{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:37:37Z","timestamp":1777657057324,"version":"3.51.4"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728891","type":"print"},{"value":"9783031728907","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-3-031-72890-7_26","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:45:06Z","timestamp":1733514306000},"page":"422-439","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Rotated Orthographic Projection for\u00a0Self-supervised 3D Human Pose Estimation"],"prefix":"10.1007","author":[{"given":"Yao","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongchen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiamao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3D human pose reconstruction. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1446\u20131455 (2015)","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Bouazizi, A., Wiederer, J., Kressel, U., Belagiannis, V.: Self-supervised 3D human pose estimation with multiple-view geometry. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp.\u00a01\u20138. IEEE (2021)","DOI":"10.1109\/FG52635.2021.9667074"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C.H., et al.: Unsupervised 3D pose estimation with geometric self-supervision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5714\u20135724 (2019)","DOI":"10.1109\/CVPR.2019.00586"},{"issue":"12","key":"26_CR4","doi-asserted-by":"publisher","first-page":"4627","DOI":"10.1109\/TIP.2013.2274748","volume":"22","author":"J Chen","year":"2013","unstructured":"Chen, J., Nie, S., Ji, Q.: Data-free prior model for upper body pose estimation and tracking. IEEE Trans. Image Process. 22(12), 4627\u20134639 (2013)","journal-title":"IEEE Trans. Image Process."},{"key":"26_CR5","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Sharma, A., Jain, A.: Learning 3D human pose from structure and motion. In: European Conference on Computer Vision, pp. 668\u2013683 (2018)","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"26_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-030-58520-4_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Georgakis","year":"2020","unstructured":"Georgakis, G., Li, R., Karanam, S., Chen, T., Ko\u0161eck\u00e1, J., Wu, Z.: Hierarchical kinematic human mesh recovery. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 768\u2013784. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_45"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Gholami, M., Rezaei, A., Rhodin, H., Ward, R., Wang, Z.J.: Tripose: a weakly-supervised 3D human pose estimation via triangulation from video. arXiv preprint arXiv:2105.06599 (2021)","DOI":"10.1016\/j.neucom.2022.02.076"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Gong, K., et al.: Posetriplet: co-evolving 3D human pose estimation, imitation, and hallucination under self-supervision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11017\u201311027 (2022)","DOI":"10.1109\/CVPR52688.2022.01074"},{"key":"26_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-031-19769-7_13","volume-title":"ECCV 2022","author":"X Gong","year":"2022","unstructured":"Gong, X., et al.: Self-supervised human mesh recovery with cross-representation alignment. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13661, pp. 212\u2013230. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_13"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Habermann, M., Xu, W., Zollhofer, M., Pons-Moll, G., Theobalt, C.: Deepcap: monocular human performance capture using weak supervision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5052\u20135063 (2020)","DOI":"10.1109\/CVPR42600.2020.00510"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Molchanov, P., Kautz, J.: Weakly-supervised 3D human pose learning via multi-view images in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5243\u20135252 (2020)","DOI":"10.1109\/CVPR42600.2020.00529"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Jack, D., Maire, F., Eriksson, A., Shirazi, S.: Adversarially parameterized optimization for 3D human pose estimation. In: 2017 International Conference on 3D Vision (3DV), pp. 145\u2013154. IEEE (2017)","DOI":"10.1109\/3DV.2017.00026"},{"key":"26_CR15","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"26_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109908","volume":"145","author":"HW Kim","year":"2024","unstructured":"Kim, H.W., et al.: MHCanonNet: multi-hypothesis canonical lifting network for self-supervised 3D human pose estimation in the wild video. Pattern Recogn. 145, 109908 (2024)","journal-title":"Pattern Recogn."},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Kim, H.W., Lee, G.H., Oh, M.S., Lee, S.W.: Cross-view self-fusion for self-supervised 3D human pose estimation in the wild. In: Proceedings of the Asian Conference on Computer Vision, pp. 1385\u20131402 (2022)","DOI":"10.1007\/978-3-031-26319-4_12"},{"key":"26_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-030-66096-3_37","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"I Kissos","year":"2020","unstructured":"Kissos, I., Fritz, L., Goldman, M., Meir, O., Oks, E., Kliger, M.: Beyond weak perspective for monocular 3D human pose estimation. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 541\u2013554. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66096-3_37"},{"key":"26_CR19","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11035\u201311045 (2021)","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagoz, S., Akbas, E.: Self-supervised learning of 3D human pose using multi-view geometry. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1077\u20131086 (2019)","DOI":"10.1109\/CVPR.2019.00117"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Seth, S., Jampani, V., Rakesh, M., Babu, R.V., Chakraborty, A.: Self-supervised 3D human pose estimation via part guided novel image synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6152\u20136162 (2020)","DOI":"10.1109\/CVPR42600.2020.00619"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, D., Li, M., Lee, D.J.: Accurate head pose estimation using image rectification and a lightweight convolutional neural network. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3144893"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, K., Jiang, S., Zhang, Z., Huang, C., Da\u00a0Xu, R.Y.: Geometry-driven self-supervised method for 3D human pose estimation. In: AAAI, vol.