{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T02:44:14Z","timestamp":1774579454385,"version":"3.50.1"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736674","type":"print"},{"value":"9783031736681","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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\/978-3-031-73668-1_13","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:01:16Z","timestamp":1733018476000},"page":"215-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["AvatarPose: Avatar-Guided 3D Pose Estimation of\u00a0Close Human Interaction from\u00a0Sparse Multi-view Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4017-9606","authenticated-orcid":false,"given":"Feichi","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4150-5072","authenticated-orcid":false,"given":"Zijian","family":"Dong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7484-1937","authenticated-orcid":false,"given":"Jie","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5068-3474","authenticated-orcid":false,"given":"Otmar","family":"Hilliges","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM SIGGRAPH 2005 Papers, pp. 408\u2013416 (2005)","DOI":"10.1145\/1186822.1073207"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., Ilic, S.: 3D pictorial structures for multiple human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1669\u20131676 (2014)","DOI":"10.1109\/CVPR.2014.216"},{"issue":"10","key":"13_CR3","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1109\/TPAMI.2015.2509986","volume":"38","author":"V Belagiannis","year":"2015","unstructured":"Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., Ilic, S.: 3D pictorial structures revisited: multiple human pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 1929\u20131942 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Benzine, A., Chabot, F., Luvison, B., Pham, Q.C., Achard, C.: Pandanet: anchor-based single-shot multi-person 3D pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6856\u20136865 (2020)","DOI":"10.1109\/CVPR42600.2020.00689"},{"key":"13_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58536-5_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"BL Bhatnagar","year":"2020","unstructured":"Bhatnagar, B.L., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Combining implicit function learning and parametric models for 3D human reconstruction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 311\u2013329. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_19"},{"key":"13_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":"13_CR7","doi-asserted-by":"crossref","unstructured":"Burov, A., Nie\u00dfner, M., Thies, J.: Dynamic surface function networks for clothed human bodies. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10754\u201310764 (2021)","DOI":"10.1109\/ICCV48922.2021.01058"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"13_CR9","unstructured":"Chen, J., et al.: Animatable neural radiance fields from monocular RGB videos. arXiv preprint arXiv:2106.13629 (2021)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L., Ai, H., Chen, R., Zhuang, Z., Liu, S.: Cross-view tracking for multi-human 3D pose estimation at over 100 FPS. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3279\u20133288 (2020)","DOI":"10.1109\/CVPR42600.2020.00334"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., Zheng, Y., Black, M.J., Hilliges, O., Geiger, A.: Snarf: differentiable forward skinning for animating non-rigid neural implicit shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11594\u201311604 (2021)","DOI":"10.1109\/ICCV48922.2021.01139"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Y., Gu, R., Huang, O., Jia, G.: VTP: volumetric transformer for multi-view multi-person 3D pose estimation. Appl. Intell. 1\u201312 (2023)","DOI":"10.1007\/s10489-023-04805-z"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Higherhrnet: scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"13_CR15","unstructured":"Cheng, Y., et al.: Segment and track anything. arXiv preprint arXiv:2305.06558 (2023)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Choudhury, R., Kitani, K.M., Jeni, L.A.: Tempo: efficient multi-view pose estimation, tracking, and forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14750\u201314760 (2023)","DOI":"10.1109\/ICCV51070.2023.01355"},{"issue":"10","key":"13_CR17","doi-asserted-by":"publisher","first-page":"6981","DOI":"10.1109\/TPAMI.2021.3098052","volume":"44","author":"J Dong","year":"2021","unstructured":"Dong, J., Fang, Q., Jiang, W., Yang, Y., Bao, H., Zhou, X.: Fast and robust multi-person 3D pose estimation and tracking from multiple views. T-PAMI 44(10), 6981\u20136992 (2021)","journal-title":"T-PAMI"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Dong, J., Jiang, W., Huang, Q., Bao, H., Zhou, X.: 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\u20137801 (2019)","DOI":"10.1109\/CVPR.2019.00798"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Dong, Z., Guo, C., Song, J., Chen, X., Geiger, A., Hilliges, O.: Pina: learning a personalized implicit neural avatar from a single RGB-D video sequence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20470\u201320480 (2022)","DOI":"10.1109\/CVPR52688.2022.01982"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Dong, Z., Song, J., Chen, X., Guo, C., Hilliges, O.: Shape-aware multi-person pose estimation from multi-view images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11158\u201311168 (2021)","DOI":"10.1109\/ICCV48922.2021.01097"},{"key":"13_CR21","doi-asserted-by":"publisher","first-page":"15573","DOI":"10.1007\/s11042-017-5133-8","volume":"77","author":"S Ershadi-Nasab","year":"2018","unstructured":"Ershadi-Nasab, S., Noury, E., Kasaei, S., Sanaei, E.: Multiple human 3D pose estimation from multiview images. Multimedia Tools Appl. 77, 15573\u201315601 (2018)","journal-title":"Multimedia Tools Appl."