{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T02:28:38Z","timestamp":1782268118920,"version":"3.54.5"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263187","type":"print"},{"value":"9783031263194","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26319-4_13","type":"book-chapter","created":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T06:02:59Z","timestamp":1677823379000},"page":"211-227","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["3D-C2FT: Coarse-to-Fine Transformer for\u00a0Multi-view 3D Reconstruction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3786-2117","authenticated-orcid":false,"given":"Leslie Ching Ow","family":"Tiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6207-5804","authenticated-orcid":false,"given":"Dick","family":"Sigmund","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5063-9484","authenticated-orcid":false,"given":"Andrew Beng Jin","family":"Teoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,4]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. arXiv e-prints (2020). https:\/\/arxiv.org\/abs\/2005.00928","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Burchfiel, B., Konidaris, G.: Bayesian eigenobjects: a unified framework for 3D robot perception. In: Robotics: Science and Systems, vol. 13 (2017)","DOI":"10.15607\/RSS.2017.XIII.011"},{"key":"13_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-46484-8_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"CB Choy","year":"2016","unstructured":"Choy, C.B., Xu, D., Gwak, J.Y., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3d object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628\u2013644. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_38"},{"key":"13_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Gao, Y., Luo, J., Qiu, H., Wu, B.: Survey of structure from motion. In: Proceedings of 2014 International Conference on Cloud Computing and Internet of Things, pp. 72\u201376 (2014)","DOI":"10.1109\/CCIOT.2014.7062508"},{"issue":"1","key":"13_CR6","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.neuron.2018.12.014","volume":"101","author":"IIA Groen","year":"2019","unstructured":"Groen, I.I.A., Baker, C.I.: Previews scenes in the human brain: comparing 2D versus 3D representations. Neuron 101(1), 8\u201310 (2019)","journal-title":"Neuron"},{"issue":"5","key":"13_CR7","doi-asserted-by":"publisher","first-page":"1578","DOI":"10.1109\/TPAMI.2019.2954885","volume":"43","author":"XF Han","year":"2021","unstructured":"Han, X.F., Laga, H., Bennamoun, M.: Image-based 3D object reconstruction: state-of-the-art and trends in the deep learning era. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1578\u20131604 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"13_CR9","unstructured":"Jab\u0142o\u0144ski, S., Martyn, T.: Real-time voxel rendering algorithm based on screen space billboard voxel buffer with sparse lookup textures. In: 24th Conference on Computer Graphics, Visualization and Computer Vision, pp. 27\u201336 (2016)"},{"issue":"7","key":"13_CR10","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/TVCG.2018.2834372","volume":"25","author":"M Kanzler","year":"2019","unstructured":"Kanzler, M., Rautenhaus, M., Westermann, R.: A voxel-based rendering pipeline for large 3d line sets. IEEE Trans. Visual Comput. Graph. 25(7), 2378\u20132391 (2019)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"13_CR11","unstructured":"Kar, A., H\u00e4ne, C., Malik, J.: Learning a multi-view stereo machine. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), pp. 364\u2013375. Curran Associates, Inc. (2017)"},{"issue":"3","key":"13_CR12","doi-asserted-by":"publisher","first-page":"1799","DOI":"10.3390\/heritage2030110","volume":"2","author":"A Kargas","year":"2019","unstructured":"Kargas, A., Loumos, G., Varoutas, D.: Using different ways of 3D reconstruction of historical cities for gaming purposes: the case study of Nafplio. Heritage 2(3), 1799\u20131811 (2019)","journal-title":"Heritage"},{"key":"13_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-030-58571-6_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"VV Kniaz","year":"2020","unstructured":"Kniaz, V.V., Knyaz, V.A., Remondino, F., Bordodymov, A., Moshkantsev, P.: Image-to-voxel model translation for 3d scene reconstruction and segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 105\u2013124. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_7"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Malik, J., et al.: HandVoxNet: deep voxel-based network for 3d hand shape and pose estimation from a single depth map. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7111\u20137120 (2020)","DOI":"10.1109\/CVPR42600.2020.00714"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3d reconstruction in function space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Nabil, M., Saleh, F.: 3D reconstruction from images for museum artefacts: a comparative study. In: International Conference on Virtual Systems and Multimedia (VSMM), pp. 257\u2013260. IEEE (2014)","DOI":"10.1109\/VSMM.2014.7136681"},{"key":"13_CR17","unstructured":"Nguyen, T.Q., Salazar, J.: Transformers without tears: improving the normalization of self-attention. In: Proceedings of the 16th International Conference on Spoken Language Translation, Hong Kong (2019)"},{"key":"13_CR18","unstructured":"Park, N., Kim, S.: How do vision transformers work? In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"13_CR19","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS), pp. 8024\u20138035 (2019)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"P\u0103v\u0103loiu, I.B., Vasil\u0103\u0163eanu, A., Goga, N., Marin, I., Ilie, C., Ungar, A., P\u0103tra\u015fcu, I.: 3D dental reconstruction from CBCT data. In: International Symposium on Fundamentals of Electrical Engineering (ISFEE), pp. 4\u20139 (2014)","DOI":"10.1109\/ISFEE.2014.7050617"},{"issue":"1","key":"13_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-53170-w","volume":"9","author":"S Roointan","year":"2019","unstructured":"Roointan, S., Tavakolian, P., Sivagurunathan, K.S., Floryan, M., Mandelis, A., Abrams, S.H.: 3D dental subsurface imaging using enhanced truncated correlation-photothermal coherence tomography. Sci. Rep. 9(1), 1\u201312 (2019)","journal-title":"Sci. Rep."