year: 2018 ident: b3 article-title: Representation, analysis, and recognition of 3D humans: A survey publication-title: ACM Trans. Multimedia Comput. Commun. Appl. – reference: Varol, G., Ceylan, D., Russell, B., Yang, J., Yumer, E., Laptev, I., Schmid, C., 2018. Bodynet: Volumetric inference of 3d human body shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20–36. – reference: Bozic, A., Palafox, P., Zollhofer, M., Thies, J., Dai, A., Nieß ner, M., 2021. Neural deformation graphs for globally-consistent non-rigid reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1450–1459. – year: 2021 ident: b16 article-title: A review of 3D human pose estimation algorithms for markerless motion capture publication-title: Comput. Vis. Image Underst. – year: 2020 ident: b46 article-title: Dist: Rendering deep implicit signed distance function with differentiable sphere tracing publication-title: CVPR – reference: Zhang, Y., An, L., Yu, T., Li, X., Li, K., Liu, Y., 2020. 4D association graph for realtime multi-person motion capture using multiple video cameras. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1324–1333. – year: 2020 ident: b18 article-title: Motion capture from internet videos publication-title: ECCV – reference: Natsume, R., Saito, S., Huang, Z., Chen, W., Ma, C., Li, H., Morishima, S., 2019. Siclope: Silhouette-based clothed people. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4480–4490. – reference: Kocabas, M., Athanasiou, N., Black, M.J., 2020. Vibe: Video inference for human body pose and shape estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253–5263. – year: 2020 ident: b32 article-title: Coherent reconstruction of multiple humans from a single image publication-title: CVPR – reference: Chibane, J., Alldieck, T., Pons-Moll, G., 2020. Implicit functions in feature space for 3d shape reconstruction and completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6970–6981. – reference: Alldieck, T., Pons-Moll, G., Theobalt, C., Magnor, M., 2019. Tex2shape: Detailed full human body geometry from a single image. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2293–2303. – reference: Hong, Y., Zhang, J., Jiang, B., Guo, Y., Liu, L., Bao, H., 2021. StereoPIFu: Depth aware clothed human digitization via stereo vision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 535–545. – year: 2018 ident: b34 article-title: End-to-end recovery of human shape and pose publication-title: CVPR – reference: Karras, T., Laine, S., Aila, T., 2019. A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410. – reference: Wang, Q., Wang, Z., Genova, K., Srinivasan, P.P., Zhou, H., Barron, J.T., Martin-Brualla, R., Snavely, N., Funkhouser, T., 2021. Ibrnet: Learning multi-view image-based rendering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690–4699. – start-page: 561 year: 2016 end-page: 578 ident: b7 article-title: Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image publication-title: European Conference on Computer Vision – start-page: 612 year: 2020 end-page: 628 ident: b15 article-title: Nasa neural articulated shape approximation publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VII 16 – reference: Peng, S., Zhang, Y., Xu, Y., Wang, Q., Shuai, Q., Bao, H., Zhou, X., 2021. Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9054–9063. – reference: Srinivasan, P.P., Deng, B., Zhang, X., Tancik, M., Mildenhall, B., Barron, J.T., 2021. Nerv: Neural reflectance and visibility fields for relighting and view synthesis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7495–7504. – year: 2020 ident: b8 article-title: Nerd: Neural reflectance decomposition from image collections – year: 2021 ident: b71 article-title: Neural free-viewpoint performance rendering under ComplexHuman-object interactions – volume: 40 start-page: 1 year: 2021 end-page: 18 ident: b86 article-title: Editable free-viewpoint video using a layered neural representation publication-title: ACM Trans. Graph. – year: 2021 ident: b55 article-title: Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields – year: 2019 ident: b24 article-title: The relightables: Volumetric performance capture of humans with realistic relighting publication-title: ACM TOG – reference: Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F., 2021. D-nerf: Neural radiance fields for dynamic scenes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10318–10327. – reference: Kato, H., Ushiku, Y., Harada, T., 2018. Neural 