{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T22:47:39Z","timestamp":1772837259109,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51975119"],"award-info":[{"award-number":["51975119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52375487"],"award-info":[{"award-number":["52375487"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2023041"],"award-info":[{"award-number":["BE2023041"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02317-y","type":"journal-article","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T03:27:51Z","timestamp":1733542071000},"page":"2620-2634","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Object Pose Estimation Based on Multi-precision Vectors and Seg-Driven PnP"],"prefix":"10.1007","volume":"133","author":[{"given":"Yulin","family":"Wang","sequence":"first","affiliation":[]},{"given":"Hongli","family":"Li","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Luo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"2317_CR1","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., et\u00a0al. (2017). Unsupervised pixel-level domain adaptation with generative adversarial networks. In CVPR, pp. 95-104.","DOI":"10.1109\/CVPR.2017.18"},{"key":"2317_CR2","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Krull, A., Michel, F., et\u00a0al. (2014). Learning 6d object pose estimation using 3d object coordinates. In ECCV, pp. 536-551.","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"2317_CR3","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Michel, F., Krull, A., et\u00a0al. (2016). Uncertainty-driven 6d pose estimation of objects and scenes from a single rgb image. In CVPR, pp. 3364-3372.","DOI":"10.1109\/CVPR.2016.366"},{"key":"2317_CR4","doi-asserted-by":"crossref","unstructured":"Capellen, C., Schwarz, M., & Behnke, S. (2020). Convposecnn: Dense convolutional 6d object pose estimation. In VISIGRAPP, pp. 162-172.","DOI":"10.5220\/0008990901620172"},{"key":"2317_CR5","doi-asserted-by":"crossref","unstructured":"Chen, B., Chin, T.J., & Klimavicius, M. (2022a). Occlusion-robust object pose estimation with holistic representation. In WACV, pp. 2223-2233.","DOI":"10.1109\/WACV51458.2022.00228"},{"key":"2317_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, P., Wang, F., et\u00a0al. (2022b). Epro-pnp: Generalized end-to-end probabilistic perspective-n-points for monocular object pose estimation. In CVPR, pp. 2771-2780.","DOI":"10.1109\/CVPR52688.2022.00280"},{"key":"2317_CR7","unstructured":"Do, T.T., Cai, M., Pham, T., et\u00a0al. (2018a). Deep-6dpose: Recovering 6d object pose from a single rgb image. Preprint at arXiv:1802.10367."},{"key":"2317_CR8","unstructured":"Do, T.T., Pham, T., Cai, M., et\u00a0al. (2018b). Real-time monocular object instance 6d pose estimation. In BMVC."},{"issue":"3","key":"2317_CR9","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1007\/s10462-020-09888-5","volume":"54","author":"G Du","year":"2021","unstructured":"Du, G., Wang, K., Lian, S., et al. (2021). Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review. Artificial Intelligence Review, 54(3), 1677\u20131734.","journal-title":"Artificial Intelligence Review"},{"issue":"2","key":"2317_CR10","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He, K., Gkioxari, G., Dollar, P., et al. (2020). Mask r-cnn. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2), 386\u2013397.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2317_CR11","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., Lepetit, V., Ilic, S., et\u00a0al. (2013). Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In ACCV, pp. 548-562.","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"2317_CR12","doi-asserted-by":"crossref","unstructured":"Hoda, T., Michel, F., Brachmann, E., et\u00a0al. (2018). Bop: Benchmark for 6d object pose estimation. In ECCV, pp. 19-35.","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"2317_CR13","doi-asserted-by":"crossref","unstructured":"Hoda, T., Sundermeyer, M., Drost, B., et\u00a0al. (2020). Bop challenge 2020 on 6d object localization. In ECCV, pp. 577-594.","DOI":"10.1007\/978-3-030-66096-3_39"},{"key":"2317_CR14","doi-asserted-by":"crossref","unstructured":"Hodan, T., Vineet, V., Gal, R., et\u00a0al. (2019). Photorealistic image synthesis for object instance detection. In ICIP, pp. 66-70.","DOI":"10.1109\/ICIP.2019.8803821"},{"key":"2317_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Y., Hugonot, J., Fua, P., et\u00a0al. (2019). Segmentation-driven 6d object pose estimation. In CVPR, pp. 3380-3389.","DOI":"10.1109\/CVPR.2019.00350"},{"key":"2317_CR16","doi-asserted-by":"crossref","unstructured":"Hu, Y., Speierer, S., Jakob, W., et\u00a0al. (2021). Wide-depth-range 6d object pose estimation in space. In CVPR, pp. 15865-15874.","DOI":"10.1109\/CVPR46437.2021.01561"},{"key":"2317_CR17","doi-asserted-by":"crossref","unstructured":"Kaskman, R., Zakharov, S., Shugurov, I., et\u00a0al. (2019). Homebreweddb: Rgb-d dataset for 6d pose estimation of 3d objects. In ICCV Workshop, pp. 2767-2776.","DOI":"10.1109\/ICCVW.2019.00338"},{"key":"2317_CR18","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., et\u00a0al. (2017). Ssd-6d: Making rgb-based 3d detection and 6d pose estimation great again. In ICCV, pp. 1530-1538.","DOI":"10.1109\/ICCV.2017.169"},{"key":"2317_CR19","doi-asserted-by":"crossref","unstructured":"Kendall, A., & Cipolla, R. (2017). Geometric loss functions for camera pose regression with deep learning. In CVPR pp. 6555-6564.","DOI":"10.1109\/CVPR.2017.694"},{"key":"2317_CR20","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., & Cipolla, R. (2015). Posenet: A convolutional network for real-time 6-dof camera relocalization. In ICCV, pp. 2938-2946.","DOI":"10.1109\/ICCV.2015.336"},{"key":"2317_CR21","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., et\u00a0al. (2020). Pointrend: Image segmentation as rendering. In CVPR, pp. 9796-9805.","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"2317_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., et\u00a0al. (2023). Segment anything. Preprint at arXiv:2304.02643.","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"2","key":"2317_CR23","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. (2009). Epnp: An accurate o(n) solution to the pnp problem. IJCV, 81(2), 155\u2013166.","journal-title":"IJCV"},{"key":"2317_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, G., & Ji, X. (2019a). Cdpn: Coordinates-based disentangled pose network for real-time rgb-based 6-dof object pose estimation. In ICCV, pp. 7677-7686.","DOI":"10.1109\/ICCV.2019.00777"},{"key":"2317_CR25","doi-asserted-by":"publisher","first-page":"94321","DOI":"10.1109\/ACCESS.2019.2923436","volume":"7","author":"Z Li","year":"2019","unstructured":"Li, Z., Wang, Y., & Ji, X. (2019). Monocular viewpoints estimation for generic objects in the wild. IEEE Access, 7, 94321\u201394331.","journal-title":"IEEE Access"},{"key":"2317_CR26","doi-asserted-by":"crossref","unstructured":"Mahendran, S., Ali, H., & Vidal, R. (2017). 3d pose regression using convolutional neural networks. In CVPR Workshops, pp. 494-495.","DOI":"10.1109\/CVPRW.2017.73"},{"key":"2317_CR27","doi-asserted-by":"crossref","unstructured":"Manhardt, F., Kehl, W., Navab, N., et\u00a0al. (2018). Deep model-based 6d pose refinement in rgb. In ECCV, pp. 833-849.","DOI":"10.1007\/978-3-030-01264-9_49"},{"key":"2317_CR28","doi-asserted-by":"crossref","unstructured":"Manhardt, F., Arroyo, D.M., Rupprecht, C., et\u00a0al. (2019). Explaining the ambiguity of object detection and 6d pose from visual data. In ICCV, pp. 6840-6849.","DOI":"10.1109\/ICCV.2019.00694"},{"key":"2317_CR29","doi-asserted-by":"crossref","unstructured":"Moreno-Noguer, F., Lepetit, V., & Fua, P. (2007). Accurate non-iterative o(n) solution to the pnp problem. In ICCV.","DOI":"10.1109\/ICCV.2007.4409116"},{"key":"2317_CR30","doi-asserted-by":"crossref","unstructured":"Oberweger, M., Rad, M., & Lepetit, V. (2018). Making deep heatmaps robust to partial occlusions for 3d object pose estimation. In ECCV, pp. 125-141.","DOI":"10.1007\/978-3-030-01267-0_8"},{"key":"2317_CR31","doi-asserted-by":"crossref","unstructured":"Park, K., Patten, T., & Vincze, M. (2019). Pix2pose: Pixel-wise coordinate regression of objects for 6d pose estimation. In ICCV, pp. 7667-7676.","DOI":"10.1109\/ICCV.2019.00776"},{"key":"2317_CR32","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Chan, A., et\u00a0al. (2017). 