},{"key":"13_CR22","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.mechatronics.2016.11.005","volume":"41","author":"Q Shi","year":"2017","unstructured":"Shi, Q., Li, C., Wang, C., Luo, H., Huang, Q., Fukuda, T.: Design and implementation of an omnidirectional vision system for robot perception. Mechatronics 41, 58\u201366 (2017)","journal-title":"Mechatronics"},{"key":"13_CR23","unstructured":"Shi, Z., Meng, Z., Xing, Y., Ma, Y., Wattenhofer, R.: 3D-RETR: end-to-end single and multi-view 3D reconstruction with transformers. In: British Machine Vision Conference (BMVC), pp. 1\u201314 (2021)"},{"issue":"5","key":"13_CR24","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1109\/TRO.2008.2004829","volume":"24","author":"G Silveira","year":"2008","unstructured":"Silveira, G., Malis, E., Rives, P.: An efficient direct approach to visual SLAM. IEEE Trans. Rob. 24(5), 969\u2013979 (2008)","journal-title":"IEEE Trans. Rob."},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Dosovitskiy, A., Brox, T.: Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs. In: IEEE International Conference on Computer Vision (ICCV), pp. 2088\u20132096 (2017)","DOI":"10.1109\/ICCV.2017.230"},{"issue":"12","key":"13_CR26","doi-asserted-by":"publisher","first-page":"3325","DOI":"10.1109\/TAC.2014.2351912","volume":"59","author":"R Tron","year":"2014","unstructured":"Tron, R., Vidal, R.: Distributed 3-D localization of camera sensor networks from 2-D image Measurements. IEEE Trans. Autom. Control 59(12), 3325\u20133340 (2014)","journal-title":"IEEE Trans. Autom. Control"},{"key":"13_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), vol. 30, pp. 6000\u20136010 (2017)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Wang, D., et al.: Multi-view 3D reconstruction with transformer. In: International Conference on Computer Vision (ICCV), pp. 5722\u20135731 (2021)","DOI":"10.1109\/ICCV48922.2021.00567"},{"key":"13_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-030-01252-6_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Wang","year":"2018","unstructured":"Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., Jiang, Y.-G.: Pixel2Mesh: generating 3d mesh models from single RGB images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 55\u201371. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_4"},{"issue":"4","key":"13_CR30","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)","journal-title":"IEEE Trans. Image Process."},{"key":"13_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/978-3-319-10578-9_5","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K Wilson","year":"2014","unstructured":"Wilson, K., Snavely, N.: Robust global translations with 1DSfM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 61\u201375. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_5"},{"key":"13_CR32","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1912\u20131920 (2015)"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Xie, H., Yao, H., Sun, X., Zhou, S., Zhang, S.: Pix2Vox: context-aware 3D reconstruction from single and multi-view images. In: IEEE International Conference on Computer Vision (ICCV), pp. 2690\u20132698 (2019)","DOI":"10.1109\/ICCV.2019.00278"},{"issue":"12","key":"13_CR34","doi-asserted-by":"publisher","first-page":"2919","DOI":"10.1007\/s11263-020-01347-6","volume":"128","author":"H Xie","year":"2020","unstructured":"Xie, H., Yao, H., Zhang, S., Zhou, S., Sun, W.: Pix2Vox++: multi-scale context-aware 3D object reconstruction from single and multiple images. Int. J. Comput. Vis. 128(12), 2919\u20132935 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR35","unstructured":"Yagubbayli, F., Tonioni, A., Tombari, F.: LegoFormer: transformers for block-by-block multi-view 3D reconstruction. arXiv e-prints (2021). http:\/\/arxiv.org\/abs\/2106.12102"},{"issue":"1","key":"13_CR36","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s11263-019-01217-w","volume":"128","author":"B Yang","year":"2020","unstructured":"Yang, B., Wang, S., Markham, A., Trigoni, N.: Robust attentional aggregation of deep feature sets for multi-view 3D reconstruction. Int. J. Comput. Vis. 128(1), 53\u201373 (2020)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26319-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T06:08:53Z","timestamp":1677823733000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26319-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263187","9783031263194"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26319-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"4 March 2023","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":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"3.3","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":"2.6","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":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","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)"}}]}}