3d mesh renderer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3907–3916. – year: 2021 ident: b82 article-title: Plenoctrees for real-time rendering of neural radiance fields – year: 2020 ident: b68 article-title: Robustfusion: Human volumetric capture with data-driven visual cues using a RGBD camera publication-title: ECCV – year: 2018 ident: b84 article-title: Doublefusion: Real-time capture of human performances with inner body shapes from a single depth sensor publication-title: CVPR – year: 2000 ident: b14 article-title: Acquiring the reflectance field of a human face publication-title: SIGGRAPH – year: 2016 ident: b19 article-title: Fusion4d: Real-time performance capture of challenging scenes publication-title: ACM TOG – year: 2018 ident: b92 article-title: Stereo magnification: Learning view synthesis using multiplane images – reference: Huang, Z., Xu, Y., Lassner, C., Li, H., Tung, T., 2020. Arch: Animatable reconstruction of clothed humans. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3093–3102. – volume: 38 start-page: 1 year: 2019 end-page: 17 ident: b25 article-title: Livecap: Real-time human performance capture from monocular video publication-title: ACM Trans. Graph. – year: 2021 ident: b77 article-title: Explicit clothing modeling for an animatable full-body avatar – reference: Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T., 2020. Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110–8119. – reference: Dong, J., Jiang, W., Huang, Q., Bao, H., Zhou, X., 2019. Fast and robust multi-person 3d pose estimation from multiple views. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7792–7801. – year: 2019 ident: b40 article-title: Convolutional mesh regression for single-image human shape reconstruction publication-title: CVPR – year: 2020 ident: b28 article-title: Geo-pifu: Geometry and pixel aligned implicit functions for single-view human reconstruction – reference: Saito, S., Simon, T., Saragih, J., Joo, H., 2020. Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 84–93. – reference: Liu, S., Li, T., Chen, W., Li, H., 2019. Soft rasterizer: A differentiable renderer for image-based 3d reasoning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7708–7717. – year: 2021 ident: b89 article-title: Deepmulticap: Performance capture of multiple characters using sparse multiview cameras – reference: Suo, X., Jiang, Y., Lin, P., Zhang, Y., Wu, M., Guo, K., Xu, L., 2021. NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6226–6237. – year: 2021 ident: b75 article-title: Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction – year: 2021 ident: b69 article-title: A-nerf: Surface-free human 3D pose refinement via neural rendering – year: 2021 ident: b87 article-title: Nerfactor: Neural factorization of shape and reflectance under an unknown illumination – start-page: 177 year: 2020 end-page: 194 ident: b93 article-title: Reconstructing nba players publication-title: European Conference on Computer Vision – year: 2020 ident: b50 article-title: Nerf: Representing scenes as neural radiance fields for view synthesis publication-title: ECCV – reference: Yang, Z., Wang, S., Manivasagam, S., Huang, Z., Ma, W.-C., Yan, X., Yumer, E., Urtasun, R., 2021. S3: Neural shape, skeleton, and skinning fields for 3D human modeling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13284–13293. – volume: 34 start-page: 1 year: 2015 end-page: 16 ident: b48 article-title: Smpl: A skinned multi-person linear model publication-title: ACM Trans. Graph. – year: 2021 ident: b11 article-title: Snarf: Differentiable forward skinning for animating non-rigid neural implicit shapes – year: 2020 ident: b43 article-title: Multiview neural surface reconstruction by disentangling geometry and appearance publication-title: NeurIPS – year: 2015 ident: b13 article-title: High-quality streamable free-viewpoint video publication-title: ACM TOG – year: 2020 ident: b53 article-title: Differentiable volumetric rendering: Learning implicit 3d representations without 3d supervision publication-title: CVPR – year: 2021 ident: b80 article-title: Volume rendering of neural implicit surfaces – volume: 72 start-page: 391 year: 2017 end-page: 406 ident: b66 article-title: A survey of local feature methods for 3D face recognition publication-title: Pattern Recognit. – year: 2019 ident: b47 article-title: Neural volumes: Learning dynamic renderable volumes from images publication-title: SIGGRAPH – year: 2021 ident: