{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:15:05Z","timestamp":1791911705225,"version":"4.3.4"},"publisher-location":"Cham","reference-count":78,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732195","type":"print"},{"value":"9783031732201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73220-1_25","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:05:14Z","timestamp":1730577914000},"page":"429-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["HSR: Holistic 3D Human-Scene Reconstruction from\u00a0Monocular Videos"],"prefix":"10.1007","author":[{"given":"Lixin","family":"Xue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengwei","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangjinghua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjian","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsuan-I","family":"Ho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manuel","family":"Kaufmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Otmar","family":"Hilliges","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Xu, W., Theobalt, C., Pons-Moll, G.: Video based reconstruction of 3D people models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8387\u20138397 (2018)","DOI":"10.1109\/CVPR.2018.00875"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Zanfir, M., Sminchisescu, C.: Photorealistic monocular 3D reconstruction of humans wearing clothing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Ara\u00fajo, J.P., et al.: Circle: capture in rich contextual environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21211\u201321221 (2023)","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: MIP-NeRF 360: unbounded anti-aliased neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Xie, X., Petrov, I., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Behave: dataset and method for tracking human object interactions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"25_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"25_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-58452-8_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Cao","year":"2020","unstructured":"Cao, Z., Gao, H., Mangalam, K., Cai, Q.-Z., Vo, M., Malik, J.: Long-term human motion prediction with scene context. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 387\u2013404. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_23"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Casado-Elvira, A., Comino\u00a0Trinidad, M., Casas, D.: PERGAMO: personalized 3D garments from monocular video. In: Computer Graphics Forum (Proceedings of SCA) (2022)","DOI":"10.1111\/cgf.14644"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: Deep stereo using adaptive thin volume representation with uncertainty awareness. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Collet, A., et al.: High-quality streamable free-viewpoint video. ACM Trans. Graph. 34(4) (2015). https:\/\/doi.org\/10.1145\/2766945","DOI":"10.1145\/2766945"},{"key":"25_CR11","unstructured":"Community, B.O.: Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam (2018). http:\/\/www.blender.org"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Dai, Y., et al.: HSC4D: human-centered 4D scene capture in large-scale indoor-outdoor space using wearable IMUs and lidar. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6792\u20136802 (2022)","DOI":"10.1109\/CVPR52688.2022.00667"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Darmon, F., Bascle, B., Devaux, J.C., Monasse, P., Aubry, M.: Improving neural implicit surfaces geometry with patch warping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6260\u20136269 (2022)","DOI":"10.1109\/CVPR52688.2022.00616"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Eftekhar, A., Sax, A., Malik, J., Zamir, A.: Omnidata: a scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10786\u201310796 (2021)","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Feng, Q., Liu, Y., Lai, Y.K., Yang, J., Li, K.: FOF: learning Fourier occupancy field for monocular real-time human reconstruction. In: NeurIPS (2022)","DOI":"10.1007\/978-3-031-20503-3_54"},{"key":"25_CR16","unstructured":"Fu, Q., Xu, Q., Ong, Y.S., Tao, W.: Geo-Neus: geometry-consistent neural implicit surfaces learning for multi-view reconstruction. arXiv preprint arXiv:2205.15848 (2022)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Galliani, S., Lasinger, K., Schindler, K.: Massively parallel multiview stereopsis by surface normal diffusion. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.106"},{"key":"25_CR18","unstructured":"Gropp, A., Yariv, L., Haim, N., Atzmon, M., Lipman, Y.: Implicit geometric regularization for learning shapes. arXiv preprint arXiv:2002.10099 (2020)"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2495\u20132504 (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Guo, C., Chen, X., Song, J., Hilliges, O.: Human performance capture from monocular video in the wild. In: 2021 International Conference on 3D Vision (3DV), pp. 889\u2013898. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00097"},{"key":"25_CR21","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12858\u201312868 (2023)","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Guzov, V., et al.: Interaction replica: tracking human-object interaction and scene changes from human motion. In: International Conference on 3D Vision (3DV) (2024)","DOI":"10.1109\/3DV62453.2024.00072"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Guzov, V., Mir, A., Sattler, T., Pons-Moll, G.: Human poseitioning system (HPS): 3D human pose estimation and self-localization in large scenes from body-mounted sensors. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Habermann, M., Xu, W., Zollhoefer, M., Pons-Moll, G., Theobalt, C.: Deepcap: monocular human performance capture using weak supervision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00510"},{"key":"25_CR25","doi-asserted-by":"publisher","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) (2019). https:\/\/doi.org\/10.1145\/3311970","DOI":"10.1145\/3311970"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3D human pose ambiguities with 3D scene constraints. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00237"},{"key":"25_CR27","unstructured":"He, T., Collomosse, J., Jin, H., Soatto, S.: Geo-PIFu: Geometry and pixel aligned implicit functions for single-view human reconstruction. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 9276\u20139287. