{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:40:18Z","timestamp":1756309218477,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031314377"},{"type":"electronic","value":"9783031314384"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-31438-4_31","type":"book-chapter","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T08:02:53Z","timestamp":1682496173000},"page":"467-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MSDA: Monocular Self-supervised Domain Adaptation for\u00a06D Object Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4286-6358","authenticated-orcid":false,"given":"Dingding","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0073-0866","authenticated-orcid":false,"given":"Janne","family":"Heikkil\u00e4","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8767-0864","authenticated-orcid":false,"given":"Esa","family":"Rahtu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Cai, D., Heikkil\u00e4, J., Rahtu, E.: Ove6d: object viewpoint encoding for depth-based 6d object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6803\u20136813 (2022)","DOI":"10.1109\/CVPR52688.2022.00668"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Cai, D., Heikkil\u00e4, J., Rahtu, E.: Sc6d: symmetry-agnostic and correspondence-free 6d object pose estimation. arXiv preprint arXiv:2208.02129 (2022)","DOI":"10.1109\/3DV57658.2022.00065"},{"key":"31_CR3","unstructured":"Chen, W., et al.: Learning to predict 3D objects with an interpolation-based differentiable renderer. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"issue":"10","key":"31_CR4","doi-asserted-by":"publisher","first-page":"1284","DOI":"10.1177\/0278364911401765","volume":"30","author":"A Collet","year":"2011","unstructured":"Collet, A., Martinez, M., Srinivasa, S.S.: The moped framework: object recognition and pose estimation for manipulation. Int. J. Rob. Res. 30(10), 1284\u20131306 (2011)","journal-title":"Int. J. Rob. Res."},{"key":"31_CR5","unstructured":"Denninger, M., et al.: Blenderproc: reducing the reality gap with photorealistic rendering. In: International Conference on Robotics: Sciene and Systems, RSS 2020 (2020)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Di, Y., Manhardt, F., Wang, G., Ji, X., Navab, N., Tombari, F.: So-pose: exploiting self-occlusion for direct 6d pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12396\u201312405 (2021)","DOI":"10.1109\/ICCV48922.2021.01217"},{"issue":"6","key":"31_CR7","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"31_CR8","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":"31_CR9","doi-asserted-by":"crossref","unstructured":"He, Y., Huang, H., Fan, H., Chen, Q., Sun, J.: Ffb6d: a full flow bidirectional fusion network for 6d pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3003\u20133013 (2021)","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"31_CR10","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":"31_CR11","doi-asserted-by":"crossref","unstructured":"Hodan, T., Barath, D., Matas, J.: Epos: estimating 6d pose of objects with symmetries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11703\u201311712 (2020)","DOI":"10.1109\/CVPR42600.2020.01172"},{"key":"31_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/978-3-030-66096-3_39","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"T Hoda\u0148","year":"2020","unstructured":"Hoda\u0148, T., et al.: BOP challenge 2020 on 6D object localization. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 577\u2013594. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66096-3_39"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Hu, Y., Fua, P., Wang, W., Salzmann, M.: Single-stage 6d object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2930\u20132939 (2020)","DOI":"10.1109\/CVPR42600.2020.00300"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Hu, Y., Hugonot, J., Fua, P., Salzmann, M.: Segmentation-driven 6d object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3385\u20133394 (2019)","DOI":"10.1109\/CVPR.2019.00350"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Iwase, S., Liu, X., Khirodkar, R., Yokota, R., Kitani, K.M.: Repose: fast 6d object pose refinement via deep texture rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3303\u20133312 (2021)","DOI":"10.1109\/ICCV48922.2021.00329"},{"key":"31_CR16","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"},{"issue":"2","key":"31_CR17","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. Int. J. Comput. Vision 81(2), 155 (2009)","journal-title":"Int. J. Comput. Vision"},{"key":"31_CR18","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":"31_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"issue":"12","key":"31_CR20","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1109\/TVCG.2015.2513408","volume":"22","author":"E Marchand","year":"2015","unstructured":"Marchand, E., Uchiyama, H., Spindler, F.: Pose estimation for augmented reality: a hands-on survey. IEEE Trans. Vis. Comput. Graph. 22(12), 2633\u20132651 (2015)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Park, K., Mousavian, A., Xiang, Y., Fox, D.: Latentfusion: end-to-end differentiable reconstruction and rendering for unseen object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10710\u201310719 (2020)","DOI":"10.1109\/CVPR42600.2020.01072"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Park, K., Patten, T., Vincze, M.: Pix2pose: pixel-wise coordinate regression of objects for 6d pose estimation. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00776"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Peng, S., Zhou, X., Liu, Y., Lin, H., Huang, Q., Bao, H.: Pvnet: pixel-wise voting network for 6dof object pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. (2020)","DOI":"10.1109\/CVPR.2019.00469"},{"key":"31_CR24","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, pp. 3828\u20133836 (2017)","DOI":"10.1109\/ICCV.2017.413"},{"issue":"3","key":"31_CR25","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: Zebrapose: coarse to fine surface encoding for 6dof object pose estimation. arXiv preprint arXiv:2203.09418 (2022)","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., et al.: Multi-path learning for object pose estimation across domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13916\u201313925 (2020)","DOI":"10.1109\/CVPR42600.2020.01393"},{"key":"31_CR28","unstructured":"Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. arXiv preprint arXiv:1809.10790 (2018)"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Densefusion: 6d object pose estimation by iterative dense fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3343\u20133352 (2019)","DOI":"10.1109\/CVPR.2019.00346"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Wang, G., Manhardt, F., Liu, X., Ji, X., Tombari, F.: Occlusion-aware self-supervised monocular 6d object pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3136301"},{"key":"31_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58452-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Wang","year":"2020","unstructured":"Wang, G., Manhardt, F., Shao, J., Ji, X., Navab, N., Tombari, F.: Self6D: self-supervised monocular 6D object pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 108\u2013125. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_7"},{"key":"31_CR32","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16611\u201316621 (2021)","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"31_CR33","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. In: Proceedings of Robotics: Science and Systems (RSS) (2018)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: Dpod: 6d pose object detector and refiner. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1941\u20131950 (2019)","DOI":"10.1109\/ICCV.2019.00203"}],"container-title":["Lecture Notes in Computer Science","Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-31438-4_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T09:08:57Z","timestamp":1685351337000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-31438-4_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031314377","9783031314384"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-31438-4_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 April 2023","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":"Lapland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"scia2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/scia2023\/","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":"CMT 3","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"108","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":"67","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":"62% - 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":"5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}