{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:49:07Z","timestamp":1778082547444,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012304","type":"print"},{"value":"9783030012311","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01231-1_43","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T20:03:25Z","timestamp":1538769805000},"page":"712-729","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":338,"title":["Implicit 3D Orientation Learning for 6D Object Detection from RGB Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0587-9643","authenticated-orcid":false,"given":"Martin","family":"Sundermeyer","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3035-493X","authenticated-orcid":false,"given":"Zoltan-Csaba","family":"Marton","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8885-5334","authenticated-orcid":false,"given":"Maximilian","family":"Durner","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6370-2753","authenticated-orcid":false,"given":"Manuel","family":"Brucker","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7975-036X","authenticated-orcid":false,"given":"Rudolph","family":"Triebel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Balntas, V., Doumanoglou, A., Sahin, C., Sock, J., Kouskouridas, R., Kim, T.K.: Pose guided RGBD feature learning for 3D object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3856\u20133864 (2017)","DOI":"10.1109\/ICCV.2017.416"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., et al.: Using simulation and domain adaptation to improve efficiency of deep robotic grasping. arXiv preprint arXiv:1709.07857 (2017)","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.18"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Michel, F., Krull, A., Ying Yang, M., Gumhold, S., Rother, C.: Uncertainty-driven 6D pose estimation of objects and scenes from a single RGB image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3364\u20133372 (2016)","DOI":"10.1109\/CVPR.2016.366"},{"key":"43_CR5","unstructured":"Csurka, G.: Domain adaptation for visual applications: a comprehensive survey. arXiv preprint arXiv:1702.05374 (2017)"},{"key":"43_CR6","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC 2012) results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"key":"43_CR7","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 249\u2013256 (2010)"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., Benhimane, S., Lepetit, V., Fua, P., Navab, N.: Simultaneous recognition and homography extraction of local patches with a simple linear classifier. In: Proceedings of the British Machine Conference (BMVC), pp. 1\u201310 (2008)","DOI":"10.5244\/C.22.10"},{"issue":"5","key":"43_CR9","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1109\/TPAMI.2011.206","volume":"34","author":"S Hinterstoisser","year":"2012","unstructured":"Hinterstoisser, S., Cagniart, C., Ilic, S., Sturm, P., Navab, N., Fua, P., Lepetit, V.: Gradient response maps for real-time detection of textureless objects. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 876\u2013888 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., et al.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 858\u2013865. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"43_CR11","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). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42"},{"key":"43_CR12","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). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_51"},{"key":"43_CR13","unstructured":"Hinterstoisser, S., Lepetit, V., Wohlhart, P., Konolige, K.: On pre-trained image features and synthetic images for deep learning. arXiv preprint arXiv:1710.10710 (2017)"},{"key":"43_CR14","unstructured":"Hodan, T.: SIXD Challenge (2017). http:\/\/cmp.felk.cvut.cz\/sixd\/challenge_2017\/"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Hoda\u0148, T., Haluza, P., Obdr\u017e\u00e1lek, \u0160., Matas, J., Lourakis, M., Zabulis, X.: T-LESS: an RGB-D dataset for 6D pose estimation of texture-less objects. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2017)","DOI":"10.1109\/WACV.2017.103"},{"key":"43_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/978-3-319-49409-8_52","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"T Hoda\u0148","year":"2016","unstructured":"Hoda\u0148, T., Matas, J., Obdr\u017e\u00e1lek, \u0160.: On evaluation of 6D object pose estimation. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 606\u2013619. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_52"},{"key":"43_CR17","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521\u20131529 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"43_CR18","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\u00a0object 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). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_13"},{"key":"43_CR19","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"43_CR21","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":"43_CR22","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":"43_CR23","doi-asserted-by":"crossref","unstructured":"Mahendran, S., Ali, H., Vidal, R.: 3D pose regression using convolutional neural networks. arXiv preprint arXiv:1708.05628 (2017)","DOI":"10.1109\/ICCVW.2017.254"},{"key":"43_CR24","unstructured":"Matthey, L., Higgins, I., Hassabis, D., Lerchner, A.: dSprites: disentanglement testing sprites dataset (2017). https:\/\/github.com\/deepmind\/dsprites-dataset\/"},{"key":"43_CR25","doi-asserted-by":"crossref","unstructured":"Mitash, C., Bekris, K.E., Boularias, A.: A self-supervised learning system for object detection using physics simulation and multi-view pose estimation. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 545\u2013551. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202206"},{"key":"43_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-319-49409-8_18","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"Y Movshovitz-Attias","year":"2016","unstructured":"Movshovitz-Attias, Y., Kanade, T., Sheikh, Y.: How useful is photo-realistic rendering for visual learning? In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 202\u2013217. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_18"},{"issue":"6","key":"43_CR27","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1145\/360825.360839","volume":"18","author":"BT Phong","year":"1975","unstructured":"Phong, B.T.: Illumination for computer generated pictures. Commun. ACM 18(6), 311\u2013317 (1975)","journal-title":"Commun. ACM"},{"key":"43_CR28","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: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.413"},{"key":"43_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), pp. 91\u201399 (2015)"},{"key":"43_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-46475-6_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"SR Richter","year":"2016","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102\u2013118. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7"},{"key":"43_CR31","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Technical report, California University, Institute for Cognitive Science, San Diego, La Jolla (1985)","DOI":"10.21236\/ADA164453"},{"key":"43_CR32","doi-asserted-by":"crossref","unstructured":"Saxena, A., Driemeyer, J., Ng, A.Y.: Learning 3D object orientation from images. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 794\u2013800. IEEE (2009)","DOI":"10.1109\/ROBOT.2009.5152855"},{"key":"43_CR33","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2242\u20132251. IEEE (2017)","DOI":"10.1109\/CVPR.2017.241"},{"key":"43_CR34","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., Guibas, L.J.: Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2686\u20132694 (2015)","DOI":"10.1109\/ICCV.2015.308"},{"key":"43_CR35","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., Fua, P.: Real-time seamless single shot 6D object pose prediction. arXiv preprint arXiv:1711.08848 (2017)","DOI":"10.1109\/CVPR.2018.00038"},{"key":"43_CR36","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 23\u201330. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"43_CR37","doi-asserted-by":"crossref","unstructured":"Ulrich, M., Wiedemann, C., Steger, C.: CAD-based recognition of 3D objects in monocular images. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), vol. 9, pp. 1191\u20131198 (2009)","DOI":"10.1109\/ROBOT.2009.5152511"},{"key":"43_CR38","doi-asserted-by":"crossref","unstructured":"Vidal, J., Lin, C.Y., Mart\u00ed, R.: 6D pose estimation using an improved method based on point pair features. arXiv preprint arXiv:1802.08516 (2018)","DOI":"10.1109\/ICCAR.2018.8384709"},{"issue":"Dec","key":"43_CR39","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(Dec), 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"43_CR40","doi-asserted-by":"crossref","unstructured":"Wohlhart, P., Lepetit, V.: Learning descriptors for object recognition and 3D pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3109\u20133118 (2015)","DOI":"10.1109\/CVPR.2015.7298930"},{"issue":"2","key":"43_CR41","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/BF01427149","volume":"13","author":"Z Zhang","year":"1994","unstructured":"Zhang, Z.: Iterative point matching for registration of free-form curves and surfaces. Int. J. Comput. Vis. 13(2), 119\u2013152 (1994)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01231-1_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:16:27Z","timestamp":1664928987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01231-1_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012304","9783030012311"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01231-1_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","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":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}