{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:43:22Z","timestamp":1774680202022,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031959172","type":"print"},{"value":"9783031959189","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-95918-9_14","type":"book-chapter","created":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T13:31:02Z","timestamp":1750512662000},"page":"196-209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EfficientPose 6D: Scalable and\u00a0Efficient 6D Object Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1926-8023","authenticated-orcid":false,"given":"Zixuan","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0075-1181","authenticated-orcid":false,"given":"Thomas","family":"P\u00f6llabauer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2445-9081","authenticated-orcid":false,"given":"Tristan","family":"Wirth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-1414","authenticated-orcid":false,"given":"Sarah","family":"Berkei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6993-5099","authenticated-orcid":false,"given":"Volker","family":"Knauthe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6413-0061","authenticated-orcid":false,"given":"Arjan","family":"Kuijper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"14_CR1","unstructured":"BOP: Benchmark for 6D Object Pose Estimation. https:\/\/bop.felk.cvut.cz\/leaderboards\/"},{"key":"14_CR2","unstructured":"Cai, H., Gan, C., Han, S.: Efficientvit: enhanced linear attention for high-resolution low-computation visual recognition. arXiv preprint arXiv:2205.14756 (2022)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Deng, X., Xiang, Y., Mousavian, A., Eppner, C., Bretl, T., Fox, D.: Self-supervised 6d object pose estimation for robot manipulation. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 3665\u20133671. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196714"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Drost, B., Ulrich, M., Bergmann, P., Hartinger, P., Steger, C.:Introducing mvtec itodd-a dataset for 3d object recognition in industry. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp.2200\u20132208 (017)","DOI":"10.1109\/ICCVW.2017.257"},{"key":"14_CR5","unstructured":"Gonzalez, S., Miikkulainen, R.: Effective regularization through loss-function metalearning. arXiv:2010.00788 (2020)"},{"issue":"3","key":"14_CR6","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3390\/jimaging8030053","volume":"8","author":"F Gorschl\u00fcter","year":"2022","unstructured":"Gorschl\u00fcter, F., Rojtberg, P., P\u00f6llabauer, T.: A survey of 6d object detection based on 3d models for industrial applications. J. Imaging 8(3), 53 (2022)","journal-title":"J. Imaging"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Haugaard, R.L., Buch, A.G.: Surfemb: dense and continuous correspondence distributions for object pose estimation with learnt surface embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6749\u20136758 (2022)","DOI":"10.1109\/CVPR52688.2022.00663"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Hodan, 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: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 880\u2013888. IEEE (2017)","DOI":"10.1109\/WACV.2017.103"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Hodan, T., et al.: Bop challenge 2023 on detection segmentation and pose estimation of seen and unseen rigid objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5610\u20135619 (2024)","DOI":"10.1109\/CVPRW63382.2024.00570"},{"key":"14_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58520-4_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Labb\u00e9","year":"2020","unstructured":"Labb\u00e9, Y., Carpentier, J., Aubry, M., Sivic, J.: CosyPose: consistent multi-view multi-object 6D Pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_34"},{"key":"14_CR11","unstructured":"Li, J., et al.: Next-vit: next generation vision transformer for efficient deployment in realistic industrial scenarios. arXiv:2207.05501 (2022)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, G., Ji. X.: CDPN: coordinates-based disentangled pose network for real-time RGB-based 6-DOF object pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7678\u20137687 (2019)","DOI":"10.1109\/ICCV.2019.00777"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Liang, Y., Chen, F., Liang, G., Wu, X., Feng, W.: An efficient lightweight deep neural network for real-time object 6d pose estimation with RGB-D inputs. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9534175"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Liu, F., Hu, Y., Salzmann, M.: Linear-covariance loss for end-to-end learning of 6D pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14107\u201314117 (2023)","DOI":"10.1109\/ICCV51070.2023.01297"},{"key":"14_CR15","unstructured":"Liu, X.: Gdrnpp for bp2022 (2024). https:\/\/github.com\/shanice-l\/gdrnpp_bop2022"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"P\u00f6llabauer, T., Li, J., Knauthe, V., Berkei, S., Kuijper, A.: End-to-end probabilistic geometry-guided regression for 6dof object pose estimation. arXiv:2409.11819 (2024)","DOI":"10.1109\/AIxVR63409.2025.00014"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"P\u00f6llabauer, T., Emrich, J., Knauthe, V., Kuijper, A.: Extending 6d object pose estimators for stereo vision. In: Pattern Recognition and Artificial Intelligence. LNCS, vol. 14893 (2024)","DOI":"10.1007\/978-981-97-8705-0_8"},{"key":"14_CR18","unstructured":"P\u00f6llabauer, T., Pramod, A., Knauthe, V., Wahl, M.: Fast gdrnpp: improving the speed of state-of-the-art 6d object pose estimation. arXiv:2409.12720 (2024)"},{"key":"14_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: Zebrapose: coarse to fine surface encoding for 6DOF object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6738\u20136748 (2022)","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"14_CR22","unstructured":"Timm (PyTorch Image Models) (2024). https:\/\/huggingface.co\/timm"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: Maxvit: multi-axis vision transformer. In: European Conference on Computer Vision, pp. 459\u2013479. Springer (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"14_CR24","unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., Tuzel, O., Ranjan, A.: Fastvit: a fast hybrid vision transformer using structural reparameterization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5785\u20135795 (2023)"},{"issue":"7","key":"14_CR25","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.3390\/electronics13071321","volume":"13","author":"F Wang","year":"2024","unstructured":"Wang, F.: A lightweight 6d pose estimation network based on improved atrous spatial pyramid pooling. Electronics 13(7), 1321 (2024)","journal-title":"Electronics"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Wang, G., Manhardt, F., Tombari, F., Ji, X.: Gdr-net: geometry-guided direct regression network for monocular 6d object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16611\u201316621 (2021)","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: Convnext v2: co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"14_CR28","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:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token vit: training vision transformers from scratch on imagenet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"}],"container-title":["Lecture Notes in Computer Science","Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-95918-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T05:17:56Z","timestamp":1774675076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-95918-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031959172","9783031959189"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-95918-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"16 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SCIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Scandinavian Conference on Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Reykjavik","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iceland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"scia2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/scia2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}