{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:19:37Z","timestamp":1781007577202,"version":"3.54.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585792","type":"print"},{"value":"9783030585808","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58580-8_16","type":"book-chapter","created":{"date-parts":[[2020,12,2]],"date-time":"2020-12-02T07:03:09Z","timestamp":1606892589000},"page":"260-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve"],"prefix":"10.1007","author":[{"given":"Weicheng","family":"Kuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anelia","family":"Angelova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsung-Yi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,12,3]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Avetisyan, A., Dahnert, M., Dai, A., Savva, M., Chang, A.X., Nie\u00dfner, M.: Scan2CAD: learning cad model alignment in RGB-D scans. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00272"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bansal, A., Russell, B., Gupta, A.: Marr revisited: 2D\u20133D alignment via surface normal prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5965\u20135974 (2016)","DOI":"10.1109\/CVPR.2016.642"},{"issue":"1","key":"16_CR3","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1177\/027836498200100103","volume":"1","author":"TO Binford","year":"1982","unstructured":"Binford, T.O.: Survey of model-based image analysis systems. Int. J. Robot. Res. 1(1), 18\u201364 (1982)","journal-title":"Int. J. Robot. Res."},{"key":"16_CR4","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Technical report. arXiv:1512.03012 [cs.GR], Stanford University \u2013 Princeton University \u2013 Toyota Technological Institute at Chicago (2015)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D.Y., Tian, X.P., Shen, Y.T., Ouhyoung, M.: On visual similarity based 3D model retrieval. In: Computer Graphics Forum, vol. 22, pp. 223\u2013232. Wiley Online Library (2003)","DOI":"10.1111\/1467-8659.00669"},{"issue":"1","key":"16_CR6","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1145\/6462.6464","volume":"18","author":"RT Chin","year":"1986","unstructured":"Chin, R.T., Dyer, C.R.: Model-based recognition in robot vision. ACM Comput. Surv. (CSUR) 18(1), 67\u2013108 (1986)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"16_CR7","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":"16_CR8","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the Computer Vision and Pattern Recognition (CVPR). IEEE (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Dai, A., Nie\u00dfner, M.: Scan2Mesh: from unstructured range scans to 3D meshes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5574\u20135583 (2019)","DOI":"10.1109\/CVPR.2019.00572"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3D object reconstruction from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 605\u2013613 (2017)","DOI":"10.1109\/CVPR.2017.264"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J., Johnson, J.: Mesh R-cnn. arXiv preprint arXiv:1906.02739 (2019)","DOI":"10.1109\/ICCV.2019.00988"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Grabner, A., Roth, P.M., Lepetit, V.: Location field descriptors: single image 3D model retrieval in the wild. In: 2019 International Conference on 3D Vision (3DV), pp. 583\u2013593. IEEE (2019)","DOI":"10.1109\/3DV.2019.00070"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: A papier-m\u00e2ch\u00e9 approach to learning 3D surface generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 216\u2013224 (2018)","DOI":"10.1109\/CVPR.2018.00030"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"16_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-01234-2_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Huang","year":"2018","unstructured":"Huang, S., Qi, S., Zhu, Y., Xiao, Y., Xu, Y., Zhu, S.-C.: Holistic 3D scene parsing and reconstruction from a single RGB image. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 194\u2013211. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_12"},{"key":"16_CR19","series-title":"Springer Series in Statistics (Perspectives in Statistics)","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-1-4612-4380-9_35","volume-title":"Breakthroughs in Statistics","author":"PJ Huber","year":"1992","unstructured":"Huber, P.J.: Robust estimation of a location parameter. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics. Springer Series in Statistics (Perspectives in Statistics), pp. 492\u2013518. Springer, New York (1992). https:\/\/doi.org\/10.1007\/978-1-4612-4380-9_35"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Izadinia, H., Seitz, S.M.: Scene recomposition by learning-based ICP. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00101"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Izadinia, H., Shan, Q., Seitz, S.M.: IM2CAD. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5134\u20135143 (2017)","DOI":"10.1109\/CVPR.2017.260"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Kim, Y.M., Mitra, N.J., Huang, Q., Guibas, L.: Guided real-time scanning of indoor objects. In: Computer Graphics Forum, vol. 32, pp. 177\u2013186. Wiley Online Library (2013)","DOI":"10.1111\/cgf.12225"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Kuo, W., Angelova, A., Malik, J., Lin, T.Y.: Shapemask: learning to segment novel objects by refining shape priors. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9207\u20139216 (2019)","DOI":"10.1109\/ICCV.2019.00930"},{"key":"16_CR24","unstructured":"Li, K., et al.: FroDO: from detections to 3D objects. arXiv preprint arXiv:2005.05125 (2020)"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Dai, A., Guibas, L., Nie\u00dfner, M.: Database-assisted object retrieval for real-time 3D reconstruction. In: Computer Graphics Forum, vol. 34, pp. 435\u2013446. Wiley Online Library (2015)","DOI":"10.1111\/cgf.12573"},{"issue":"6","key":"16_CR26","first-page":"1","volume":"34","author":"Y Li","year":"2015","unstructured":"Li, Y., Su, H., Qi, C.R., Fish, N., Cohen-Or, D., Guibas, L.J.: Joint embeddings of shapes and images via CNN image purification. ACM Trans. Graph. (TOG) 34(6), 1\u201312 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"16_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"16_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"16_CR30","unstructured":"Maaten, L.v.d., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)"},{"key":"16_CR31","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, pp. 4460\u20134470 (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"16_CR32","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 165\u2013174 (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"16_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Riegler, G., Osman Ulusoy, A., Geiger, A.: OctNet: Learning deep 3D representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3577\u20133586 (2017)","DOI":"10.1109\/CVPR.2017.701"},{"key":"16_CR37","unstructured":"Roberts, L.G.: Machine perception of three-dimensional solids. Ph.D. thesis, Massachusetts Institute of Technology (1963)"},{"issue":"6","key":"16_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2366145.2366155","volume":"31","author":"T Shao","year":"2012","unstructured":"Shao, T., Xu, W., Zhou, K., Wang, J., Li, D., Guo, B.: An interactive approach to semantic modeling of indoor scenes with an RGBD camera. ACM Trans. Graph. (TOG) 31(6), 1\u201311 (2012)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Pix3D: dataset and methods for single-image 3D shape modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2974\u20132983 (2018)","DOI":"10.1109\/CVPR.2018.00314"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Tang, J., Han, X., Pan, J., Jia, K., Tong, X.: A skeleton-bridged deep learning approach for generating meshes of complex topologies from single RGB images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4541\u20134550 (2019)","DOI":"10.1109\/CVPR.2019.00467"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Dosovitskiy, A., Brox, T.: Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2088\u20132096 (2017)","DOI":"10.1109\/ICCV.2017.230"},{"key":"16_CR42","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"},{"key":"16_CR43","unstructured":"Wu, J., Wang, Y., Xue, T., Sun, X., Freeman, B., Tenenbaum, J.: MarrNet: 3D shape reconstruction via 2.5 D sketches. In: Advances in Neural Information Processing Systems, pp. 540\u2013550 (2017)"},{"key":"16_CR44","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Advances in Neural Information Processing Systems, pp. 82\u201390 (2016)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4541\u20134550 (2019)","DOI":"10.1109\/ICCV.2019.00464"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58580-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:06:31Z","timestamp":1733097991000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58580-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585792","9783030585808"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58580-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 December 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","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":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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 due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 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)"}}]}}