{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:13:39Z","timestamp":1781021619793,"version":"3.54.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585358","type":"print"},{"value":"9783030585365","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\/978-3-030-58536-5_22","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T23:02:42Z","timestamp":1604358162000},"page":"366-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["CoReNet: Coherent 3D Scene Reconstruction from a Single RGB Image"],"prefix":"10.1007","author":[{"given":"Stefan","family":"Popov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Bauszat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vittorio","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"22_CR1","unstructured":"https:\/\/github.com\/google-research\/corenet"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A.R., Blaschko, M.B.: The Lov\u00e1sz-Softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00464"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Chang, A.X., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 2017 International Conference on 3D Vision (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"22_CR4","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. CoRR abs\/1512.03012 (2015). http:\/\/arxiv.org\/abs\/1512.03012"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Tagliasacchi, A., Zhang, H.: BSP-Net: generating compact meshes via binary space partitioning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00012"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00609"},{"key":"22_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":"22_CR8","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.264"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J., Johnson, J.: Mesh R-CNN. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00988"},{"key":"22_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-319-46466-4_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Girdhar","year":"2016","unstructured":"Girdhar, R., Fouhey, D.F., Rodriguez, M., Gupta, A.: Learning a predictable and generative vector representation for objects. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 484\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_29"},{"key":"22_CR11","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00030"},{"key":"22_CR12","volume-title":"Multiple View Geometry in Computer Vision","author":"RI Hartley","year":"2000","unstructured":"Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000). ISBN 0521623049"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Izadinia, H., Shan, Q., Seitz, S.M.: IM2CAD. In: CVPR, pp. 2422\u20132431 (2017)","DOI":"10.1109\/CVPR.2017.260"},{"key":"22_CR16","unstructured":"Kar, A., H\u00e4ne, C., Malik, J.: Learning a multi-view stereo machine. In: NIPS (2017)"},{"key":"22_CR17","unstructured":"Krasin, I., et al.: OpenImages: a public dataset for large-scale multi-label and multi-class image classification (2017). Dataset https:\/\/g.co\/dataset\/openimages"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Kundu, A., Li, Y., Rehg, J.M.: 3D-RCNN: instance-level 3D object reconstruction via render-and-compare. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00375"},{"key":"22_CR19","unstructured":"Kuznetsova, A., et al.: The Open Images Dataset V4: unified image classification, object detection, and visual relationship detection at scale. arXiv preprint arXiv:1811.00982 (2018)"},{"issue":"2","key":"22_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10867651.2003.10487582","volume":"8","author":"T Lewiner","year":"2003","unstructured":"Lewiner, T., Lopes, H., Vieira, A.W., Tavares, G.: Efficient implementation of marching cubes\u2019 cases with topological guarantees. J. Graph. GPU Game Tools 8(2), 1\u201315 (2003)","journal-title":"J. Graph. GPU Game Tools"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Liao, Y., Donn\u00e9, S., Geiger, A.: Deep marching cubes: learning explicit surface representations. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00308"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"issue":"4","key":"22_CR23","doi-asserted-by":"publisher","first-page":"65:1","DOI":"10.1145\/3306346.3323020","volume":"38","author":"S Lombardi","year":"2019","unstructured":"Lombardi, S., Simon, T., Saragih, J., Schwartz, G., Lehrmann, A., Sheikh, Y.: Neural volumes: learning dynamic renderable volumes from images. ACM Trans. Graph. 38(4), 65:1\u201365:14 (2019)","journal-title":"ACM Trans. Graph."},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Mandikal, P., Navaneet, K.L., Agarwal, M., Radhakrishnan, V.B.: 3D-LMNet: latent embedding matching for accurate and diverse 3D point cloud reconstruction from a single image. In: BMVC (2018)","DOI":"10.1007\/978-3-030-11015-4_50"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Mescheder, L.M., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"22_CR26","unstructured":"Nguyen-Phuoc, T., Li, C., Balaban, S., Yang, Y.: RenderNet: a deep convolutional network for differentiable rendering from 3D shapes. In: NIPS (2018)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.L.: HoloGAN: unsupervised learning of 3D representations from natural images. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00768"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Nicastro, A., Clark, R., Leutenegger, S.: X-Section: cross-section prediction for enhanced RGB-D fusion. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00160"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Nie, Y., Han, X., Guo, S., Zheng, Y., Chang, J., Zhang, J.J.: Total3DUnderstanding: joint layout, object pose and mesh reconstruction for indoor scenes from a single image. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Niu, C., Li, J., Xu, K.: Im2Struct: recovering 3D shape structure from a single RGB image. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00475"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R.A., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"22_CR32","volume-title":"Physically Based Rendering: From Theory to Implementation","author":"M Pharr","year":"2016","unstructured":"Pharr, M., Jakob, W., Humphreys, G.: Physically Based Rendering: From Theory to Implementation, 3rd edn. Morgan Kaufmann Publishers Inc., San Francisco (2016)","edition":"3"},{"key":"22_CR33","unstructured":"Richter, S.R., Roth, S.: Matryoshka networks: predicting 3D geometry via nested shape layers. In: CVPR (2018)"},{"key":"22_CR34","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Shin, D., Fowlkes, C.C., Hoiem, D.: Pixels, voxels, and views: a study of shape representations for single view 3D object shape prediction. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00323"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., Niessner, M., Wetzstein, G., Zollhofer, M.: DeepVoxels: learning persistent 3D feature embeddings. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00254"},{"key":"22_CR37","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. In: NIPS (2019)"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Soltani, A.A., Huang, H., Wu, J., Kulkarni, T.D., Tenenbaum, J.B.: Synthesizing 3D shapes via modeling multi-view depth maps and silhouettes with deep generative networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.269"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"22_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-319-67558-9_28","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"CH Sudre","year":"2017","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA\/ML-CDS 2017. LNCS, vol. 10553, pp. 240\u2013248. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-67558-9_28"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Pix3D: dataset and methods for single-image 3D shape modeling. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00314"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Richter, S.R., Ranftl, R., Li, Z., Koltun, V., Brox, T.: What do single-view 3D reconstruction networks learn? In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00352"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Gupta, S., Fouhey, D.F., Efros, A.A., Malik, J.: Factoring shape, pose, and layout from the 2D image of a 3D scene. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00039"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Su, H., Guibas, L.J., Efros, A.A., Malik, J.: Learning shape abstractions by assembling volumetric primitives. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.160"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Tung, H.F., Cheng, R., Fragkiadaki, K.: Learning spatial common sense with geometry-aware recurrent networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00270"},{"key":"22_CR46","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":"22_CR47","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W.T., Tenenbaum, J.B.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: NIPS (2016)"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K., Oliva, A., Torralba, A.: SUN database: large-scale scene recognition from abbey to zoo. In: CVPR, pp. 3485\u20133492 (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"22_CR49","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00278"},{"key":"22_CR50","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. IJCV 128, 2919\u20132935 (2020)","journal-title":"IJCV"},{"key":"22_CR51","doi-asserted-by":"crossref","unstructured":"Yao, Y., Schertler, N., Rosales, E., Rhodin, H., Sigal, L., Sheffer, A.: Front2Back: single view 3D shape reconstruction via front to back prediction. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00061"},{"key":"22_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_26"}],"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\/978-3-030-58536-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:42:00Z","timestamp":1730594520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58536-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585358","9783030585365"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58536-5_22","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 November 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)"}}]}}