\u00a034, pp. 11442\u201311449 (2020)","DOI":"10.1609\/aaai.v34i07.6808"},{"key":"26_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1007\/978-3-031-20065-6_34","volume-title":"ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., Liu, J., Zhang, Z., Xu, S., Yan, Y.: CLIFF: carrying location information in full frames into human pose and shape estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 590\u2013606. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_34"},{"issue":"4","key":"26_CR25","doi-asserted-by":"publisher","first-page":"3864","DOI":"10.1007\/s10489-022-03714-x","volume":"53","author":"Z Ma","year":"2023","unstructured":"Ma, Z., Li, K., Li, Y.: Self-supervised method for 3D human pose estimation with consistent shape and viewpoint factorization. Appl. Intell. 53(4), 3864\u20133876 (2023)","journal-title":"Appl. Intell."},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506\u2013516. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Kolotouros, N., Daniilidis, K.: Texturepose: supervising human mesh estimation with texture consistency. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 803\u2013812 (2019)","DOI":"10.1109\/ICCV.2019.00089"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Rhodin, H., et al.: Learning monocular 3D human pose estimation from multi-view images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8437\u20138446 (2018)","DOI":"10.1109\/CVPR.2018.00880"},{"key":"26_CR30","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/978-3-031-20065-6_27","volume-title":"ECCV 2022","author":"W Shan","year":"2022","unstructured":"Shan, W., Liu, Z., Zhang, X., Wang, S., Ma, S., Gao, W.: P-STMO: pre-trained spatial temporal many-to-one model for 3D human pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 461\u2013478. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_27"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Usman, B., Tagliasacchi, A., Saenko, K., Sud, A.: Metapose: fast 3D pose from multiple views without 3D supervision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6759\u20136770 (2022)","DOI":"10.1109\/CVPR52688.2022.00664"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Wandt, B., Little, J.J., Rhodin, H.: Elepose: unsupervised 3D human pose estimation by predicting camera elevation and learning normalizing flows on 2D poses. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6635\u20136645 (2022)","DOI":"10.1109\/CVPR52688.2022.00652"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Wandt, B., Rosenhahn, B.: Repnet: weakly supervised training of an adversarial reprojection network for 3D human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7782\u20137791 (2019)","DOI":"10.1109\/CVPR.2019.00797"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Wandt, B., Rudolph, M., Zell, P., Rhodin, H., Rosenhahn, B.: Canonpose: self-supervised monocular 3D human pose estimation in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 13294\u201313304 (2021)","DOI":"10.1109\/CVPR46437.2021.01309"},{"issue":"5","key":"26_CR35","first-page":"1069","volume":"42","author":"K Wang","year":"2019","unstructured":"Wang, K., Lin, L., Jiang, C., Qian, C., Wei, P.: 3D human pose machines with self-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 42(5), 1069\u20131082 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Wehrbein, T., Rudolph, M., Rosenhahn, B., Wandt, B.: Probabilistic monocular 3D human pose estimation with normalizing flows. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11199\u201311208 (2021)","DOI":"10.1109\/ICCV48922.2021.01101"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Wei, X.K., Chai, J.: Modeling 3D human poses from uncalibrated monocular images. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1873\u20131880. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459415"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X.: 3D human pose estimation in the wild by adversarial learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5255\u20135264 (2018)","DOI":"10.1109\/CVPR.2018.00551"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Yoo, N., Russakovsky, O.: Efficient, self-supervised human pose estimation with inductive prior tuning. In: International Conference on Computer Vision, pp. 3271\u20133280 (2023)","DOI":"10.1109\/ICCVW60793.2023.00351"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Yu, F., Salzmann, M., Fua, P., Rhodin, H.: PCLS: geometry-aware neural reconstruction of 3D pose with perspective crop layers. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9064\u20139073 (2021)","DOI":"10.1109\/CVPR46437.2021.00895"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Yu, Z., Ni, B., Xu, J., Wang, J., Zhao, C., Zhang, W.: Towards alleviating the modeling ambiguity of unsupervised monocular 3D human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8651\u20138660 (2021)","DOI":"10.1109\/ICCV48922.2021.00853"},{"key":"26_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/978-3-030-58539-6_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zanfir","year":"2020","unstructured":"Zanfir, A., Bazavan, E.G., Xu, H., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Weakly supervised 3D human pose and shape reconstruction with normalizing flows. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 465\u2013481. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_28"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, H., Kephart, J.O., Ji, Q.: Body knowledge and uncertainty modeling for monocular 3D human body reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9020\u20139032 (2023)","DOI":"10.1109\/ICCV51070.2023.00828"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3D human pose regression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"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\/978-3-031-72890-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:08:11Z","timestamp":1733515691000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72890-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9783031728891","9783031728907"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72890-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 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"}}]}}