b58 article-title: Animatable neural radiance fields for human body modeling publication-title: ICCV – start-page: 311 year: 2020 end-page: 329 ident: b4 article-title: Combining implicit function learning and parametric models for 3d human reconstruction publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16 – year: 2021 ident: b90 article-title: Pamir: Parametric model-conditioned implicit representation for image-based human reconstruction publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2016 ident: b64 article-title: Structure-from-motion revisited publication-title: CVPR – reference: Li, Z., Niklaus, S., Snavely, N., Wang, O., 2021. Neural scene flow fields for space-time view synthesis of dynamic scenes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6498–6508. – year: 2020 ident: b5 article-title: Neural reflectance fields for appearance acquisition – reference: Zheng, E., Dunn, E., Jojic, V., Frahm, J.-M., 2014. Patchmatch based joint view selection and depthmap estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1510–1517. – year: 2018 ident: b57 article-title: Learning to estimate 3D human pose and shape from a single color image publication-title: CVPR – reference: Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H., 2019. Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2304–2314. – ident: 10.1016/j.visinf.2021.10.003_b60 doi: 10.1109/CVPR46437.2021.01018 – ident: 10.1016/j.visinf.2021.10.003_b38 doi: 10.1109/CVPR.2018.00411 – year: 2019 ident: 10.1016/j.visinf.2021.10.003_b47 article-title: Neural volumes: Learning dynamic renderable volumes from images – start-page: 612 year: 2020 ident: 10.1016/j.visinf.2021.10.003_b15 article-title: Nasa neural articulated shape approximation – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b81 – ident: 10.1016/j.visinf.2021.10.003_b17 doi: 10.1109/CVPR.2019.00798 – year: 2018 ident: 10.1016/j.visinf.2021.10.003_b34 article-title: End-to-end recovery of human shape and pose – start-page: 49 year: 2020 ident: 10.1016/j.visinf.2021.10.003_b42 article-title: Monocular real-time volumetric performance capture – year: 2019 ident: 10.1016/j.visinf.2021.10.003_b24 article-title: The relightables: Volumetric performance capture of humans with realistic relighting publication-title: ACM TOG doi: 10.1145/3355089.3356571 – ident: 10.1016/j.visinf.2021.10.003_b59 doi: 10.1109/CVPR46437.2021.00894 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b69 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b89 – volume: 43 start-page: 1578 issue: 5 year: 2019 ident: 10.1016/j.visinf.2021.10.003_b27 article-title: Image-based 3D object reconstruction: State-of-the-art and trends in the deep learning era publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2019.2954885 – ident: 10.1016/j.visinf.2021.10.003_b37 doi: 10.1109/CVPR42600.2020.00813 – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b53 article-title: Differentiable volumetric rendering: Learning implicit 3d representations without 3d supervision – year: 2017 ident: 10.1016/j.visinf.2021.10.003_b23 – ident: 10.1016/j.visinf.2021.10.003_b76 doi: 10.1109/CVPR46437.2021.00466 – ident: 10.1016/j.visinf.2021.10.003_b51 doi: 10.1109/CVPR.2019.00461 – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b46 article-title: Dist: Rendering deep implicit signed distance function with differentiable sphere tracing – ident: 10.1016/j.visinf.2021.10.003_b39 doi: 10.1109/CVPR42600.2020.00530 – ident: 10.1016/j.visinf.2021.10.003_b74 doi: 10.1007/978-3-030-01234-2_2 – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b43 article-title: Multiview neural surface reconstruction by disentangling geometry and appearance – year: 2019 ident: 10.1016/j.visinf.2021.10.003_b56 article-title: Expressive body capture: 3D hands, face, and body from a single image – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b90 article-title: Pamir: Parametric model-conditioned implicit representation for image-based human reconstruction publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – ident: 10.1016/j.visinf.2021.10.003_b67 doi: 10.1109/CVPR46437.2021.00741 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b80 – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b5 – ident: 10.1016/j.visinf.2021.10.003_b62 doi: 10.1109/CVPR42600.2020.00016 – ident: 10.1016/j.visinf.2021.10.003_b9 doi: 10.1109/CVPR46437.2021.00150 – year: 2016 ident: 10.1016/j.visinf.2021.10.003_b65 article-title: Pixelwise