{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:50:01Z","timestamp":1754110201896,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695248"},{"type":"electronic","value":"9783030695255"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69525-5_5","type":"book-chapter","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T16:21:16Z","timestamp":1614356476000},"page":"71-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-view Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2918-5603","authenticated-orcid":false,"given":"Akin","family":"Caliskan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1779-2775","authenticated-orcid":false,"given":"Armin","family":"Mustafa","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7837-7516","authenticated-orcid":false,"given":"Evren","family":"Imre","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4223-238X","authenticated-orcid":false,"given":"Adrian","family":"Hilton","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"5_CR1","first-page":"1","volume":"38","author":"K Guo","year":"2019","unstructured":"Guo, K., et al.: The relightables: volumetric performance capture of humans with realistic relighting. ACM Trans. Graph. (TOG) 38, 1\u201319 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Mustafa, A., Russell, C., Hilton, A.: U4D: unsupervised 4D dynamic scene understanding. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01052"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Dong, H., et al.: Towards multi-pose guided virtual try-on network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9026\u20139035 (2019)","DOI":"10.1109\/ICCV.2019.00912"},{"key":"5_CR4","unstructured":"Liu, L., et al.: Neural rendering and reenactment of human actor videos (2018)"},{"key":"5_CR5","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Alp G\u00fcler, R., Neverova, N., Kokkinos, I.: DensePose: dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Yang, L., Song, Q., Wang, Z., Jiang, M.: Parsing R-CNN for instance-level human analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 364\u2013373 (2019)","DOI":"10.1109\/CVPR.2019.00045"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagoz, S., Akbas, E.: Self-supervised learning of 3D human pose using multi-view geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1077\u20131086 (2019)","DOI":"10.1109\/CVPR.2019.00117"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: posing face, body, and hands in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310974 (2019)","DOI":"10.1109\/CVPR.2019.01122"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito, L.: Lifting from the deep: convolutional 3D pose estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2500\u20132509 (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"5_CR12","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":"5_CR13","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 International Conference on Computer Vision, pp. 2304\u20132314 (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y.: DeepHuman: 3D human reconstruction from a single image. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7739\u20137749 (2019)","DOI":"10.1109\/ICCV.2019.00783"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Jackson, A.S., Manafas, C., Tzimiropoulos, G.: 3D human body reconstruction from a single image via volumetric regression. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-11018-5_6"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Mustafa, A., Kim, H., Guillemaut, J.Y., Hilton, A.: General dynamic scene reconstruction from multiple view video. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.109"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Leroy, V., Franco, J.S., Boyer, E.: Shape reconstruction using volume sweeping and learned photoconsistency. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01240-3_48"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Gilbert, A., Volino, M., Collomosse, J., Hilton, A.: Volumetric performance capture from minimal camera viewpoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 566\u2013581 (2018)","DOI":"10.1007\/978-3-030-01252-6_35"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: BodyNet: volumetric inference of 3D human body shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01234-2_2"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: DoubleFusion: real-time capture of human performances with inner body shapes from a single depth sensor. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7287\u20137296 (2018)","DOI":"10.1109\/CVPR.2018.00761"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Caliskan, A., Mustafa, A., Imre, E., Hilton, A.: Learning dense wide baseline stereo matching for people. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00271"},{"key":"5_CR22","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":"5_CR23","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":"5_CR24","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Tiwari, G., Theobalt, C., Pons-Moll, G.: Multi-Garment Net: learning to dress 3D people from images. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5419\u20135429 (2019)","DOI":"10.1109\/ICCV.2019.00552"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Natsume, R., et al.: SiCloPe: silhouette-based clothed people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4480\u20134490 (2019)","DOI":"10.1109\/CVPR.2019.00461"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Franco, J.S., Martin, X., Schmid, C., Rogez, G.: Moulding humans: non-parametric 3D human shape estimation from single images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2232\u20132241 (2019)","DOI":"10.1109\/ICCV.2019.00232"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Sanchez, J., Choi, G., Sanfeliu, A., Moreno-Noguer, F.: 3DPeople: modeling the geometry of dressed humans. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00233"},{"key":"5_CR29","first-page":"248:1","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. (Proc. SIGGRAPH Asia) 34, 248:1\u2013248:16 (2015)","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH Asia)"},{"key":"5_CR30","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\/1073204.1073207"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Ma, Q., et al.: Learning to dress 3D people in generative clothing. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00650"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: SimulCap: single-view human performance capture with cloth simulation. In: 32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00565"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Pons-Moll, G., Theobalt, C., Magnor, M.: Tex2Shape: detailed full human body geometry from a single image. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2293\u20132303 (2019)","DOI":"10.1109\/ICCV.2019.00238"},{"key":"5_CR34","unstructured":"Multiview video repository: Center for Vision Speech and Signal Processing (CVSSP). University of Surrey, UK (2020). https:\/\/cvssp.org\/data\/cvssp3d\/"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Vlasic, D., Baran, I., Matusik, W., Popovi\u0107, J.: Articulated mesh animation from multi-view silhouettes. In: ACM SIGGRAPH 2008 Papers, pp. 1\u20139 (2008)","DOI":"10.1145\/1360612.1360696"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 109\u2013117 (2017)","DOI":"10.1109\/CVPR.2017.492"},{"key":"5_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/978-3-319-46493-0_27","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Yang","year":"2016","unstructured":"Yang, J., Franco, J.-S., H\u00e9troy-Wheeler, F., Wuhrer, S.: Estimation of human body shape in motion with wide clothing. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 439\u2013454. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_27"},{"key":"5_CR38","first-page":"27:1","volume":"37","author":"W Xu","year":"2018","unstructured":"Xu, W., et al.: MonoPerfCap: human performance capture from monocular video. ACM Trans. Graph. 37, 27:1\u201327:15 (2018)","journal-title":"ACM Trans. Graph."},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V.: Unite the people: closing the loop between 3D and 2D human representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6050\u20136059 (2017)","DOI":"10.1109\/CVPR.2017.500"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Efros, A.A., Malik, J.: Multi-view consistency as supervisory signal for learning shape and pose prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2897\u20132905 (2018)","DOI":"10.1109\/CVPR.2018.00306"},{"key":"5_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Jackson, A.S., Bulat, A., Argyriou, V., Tzimiropoulos, G.: Large pose 3D face reconstruction from a single image via direct volumetric CNN regression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1031\u20131039 (2017)","DOI":"10.1109\/ICCV.2017.117"},{"key":"5_CR44","unstructured":"Adobe: Fuse (2020). https:\/\/www.adobe.com\/products\/fuse.html"},{"key":"5_CR45","unstructured":"Adobe: Mixamo (2020). https:\/\/www.mixamo.com\/"},{"key":"5_CR46","unstructured":"HDRI: Heaven (2020). https:\/\/hdrihaven.com\/"},{"key":"5_CR47","unstructured":"Jatavallabhula, K.M., et al.: Kaolin: a PyTorch library for accelerating 3D deep learning research. arXiv:1911.05063 (2019)"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Huang, Z., Xu, Y., Lassner, C., Li, H., Tung, T.: ARCH: animatable reconstruction of clothed humans. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00316"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69525-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T16:38:26Z","timestamp":1614357506000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69525-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695248","9783030695255"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69525-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}