{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:41:57Z","timestamp":1781584917491,"version":"3.54.5"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012694","type":"print"},{"value":"9783030012700","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\/978-3-030-01270-0_16","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T22:07:51Z","timestamp":1538777271000},"page":"263-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":124,"title":["A Unified Framework for Multi-view Multi-class Object Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5957-5680","authenticated-orcid":false,"given":"Chi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0653-0542","authenticated-orcid":false,"given":"Jin","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6662-9763","authenticated-orcid":false,"given":"Gregory D.","family":"Hager","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"16_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: CVPR (2017)","DOI":"10.1109\/ICCV.2017.416"},{"key":"16_CR2","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). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_35"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Michel, F., Krull, A., Ying Yang, M., Gumhold, S., et al.: Uncertainty-driven 6d pose estimation of objects and scenes from a single rgb image. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.366"},{"key":"16_CR4","doi-asserted-by":"publisher","first-page":"021008","DOI":"10.1115\/1.4039121","volume":"10","author":"GS Chirikjian","year":"2018","unstructured":"Chirikjian, G.S., Mahony, R., Ruan, S., Trumpf, J.: Pose changes from a different point of view. J. Mech. Robot. 10, 021008 (2018)","journal-title":"J. Mech. Robot."},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Doumanoglou, A., Kouskouridas, R., Malassiotis, S., Kim, T.K.: Recovering 6d object pose and predicting next-best-view in the crowd. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.390"},{"key":"16_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-319-46478-7_10","volume-title":"Computer Vision \u2013 ECCV 2016","author":"\u00d6 Erkent","year":"2016","unstructured":"Erkent, \u00d6., Shukla, D., Piater, J.: Integration of probabilistic pose estimates from multiple views. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 154\u2013170. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_10"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"F. Tombari, S.S., Stefano, L.D.: A combined texture-shape descriptor for enhanced 3d feature matching. In: ICIP (2011)","DOI":"10.1109\/ICIP.2011.6116679"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. arXiv preprint arXiv:1504.08083 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"16_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":"16_CR12","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: JMLR (2015)"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Izadi, S., et al.: Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera. In: ACM symposium on User interface software and technology. ACM (2011)","DOI":"10.1145\/2047196.2047270"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Johns, E., Leutenegger, S., Davison, A.J.: Pairwise decomposition of image sequences for active multi-view recognition. In: CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.414"},{"key":"16_CR15","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: CVPR (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"16_CR16","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":"16_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Krull, A., Brachmann, E., Michel, F., Ying Yang, M., 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":"16_CR19","doi-asserted-by":"crossref","unstructured":"Lai, K., Bo, L., Ren, X., Fox, D.: Detection-based object labeling in 3d scenes. In: ICRA. IEEE (2012)","DOI":"10.1109\/ICRA.2012.6225316"},{"key":"16_CR20","series-title":"Springer Proceedings in Advanced Robotics","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-319-50115-4_16","volume-title":"2016 International Symposium on Experimental Robotics","author":"S Levine","year":"2017","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., Quillen, D.: Learning hand-eye coordination for robotic grasping with large-scale data collection. In: Kuli\u0107, D., Nakamura, Y., Khatib, O., Venture, G. (eds.) ISER 2016. SPAR, vol. 1, pp. 173\u2013184. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-50115-4_16"},{"key":"16_CR21","unstructured":"Li, C., Boheren, J., Carlson, E., Hager, G.D.: Hierarchical semantic parsing for object pose estimation in densely cluttered scenes. In: ICRA (2016)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Li, C., Xiao, H., Tateno, K., Tombari, F., Navab, N., Hager, G.D.: Incremental scene understanding on dense slam. In: IROS. IEEE (2016)","DOI":"10.1109\/IROS.2016.7759111"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Li, C., Zia, M.Z., Tran, Q.H., 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":"16_CR24","doi-asserted-by":"crossref","unstructured":"Massa, F., Marlet, R., Aubry, M.: Crafting a multi-task cnn for viewpoint estimation. In: BMVC (2016)","DOI":"10.5244\/C.30.91"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Michel, F., et al.: Global hypothesis generation for 6d object pose estimation. In: ICCV (2017)","DOI":"10.1109\/CVPR.2017.20"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Ko\u0161eck\u00e1, J.: 3d bounding box estimation using deep learning and geometry. In: CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"16_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-642-19315-6_11","volume-title":"Computer Vision \u2013 ACCV 2010","author":"C Papazov","year":"2011","unstructured":"Papazov, C., Burschka, D.: An efficient RANSAC for 3d object recognition in noisy and occluded scenes. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6492, pp. 135\u2013148. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19315-6_11"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Pillai, S., Leonard, J.: Monocular slam supported object recognition. In: RSS (2015)","DOI":"10.15607\/RSS.2015.XI.034"},{"key":"16_CR29","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":"16_CR30","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"16_CR31","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s13218-010-0059-6","volume":"24","author":"RB Rusu","year":"2010","unstructured":"Rusu, R.B.: Semantic 3d object maps for everyday manipulation in human living environments. KI-K\u00fcnstliche Intelligenz 24, 345\u2013348 (2010)","journal-title":"KI-K\u00fcnstliche Intelligenz"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Salas-Moreno, R., Newcombe, R., Strasdat, H., Kelly, P., Davison, A.: Slam++: simultaneous localisation and mapping at the level of objects. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.178"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3d shape recognition. In: CVPR, pp. 945\u2013953 (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"16_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: ICCV (2015)","DOI":"10.1109\/ICCV.2015.308"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Tateno, K., Tombari, F., Laina, I., Navab, N.: Cnn-slam: Real-time dense monocular slam with learned depth prediction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.695"},{"key":"16_CR36","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). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_30"},{"key":"16_CR37","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":"16_CR38","doi-asserted-by":"crossref","unstructured":"Tjaden, H., Schwanecke, U., Sch\u00f6mer, E.: Real-time monocular pose estimation of 3d objects using temporally consistent local color histograms. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.23"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Qiu, W., et al.: Unrealcv: virtual worlds for computer vision. In: ACM Multimedia Open Source Software Competition (2017)","DOI":"10.1145\/3123266.3129396"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Wohlhart, P., Lepetit, V.: Learning descriptors for object recognition and 3d pose estimation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Xiang, Y., et al.: Objectnet3d: a large scale database for 3d object recognition. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_10"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond PASCAL: a benchmark for 3d object detection in the wild. In: WACV (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6d object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Yan, Y., Chirikjian, G.S.: Almost-uniform sampling of rotations for conformational searches in robotics and structural biology. In: ICRA (2012)","DOI":"10.1109\/ICRA.2012.6225326"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Zeng, A., et al.: Multi-view self-supervised deep learning for 6d pose estimation in the amazon picking challenge. In: ICRA. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989165"}],"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\/978-3-030-01270-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:43:18Z","timestamp":1665016998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01270-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012694","9783030012700"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01270-0_16","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"}]}}