view selection for unstructured multi-view stereo – start-page: 177 year: 2020 ident: 10.1016/j.visinf.2021.10.003_b93 article-title: Reconstructing nba players – ident: 10.1016/j.visinf.2021.10.003_b85 doi: 10.1109/CVPR42600.2020.00140 – ident: 10.1016/j.visinf.2021.10.003_b36 doi: 10.1109/CVPR.2019.00453 – ident: 10.1016/j.visinf.2021.10.003_b72 doi: 10.1109/CVPR46437.2021.00616 – year: 2018 ident: 10.1016/j.visinf.2021.10.003_b33 article-title: Total capture: A 3d deformation model for tracking faces, hands, and bodies – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b82 – year: 2000 ident: 10.1016/j.visinf.2021.10.003_b14 article-title: Acquiring the reflectance field of a human face – ident: 10.1016/j.visinf.2021.10.003_b88 doi: 10.1109/CVPR.2014.196 – volume: 192 year: 2020 ident: 10.1016/j.visinf.2021.10.003_b10 article-title: Monocular human pose estimation: A survey of deep learning-based methods publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2019.102897 – ident: 10.1016/j.visinf.2021.10.003_b26 doi: 10.1109/CVPR42600.2020.00510 – year: 2018 ident: 10.1016/j.visinf.2021.10.003_b92 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b55 – start-page: 471 year: 2018 ident: 10.1016/j.visinf.2021.10.003_b49 article-title: Deep face recognition: A survey – ident: 10.1016/j.visinf.2021.10.003_b63 doi: 10.1109/CVPR46437.2021.00291 – volume: 34 start-page: 1 issue: 6 year: 2015 ident: 10.1016/j.visinf.2021.10.003_b48 article-title: Smpl: A skinned multi-person linear model publication-title: ACM Trans. Graph. doi: 10.1145/2816795.2818013 – start-page: 98 year: 2018 ident: 10.1016/j.visinf.2021.10.003_b1 article-title: Detailed human avatars from monocular video – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b68 article-title: Robustfusion: Human volumetric capture with data-driven visual cues using a RGBD camera – ident: 10.1016/j.visinf.2021.10.003_b22 doi: 10.1007/978-3-030-01252-6_35 – start-page: 561 year: 2016 ident: 10.1016/j.visinf.2021.10.003_b7 article-title: Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b50 article-title: Nerf: Representing scenes as neural radiance fields for view synthesis – ident: 10.1016/j.visinf.2021.10.003_b73 doi: 10.1109/CVPR46437.2021.00287 – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b18 article-title: Motion capture from internet videos – year: 2018 ident: 10.1016/j.visinf.2021.10.003_b84 article-title: Doublefusion: Real-time capture of human performances with inner body shapes from a single depth sensor – ident: 10.1016/j.visinf.2021.10.003_b35 doi: 10.1109/CVPR.2019.00576 – ident: 10.1016/j.visinf.2021.10.003_b54 doi: 10.1109/ICCV48922.2021.00581 – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b28 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b71 – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b32 article-title: Coherent reconstruction of multiple humans from a single image – ident: 10.1016/j.visinf.2021.10.003_b79 doi: 10.1109/CVPR46437.2021.01308 – ident: 10.1016/j.visinf.2021.10.003_b12 doi: 10.1109/CVPR42600.2020.00700 – volume: 40 start-page: 1 issue: 4 year: 2021 ident: 10.1016/j.visinf.2021.10.003_b86 article-title: Editable free-viewpoint video using a layered neural representation publication-title: ACM Trans. Graph. doi: 10.1145/3450626.3459783 – ident: 10.1016/j.visinf.2021.10.003_b30 doi: 10.1007/978-3-030-01270-0_21 – ident: 10.1016/j.visinf.2021.10.003_b29 doi: 10.1109/CVPR46437.2021.00060 – volume: 37 start-page: 1 issue: 2 year: 2018 ident: 10.1016/j.visinf.2021.10.003_b78 article-title: Monoperfcap: Human performance capture from monocular video publication-title: ACM Trans. Graphics (ToG) doi: 10.1145/3181973 – ident: 10.1016/j.visinf.2021.10.003_b83 doi: 10.1109/CVPR46437.2021.00455 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b87 – ident: 10.1016/j.visinf.2021.10.003_b45 doi: 10.1109/ICCV.2019.00780 – ident: 10.1016/j.visinf.2021.10.003_b61 doi: 10.1109/ICCV.2019.00239 – start-page: 294 year: 2020 ident: 10.1016/j.visinf.2021.10.003_b6 article-title: Deep reflectance volumes: Relightable reconstructions from multi-view photometric images – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b77 – year: 2015 ident: 10.1016/j.visinf.2021.10.003_b13 article-title: High-quality streamable free-viewpoint video publication-title: ACM TOG doi: 10.1145/2766945 – ident: 10.1016/j.visinf.2021.10.003_b41 doi: 10.1109/CVPR46437.2021.00643 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b11 