},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Fabbri, M., Lanzi, F., Calderara, S., Alletto, S., Cucchiara, R.: Compressed volumetric heatmaps for multi-person 3D pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7204\u20137213 (2020)","DOI":"10.1109\/CVPR42600.2020.00723"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: RMPE: regional multi-person pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2334\u20132343 (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Three-dimensional reconstruction of human interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7214\u20137223 (2020)","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"13_CR25","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":"13_CR26","doi-asserted-by":"crossref","unstructured":"Guo, W., Bie, X., Alameda-Pineda, X., Moreno-Noguer, F.: Multi-person extreme motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13053\u201313064 (2022)","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.P.: A statistical model of human pose and body shape. In: Computer Graphics Forum, vol.\u00a028, pp. 337\u2013346. Wiley Online Library (2009)","DOI":"10.1111\/j.1467-8659.2009.01373.x"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, T., Chen, X., Song, J., Hilliges, O.: Instantavatar: learning avatars from monocular video in 60 seconds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16922\u201316932 (2023)","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Joo, H., et al.: Panoptic studio: a massively multiview system for social motion capture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3334\u20133342 (2015)","DOI":"10.1109\/ICCV.2015.381"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"13_CR31","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 of the IEEE\/CVF International Conference on Computer Vision, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Tesch, J., M\u00fcller, L., Hilliges, O., Black, M.J.: Spec: seeing people in the wild with an estimated camera. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11035\u201311045 (2021)","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Tokenpose: learning keypoint tokens for human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11313\u201311322 (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Lin, J., Lee, G.H.: Multi-view multi-person 3D pose estimation with plane sweep stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11886\u201311895 (2021)","DOI":"10.1109\/CVPR46437.2021.01171"},{"issue":"11","key":"13_CR35","doi-asserted-by":"publisher","first-page":"2720","DOI":"10.1109\/TPAMI.2013.47","volume":"35","author":"Y Liu","year":"2013","unstructured":"Liu, Y., Gall, J., Stoll, C., Dai, Q., Seidel, H.P., Theobalt, C.: Markerless motion capture of multiple characters using multiview image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 35(11), 2720\u20132735 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"13_CR36","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":"13_CR37","doi-asserted-by":"crossref","unstructured":"Luvizon, D.C., Habermann, M., Golyanik, V., Kortylewski, A., Theobalt, C.: Scene-aware 3D multi-human motion capture from a single camera. In: Computer Graphics Forum, vol.\u00a042, pp. 371\u2013383. Wiley Online Library (2023)","DOI":"10.1111\/cgf.14768"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"issue":"4","key":"13_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. (TOG) 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"1","key":"13_CR40","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Muller, L., Osman, A.A.A., Tang, S., Huang, C.H.P., Black, M.J.: On self-contact and human pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9990\u20139999 (2021)","DOI":"10.1109\/CVPR46437.2021.00986"},{"issue":"4","key":"13_CR42","doi-asserted-by":"publisher","first-page":"1","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. (ToG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"13_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1007\/978-3-030-58539-6_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"AAA Osman","year":"2020","unstructured":"Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: sparse trained articulated human body regressor. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 598\u2013613. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_36"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Patel, P., Huang, C.H.P., Tesch, J., Hoffmann, D.T., Tripathi, S., Black, M.J.: Agora: avatars in geography optimized for regression analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13468\u201313478 (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468 (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"13_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":"13_CR48","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., et al.: Deepcut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4929\u20134937 (2016)","DOI":"10.1109\/CVPR.2016.533"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Reddy, N.D., Guigues, L., Pishchulin, L., Eledath, J., Narasimhan, S.G.: Tessetrack: end-to-end learnable multi-person articulated 3D pose tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15190\u201315200 (2021)","DOI":"10.1109\/CVPR46437.2021.01494"},{"key":"13_CR50","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610 (2022)"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Saito, S., Yang, J., Ma, Q., Black, M.J.: Scanimate: weakly supervised learning of skinned clothed avatar networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2886\u20132897 (2021)","DOI":"10.1109\/CVPR46437.2021.00291"},{"key":"13_CR52","doi-asserted-by":"publisher","unstructured":"Shuai, Q., et al.: Novel view synthesis of human interactions from sparse multi-view videos. In: ACM SIGGRAPH 2022 Conference Proceedings. SIGGRAPH 2022. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3528233.3530704","DOI":"10.1145\/3528233.3530704"},{"key":"13_CR53","doi-asserted-by":"publisher","unstructured":"Shuai, Q., et al.: Reconstructing close human interactions from multiple views. ACM Trans. Graph. (2023). https:\/\/doi.org\/10.1145\/3618336","DOI":"10.1145\/3618336"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M.J., Mei, T.: Monocular, one-stage, regression of multiple 3D people. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11179\u201311188 (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, W., Bao, Q., Fu, Y., Mei, T., Black, M.J.: Putting people in their place: monocular regression of 3D people in depth. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13243\u201313252 (2022)","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"13_CR56","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-031-20068-7_16","volume-title":"European Conference on Computer Vision","author":"G Te","year":"2022","unstructured":"Te, G., Li, X., Li, X., Wang, J., Hu, W., Lu, Y.: Neural capture of animatable 3D human from monocular video. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 275\u2013291. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_16"},{"key":"13_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-030-58452-8_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Tu","year":"2020","unstructured":"Tu, H., Wang, C., Zeng, W.: VoxelPose: towards multi-camera 3D human pose estimation in wild environment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 197\u2013212. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_12"},{"key":"13_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1007\/978-3-030-58580-8_15","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Wang","year":"2020","unstructured":"Wang, C., Li, J., Liu, W., Qian, C., Lu, C.: HMOR: hierarchical multi-person ordinal relations for monocular multi-person 3D pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 242\u2013259. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_15"},{"key":"13_CR59","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-19824-3_1","volume-title":"European conference on computer vision","author":"S Wang","year":"2022","unstructured":"Wang, S., Schwarz, K., Geiger, A., Tang, S.: ARAH: animatable volume rendering of articulated human SDFs. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 1\u201319. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_1"},{"key":"13_CR60","unstructured":"Wang, T., Zhang, J., Cai, Y., Yan, S., Feng, J.: Direct multi-view multi-person 3D pose estimation. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034, pp. 13153\u201313164. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/6da9003b743b65f4c0ccd295cc484e57-Paper.pdf"},{"key":"13_CR61","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, pp. 16210\u201316220 (2022)","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"13_CR62","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Graph-based 3D multi-person pose estimation using multi-view images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11148\u201311157 (2021)","DOI":"10.1109\/ICCV48922.2021.01096"},{"key":"13_CR63","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Graph-based 3D multi-person pose estimation using multi-view images. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01096"},{"key":"13_CR64","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6184\u20136193 (2020)","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"13_CR65","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-031-20068-7_9","volume-title":"European Conference on Computer Vision","author":"H Ye","year":"2022","unstructured":"Ye, H., Zhu, W., Wang, C., Wu, R., Wang, Y.: Faster voxelpose: real-time 3D human pose estimation by orthographic projection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 142\u2013159. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_9"},{"key":"13_CR66","doi-asserted-by":"crossref","unstructured":"Yin, Y., Guo, C., Kaufmann, M., Zarate, J.J., Song, J., Hilliges, O.: HI4D: 4D instance segmentation of close human interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17016\u201317027 (2023)","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"13_CR67","doi-asserted-by":"crossref","unstructured":"Zanfir, A., Marinoiu, E., Sminchisescu, C.: Monocular 3D pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2148\u20132157 (2018)","DOI":"10.1109\/CVPR.2018.00229"},{"key":"13_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Pymaf: 3D human pose and shape regression with pyramidal mesh alignment feedback loop. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11446\u201311456 (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"issue":"4","key":"13_CR69","first-page":"1","volume":"40","author":"J Zhang","year":"2021","unstructured":"Zhang, J., et al.: Editable free-viewpoint video using a layered neural representation. ACM Trans. Graph. (TOG) 40(4), 1\u201318 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"2","key":"13_CR70","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1109\/TPAMI.2022.3163709","volume":"45","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Wang, C., Wang, X., Liu, W., Zeng, W.: Voxeltrack: multi-person 3D human pose estimation and tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 2613\u20132626 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, Y., An, L., Yu, T., Li, X., Li, K., Liu, Y.: 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\u20131333 (2020)","DOI":"10.1109\/CVPR42600.2020.00140"},{"key":"13_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, Z., An, L., Li, M., Yu, T., Liu, Y.: Lightweight multi-person total motion capture using sparse multi-view cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5560\u20135569 (2021)","DOI":"10.1109\/ICCV48922.2021.00551"},{"key":"13_CR73","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: Deepmulticap: performance capture of multiple characters using sparse multiview cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6239\u20136249 (2021)","DOI":"10.1109\/ICCV48922.2021.00618"},{"key":"13_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, H., Hong, C., Han, Y., Huang, P., Zhuang, Y.: MH pose: 3D human pose estimation based on high-quality heatmap. In: 2021 IEEE International Conference on Big Data (Big Data), pp. 3215\u20133222. IEEE (2021)","DOI":"10.1109\/BigData52589.2021.9671770"},{"key":"13_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Quickpose: real-time multi-view multi-person pose estimation in crowded scenes. In: ACM SIGGRAPH 2022 Conference Proceedings, pp.\u00a01\u20139 (2022)","DOI":"10.1145\/3528233.3530746"}],"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\/978-3-031-73668-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:09:21Z","timestamp":1733018961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73668-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031736674","9783031736681"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73668-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"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"}}]}}