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/690f44c8c2b7ded579d01abe8fdb6110-Paper.pdf"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"He, T., Xu, Y., Saito, S., Soatto, S., Tung, T.: ARCH++: animation-ready clothed human reconstruction revisited. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11046\u201311056 (2021)","DOI":"10.1109\/ICCV48922.2021.01086"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Ho, H.I., Song, J., Hilliges, O.: SiTH: single-view textured human reconstruction with image-conditioned diffusion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Huang, C.H.P., et al.: Capturing and inferring dense full-body human-scene contact. In: IEEE\/CVF Conference\u00a0on Computer Vision and Pattern Recognition (CVPR), pp. 13274\u201313285 (2022)","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"25_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01984-1","author":"Y Huang","year":"2024","unstructured":"Huang, Y., Taheri, O., Black, M.J., Tzionas, D.: InterCap: joint markerless 3D tracking of humans and objects in interaction from multi-view RGB-D images. Int. J. Comput. Vis. (IJCV) (2024). https:\/\/doi.org\/10.1007\/s11263-024-01984-1","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Huang, Z., Xu, Y., Lassner, C., Li, H., Tung, T.: Arch: animatable reconstruction of clothed humans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3093\u20133102 (2020)","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Jiang, B., Hong, Y., Bao, H., Zhang, J.: SelfRecon: self reconstruction your digital avatar from monocular video. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00552"},{"key":"25_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-031-19824-3_24","volume-title":"ECCV 2022","author":"W Jiang","year":"2022","unstructured":"Jiang, W., Yi, K.M., Samei, G., Tuzel, O., Ranjan, A.: NeuMan: neural human radiance field from a single video. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 402\u2013412. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_24"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Jiang, Z., et al.: Multiply: reconstruction of multiple people from monocular video in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00019"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Kaufmann, M., et al.: EMDB: the electromagnetic database of global 3D human pose and shape in the wild. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01345"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: PARE: part attention regressor for 3d human body estimation. In: Proceedings International Conference on Computer Vision (ICCV), pp. 11127\u201311137. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Li, Z., Shimada, S., Schiele, B., Theobalt, C., Golyanik, V.: MoCapDeform: monocular 3D human motion capture in deformable scenes. In: International Conference on 3D Vision (3DV) (2022)","DOI":"10.1109\/3DV57658.2022.00013"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Lin, W., Zheng, C., Yong, J.H., Xu, F.: Relightable and animatable neural avatars from videos. In: Proceedings of the AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i4.28136"},{"key":"25_CR40","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-031-19824-3_13","volume-title":"ECCV 2022","author":"X Long","year":"2022","unstructured":"Long, X., Lin, C., Wang, P., Komura, T., Wang, W.: SparseNeuS: fast generalizable neural surface reconstruction from sparse views. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 210\u2013227. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_13"},{"issue":"6","key":"25_CR41","doi-asserted-by":"publisher","first-page":"1","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. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Ma, X., Gong, Y., Wang, Q., Huang, J., Chen, L., Yu, F.: EPP-MVSNet: epipolar-assembling based depth prediction for multi-view stereo. In: ICCV, pp. 5732\u20135740 (2021)","DOI":"10.1109\/ICCV48922.2021.00568"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"25_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","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: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"issue":"4","key":"25_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322961","volume":"38","author":"A Monszpart","year":"2019","unstructured":"Monszpart, A., Guerrero, P., Ceylan, D., Yumer, E., Mitra, N.J.: iMapper: interaction-guided scene mapping from monocular videos. ACM Trans. Graph. (TOG) 38(4), 1\u201315 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR46","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/978-3-031-20086-1_11","volume-title":"ECCV 2022","author":"G Moon","year":"2022","unstructured":"Moon, G., Nam, H., Shiratori, T., Lee, K.M.: 3D clothed human reconstruction in the wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 184\u2013200. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_11"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9054\u20139063 (2021)","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Ren, Y., Wang, F., Zhang, T., Pollefeys, M., S\u00fcsstrunk, S.: VolRecon: volume rendering of signed ray distance functions for generalizable multi-view reconstruction. arXiv preprint arXiv:2212.08067 (2022)","DOI":"10.1109\/CVPR52729.2023.01601"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PiFU: pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2304\u20132314 (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Saito, S., Simon, T., Saragih, J., Joo, H.: PIFuHD: multi-level pixel-aligned implicit function for high-resolution 3d human digitization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 84\u201393 (2020)","DOI":"10.1109\/CVPR42600.2020.00016"},{"issue":"4","key":"25_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925867","volume":"35","author":"M Savva","year":"2016","unstructured":"Savva, M., Chang, A.X., Hanrahan, P., Fisher, M., Nie\u00dfner, M.: PiGraphs: learning interaction snapshots from observations. ACM Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"JL Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501\u2013518. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Song, C., Yang, G., Deng, K., Zhu, J.Y., Ramanan, D.: Total-recon: deformable scene reconstruction for embodied view synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17671\u201317682 (2023)","DOI":"10.1109\/ICCV51070.2023.01620"},{"key":"25_CR54","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-031-20086-1_7","volume-title":"ECCV 2022","author":"SY Su","year":"2022","unstructured":"Su, S.Y., Bagautdinov, T., Rhodin, H.: DANBO: disentangled articulated neural body representations via graph neural networks. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 107\u2013124. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_7"},{"key":"25_CR55","unstructured":"Su, S.Y., Yu, F., Zollh\u00f6fer, M., Rhodin, H.: A-NeRF: articulated neural radiance fields for learning human shape, appearance, and pose. In: Advances in Neural Information Processing Systems (2021)"},{"key":"25_CR56","unstructured":"Szot, A., et al.: Habitat 2.0: training home assistants to rearrange their habitat. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Pollefeys, M.: IterMVS: iterative probability estimation for efficient multi-view stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8606\u20138615 (2022)","DOI":"10.1109\/CVPR52688.2022.00841"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M.: PatchmatchNet: learned multi-view patchmatch stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14194\u201314203 (2021)","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"25_CR59","series-title":"LNCS","first-page":"139","volume-title":"ECCV 2022","author":"J Wang","year":"2022","unstructured":"Wang, J., et al.: NeuRIS: neural reconstruction of indoor scenes using normal priors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 139\u2013155. Springer, Cham (2022)"},{"key":"25_CR60","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. In: Advances in Neural Information Processing Systems, vol. 34, pp. 27171\u201327183 (2021)"},{"issue":"4","key":"25_CR61","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., Sheikh, H., Simoncelli, E.: 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."},{"key":"25_CR62","doi-asserted-by":"crossref","unstructured":"Wei, Y., Liu, S., Rao, Y., Zhao, W., Lu, J., Zhou, J.: NerfingMVS: guided optimization of neural radiance fields for indoor multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5610\u20135619 (2021)","DOI":"10.1109\/ICCV48922.2021.00556"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Curless, B., Srinivasan, P.P., Barron, J.T., Kemelmacher-Shlizerman, I.: HumanNeRF: free-viewpoint rendering of moving people from monocular video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16210\u201316220 (2022)","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"25_CR64","doi-asserted-by":"crossref","unstructured":"Xiang, T., Sun, A., Wu, J., Adeli, E., Li, F.F.: Rendering humans from object-occluded monocular videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00300"},{"key":"25_CR65","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Yang, J., Tzionas, D., Black, M.J.: ICON: implicit clothed humans obtained from normals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13296\u201313306 (2022)","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"25_CR66","doi-asserted-by":"publisher","unstructured":"Xu, W., et al.: MonoPerfCap: human performance capture from monocular video. ACM TOG 37(2), 27:1\u201327:15 (2018). https:\/\/doi.org\/10.1145\/3181973","DOI":"10.1145\/3181973"},{"key":"25_CR67","doi-asserted-by":"crossref","unstructured":"Yang, G., Yang, S., Zhang, J.Z., Manchester, Z., Ramanan, D.: PPR: physically plausible reconstruction from monocular videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3914\u20133924 (2023)","DOI":"10.1109\/ICCV51070.2023.00362"},{"key":"25_CR68","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: Proceedings of the European conference on computer vision (ECCV), pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"25_CR69","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Shen, T., Fang, T., Quan, L.: Recurrent MVSNet for high-resolution multi-view stereo depth inference. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00567"},{"key":"25_CR70","unstructured":"Yariv, L., Gu, J., Kasten, Y., Lipman, Y.: Volume rendering of neural implicit surfaces. In: Thirty-Fifth Conference on Neural Information Processing Systems (2021)"},{"key":"25_CR71","unstructured":"Yariv, L., et al.: Multiview neural surface reconstruction by disentangling geometry and appearance. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"25_CR72","doi-asserted-by":"publisher","unstructured":"Yi, H., et al.: Human-aware object placement for visual environment reconstruction. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3949\u20133960 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00393","DOI":"10.1109\/CVPR52688.2022.00393"},{"key":"25_CR73","unstructured":"Yu, Z., Peng, S., Niemeyer, M., Sattler, T., Geiger, A.: MonoSDF: exploring monocular geometric cues for neural implicit surface reconstruction. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"25_CR74","unstructured":"Zhang, K., Riegler, G., Snavely, N., Koltun, V.: NeRF++: analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492 (2020)"},{"key":"25_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"25_CR76","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-3-031-20068-7_11","volume-title":"ECCV 2022","author":"S Zhang","year":"2022","unstructured":"Zhang, S., et al.: EgoBody: human body shape and motion of interacting people from head-mounted devices. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 180\u2013200. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_11"},{"key":"25_CR77","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Abrevaya, V.F., B\u00fchler, M.C., Chen, X., Black, M.J., Hilliges, O.: Im avatar: implicit morphable head avatars from videos. In: Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"25_CR78","doi-asserted-by":"crossref","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. (2021)","DOI":"10.1109\/TPAMI.2021.3050505"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73220-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:08:15Z","timestamp":1730578095000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73220-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031732195","9783031732201"],"references-count":78,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73220-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The collection of datasets, as\u00a0well as its usage involving human subjects, has undergone a rigorous ethical review and approval process by an Institutional Review Board. This ensures that all necessary ethical considerations\u00a0and guidelines are adhered to.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Concerns"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}