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b20 – year: 2018 ident: 10.1016/j.visinf.2021.10.003_b57 article-title: Learning to estimate 3D human pose and shape from a single color image – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b44 – volume: 14 issue: 1s year: 2018 ident: 10.1016/j.visinf.2021.10.003_b3 article-title: Representation, analysis, and recognition of 3D humans: A survey publication-title: ACM Trans. Multimedia Comput. Commun. Appl. – ident: 10.1016/j.visinf.2021.10.003_b31 doi: 10.1109/CVPR42600.2020.00316 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b58 article-title: Animatable neural radiance fields for human body modeling – year: 2020 ident: 10.1016/j.visinf.2021.10.003_b8 – year: 2016 ident: 10.1016/j.visinf.2021.10.003_b64 article-title: Structure-from-motion revisited – volume: 72 start-page: 391 year: 2017 ident: 10.1016/j.visinf.2021.10.003_b66 article-title: A survey of local feature methods for 3D face recognition publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.08.003 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b16 article-title: A review of 3D human pose estimation algorithms for markerless motion capture publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2021.103275 – year: 2015 ident: 10.1016/j.visinf.2021.10.003_b52 article-title: Dynamicfusion: Reconstruction and tracking of non-rigid scenes in real-time – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b70 article-title: A-nerf: A-nerf: Articulated neural radiance fields for learning human shape, appearance, and pose – ident: 10.1016/j.visinf.2021.10.003_b91 doi: 10.1109/ICCV.2019.00783 – ident: 10.1016/j.visinf.2021.10.003_b2 doi: 10.1109/ICCV.2019.00238 – volume: 38 start-page: 1 issue: 2 year: 2019 ident: 10.1016/j.visinf.2021.10.003_b25 article-title: Livecap: Real-time human performance capture from monocular video publication-title: ACM Trans. Graph. doi: 10.1145/3311970 – year: 2021 ident: 10.1016/j.visinf.2021.10.003_b75 – start-page: 311 year: 2020 ident: 10.1016/j.visinf.2021.10.003_b4 article-title: Combining implicit function learning and parametric models for 3d human reconstruction – year: 2016 ident: 10.1016/j.visinf.2021.10.003_b19 article-title: Fusion4d: Real-time performance capture of challenging scenes publication-title: ACM TOG doi: 10.1145/2897824.2925969 – ident: 10.1016/j.visinf.2021.10.003_b21 doi: 10.1109/CVPR42600.2020.00491 – year: 2019 ident: 10.1016/j.visinf.2021.10.003_b40 article-title: Convolutional mesh regression for single-image human shape reconstruction |
| SSID | ssj0002810111 |
| Score | 2.3147945 |
| SecondaryResourceType | review_article |
| Snippet | Reconstructing 3D digital models of humans from sensory data is a long-standing problem in computer vision and graphics with a variety of applications in... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 11 |
| SubjectTerms | 3D human reconstruction Differentiable rendering Neural representation |
| Title | Towards efficient and photorealistic 3D human reconstruction: A brief survey |
| URI | https://dx.doi.org/10.1016/j.visinf.2021.10.003 https://doaj.org/article/8fedf2af48b443eeb954bfb07969c3fc |
| Volume | 5 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELYQEwsCAaK85IE10DhO4rCVR1UhYGqlbpEfZ0GF0ooWJP49d05ShYUujLEcOzmf_d0ld98xdpnhkZeqrIgK4_JIAq6FdiAjEPSPS1phHOUOP79ko4l8nKbTTqkvigmr6YFrwV0rD84L7aUyUiYApkil8aafF1lhE2_p9EXM6zhTs_DJKKYi6lRZLqQW9cW0zZsLwV2UuF0Rg6eIr0JwV_ILlwJ9fweeOpAz3GO7ja3IB_Uz7rMtqA7Y0zgEui45BPIHxAyuK8cXr3P0noHoDLE3T-55qL7Hg8O7Jom94QNu0Dn2fPn58QXfh2wyfBjfjaKmJEJkZaxWUS4zn3ptCjQjPAgjnLH49t4hrOcOd6dVeAHO9CGxmXTa4abNKUEaYd6haXfEtqt5BceMe0VsYgbiJFNSW6HxsXOpdBw7A9K6HktagZS24QunshXvZRsYNitrMZYkRmpFMfZYtL5rUfNlbOh_S7Je9yW269CAOlA2OlBu0oEey9uVKhvDoTYIcKi3P6c_-Y_pT9kODVkHuZyxbVxTOEdTZWUuglb-ACVu6Es |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Towards+efficient+and+photorealistic+3D+human+reconstruction%3A+A+brief+survey&rft.jtitle=Visual+informatics+%28Online%29&rft.au=Chen%2C+Lu&rft.au=Peng%2C+Sida&rft.au=Zhou%2C+Xiaowei&rft.date=2021-12-01&rft.pub=Elsevier+B.V&rft.issn=2468-502X&rft.eissn=2468-502X&rft.volume=5&rft.issue=4&rft.spage=11&rft.epage=19&rft_id=info:doi/10.1016%2Fj.visinf.2021.10.003&rft.externalDocID=S2468502X21000413 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2468-502X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2468-502X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2468-502X&client=summon |