{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:46:57Z","timestamp":1752101217913},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208929"},{"type":"electronic","value":"9783030208936"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-20893-6_30","type":"book-chapter","created":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:25:52Z","timestamp":1559013952000},"page":"477-492","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects"],"prefix":"10.1007","author":[{"given":"Omid","family":"Hosseini\u00a0Jafari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siva Karthik","family":"Mustikovela","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karl","family":"Pertsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Brachmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carsten","family":"Rother","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"30_CR1","unstructured":"Alhaija, H.A., Mustikovela, S.K., Mescheder, L., Geiger, A., Rother, C.: Augmented reality meets deep learning for car instance segmentation in urban scenes. In: BMVC (2017)"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Behl, A., Hosseini Jafari, O., Mustikovela, S.K., Alhaija, H.A., Rother, C., Geiger, A.: Bounding boxes, segmentations and object coordinates: how important is recognition for 3D scene flow estimation in autonomous driving scenarios? In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.281"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Michel, F., Krull, A., Yang, M.Y., Gumhold, S., Rother, C.: Uncertainty-driven 6D pose estimation of objects and scenes from a single RGB image. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.366"},{"key":"30_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-319-10605-2_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"E Brachmann","year":"2014","unstructured":"Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6D object pose estimation using 3D object coordinates. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 536\u2013551. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10605-2_35"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Brachmann, E., et al.: DSAC-differentiable RANSAC for camera localization. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.267"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.343"},{"key":"30_CR7","unstructured":"Doumanoglou, A., Kouskouridas, R., Malassiotis, S., Kim, T.: 6D object detection and next-best-view prediction in the crowd. In: CVPR (2016)"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: efficient and robust 3D object recognition. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.470"},{"key":"30_CR10","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TPAMI.2003.1217599","volume":"25","author":"XS Gao","year":"2003","unstructured":"Gao, X.S., Hou, X.R., Tang, J., Cheng, H.F.: Complete solution classification for the perspective-three-point problem. IEEE Trans. PAMI 25, 930\u2013943 (2003)","journal-title":"IEEE Trans. PAMI"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"30_CR13","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1109\/TPAMI.2011.206","volume":"34","author":"S Hinterstoisser","year":"2012","unstructured":"Hinterstoisser, S., et al.: Gradient response maps for real-time detection of texture-less objects. IEEE Trans. PAMI 34, 876\u2013888 (2012)","journal-title":"IEEE Trans. PAMI"},{"key":"30_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","volume-title":"Computer Vision \u2013 ACCV 2012","author":"S Hinterstoisser","year":"2013","unstructured":"Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548\u2013562. Springer, Heidelberg (2013). \n                      https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., et al.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"30_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-46487-9_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Hinterstoisser","year":"2016","unstructured":"Hinterstoisser, S., Lepetit, V., Rajkumar, N., Konolige, K.: Going further with point pair features. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 834\u2013848. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46487-9_51"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Hoda\u0148, T., Zabulis, X., Lourakis, M., Obdr\u017e\u00e1lek, \u0160., Matas, J.: Detection and fine 3D pose estimation of texture-less objects in RGB-D images. In: IROS (2015)","DOI":"10.1109\/IROS.2015.7354005"},{"key":"30_CR18","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1109\/34.232073","volume":"15","author":"D Huttenlocher","year":"1993","unstructured":"Huttenlocher, D., Klanderman, G., Rucklidge, W.: Comparing images using the Hausdorff distance. IEEE Trans. PAMI 15, 850\u2013863 (1993)","journal-title":"IEEE Trans. PAMI"},{"key":"30_CR19","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1107\/S0567739476001873","volume":"32","author":"W Kabsch","year":"1976","unstructured":"Kabsch, W.: A solution for the best rotation to relate two sets of vectors. Acta Crystallogr. 32, 922\u2013923 (1976)","journal-title":"Acta Crystallogr."},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"30_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-319-46487-9_13","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Kehl","year":"2016","unstructured":"Kehl, W., Milletari, F., Tombari, F., Ilic, S., Navab, N.: Deep learning of local RGB-D patches for 3D object detection and 6D pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 205\u2013220. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46487-9_13"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Kehl, W., Tombari, F., Navab, N., Ilic, S., Lepetit, V.: Hashmod: a hashing method for scalable 3D object detection. In: BMVC (2016)","DOI":"10.5244\/C.29.36"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"30_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"30_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/978-3-319-46448-0_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Konishi","year":"2016","unstructured":"Konishi, Y., Hanzawa, Y., Kawade, M., Hashimoto, M.: Fast 6D pose estimation from a monocular image using hierarchical pose trees. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 398\u2013413. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_24"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Krull, A., Brachmann, E., Michel, F., Yang, M.Y., Gumhold, S., Rother, C.: Learning analysis-by-synthesis for 6D pose estimation in RGB-D images. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.115"},{"key":"30_CR27","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"V Lepetit","year":"2009","unstructured":"Lepetit, V., Moreno-Noguer, F., Fua, P.: EPNP: An accurate O(n) solution to the PnP problem. IJCV 81, 155 (2009)","journal-title":"IJCV"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Li, C., Zia, M.Z., Tran, Q., Yu, X., Hager, G.D., Chandraker, M.: Deep supervision with shape concepts for occlusion-aware 3D object parsing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.49"},{"key":"30_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). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"30_CR30","unstructured":"Lowe, D.G.: Local feature view clustering for 3D object recognition. In: CVPR (2001)"},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Michel, F., et al.: Global hypothesis generation for 6D object pose estimation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.20"},{"key":"30_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). \n                      https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Rad, M., Lepetit, V.: BB8: a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.413"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Rios-Cabrera, R., Tuytelaars, T.: Discriminatively trained templates for 3D object detection: a real time scalable approach. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.256"},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.W.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.377"},{"key":"30_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1007\/978-3-319-10599-4_30","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Tejani","year":"2014","unstructured":"Tejani, A., Tang, D., Kouskouridas, R., Kim, T.-K.: Latent-class hough forests for 3D object detection and pose estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 462\u2013477. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10599-4_30"},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., Fua, P.: Real time seamless single shot 6D object pose prediction. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00038"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Zach, C., Penate-Sanchez, A., Pham, M.T.: A dynamic programming approach for fast and robust object pose recognition from range images. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298615"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20893-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:52:45Z","timestamp":1559015565000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20893-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208929","9783030208936"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20893-6_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 May 2019","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - 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"}},{"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"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}