6-dof object pose from semantic keypoints. In ICRA, pp. 2011-2018.","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"2317_CR33","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., et\u00a0al. (2019). Pvnet: Pixel-wise voting network for 6dof pose estimation. In CVPR, pp. 4556-4565.","DOI":"10.1109\/CVPR.2019.00469"},{"key":"2317_CR34","doi-asserted-by":"crossref","unstructured":"Rad, M., & Lepetit, V. (2017). Bb8: A scalable, accurate, robust to partial occlusion method for predicting the 3d poses of challenging objects without using depth. In ICCV, pp. 3848-3856.","DOI":"10.1109\/ICCV.2017.413"},{"issue":"6","key":"2317_CR35","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., et al. (2017). Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2317_CR36","doi-asserted-by":"crossref","unstructured":"Sattler, T., Zhou, Q., Pollefeys, M., et\u00a0al. (2019). Understanding the limitations of cnn-based absolute camera pose regression. In CVPR, pp. 3297-3307.","DOI":"10.1109\/CVPR.2019.00342"},{"key":"2317_CR37","doi-asserted-by":"crossref","unstructured":"Song, C., Song, J., & Huang, Q. (2020). Hybridpose: 6d object pose estimation under hybrid representations. In CVPR, pp. 428-437.","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"2317_CR38","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., et\u00a0al. (2015). Render for cnn: Viewpoint estimation in images using cnns trained with rendered 3d model views. In ICCV, pp. 2686-2694.","DOI":"10.1109\/ICCV.2015.308"},{"key":"2317_CR39","doi-asserted-by":"crossref","unstructured":"Su, Y., Saleh, M., Fetzer, T., et\u00a0al. (2022). Zebrapose: Coarse to fine surface encoding for 6dof object pose estimation. In CVPR, pp. 6728-6738.","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"2317_CR40","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Marton, Z.C., Durner, M., et\u00a0al. (2018). Implicit 3d orientation learning for 6d object detection from rgb images. In ECCV, pp. 712-729.","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"2317_CR41","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Durner, M., Puang, E.Y., et\u00a0al. (2020a). Multi-path learning for object pose estimation across domains. In CVPR, pp. 13913-13922.","DOI":"10.1109\/CVPR42600.2020.01393"},{"issue":"3","key":"2317_CR42","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1007\/s11263-019-01243-8","volume":"128","author":"M Sundermeyer","year":"2020","unstructured":"Sundermeyer, M., Marton, Z. C., Durner, M., et al. (2020). Augmented autoencoders: Implicit 3d orientation learning for 6d object detection. International Journal of Computer Vision, 128(3), 714\u2013729.","journal-title":"International Journal of Computer Vision"},{"key":"2317_CR43","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., & Fua, P. (2018). Real-time seamless single shot 6d object pose prediction. In CVPR, pp. 292-301.","DOI":"10.1109\/CVPR.2018.00038"},{"key":"2317_CR44","doi-asserted-by":"crossref","unstructured":"Wang, G., Manhardt, F., Shao, J., et\u00a0al. (2020). Self6d: Self-supervised monocular 6d object pose estimation. In ECCV, pp. 108-125.","DOI":"10.1007\/978-3-030-58452-8_7"},{"key":"2317_CR45","unstructured":"Wang, G., Manhardt, F., Liu, X., et\u00a0al. (2021a). Occlusion-aware self-supervised monocular 6d object pose estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"2317_CR46","doi-asserted-by":"crossref","unstructured":"Wang, G., Manhardt, F., Tombari, F., et\u00a0al. (2021b). Gdr-net: Geometry-guided direct regression network for monocular 6d object pose estimation. In CVPR, pp. 16606-16616.","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"2317_CR47","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., et\u00a0al. (2018). Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes. In RSS.","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"2317_CR48","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yu, X., & Yang, Y. (2021). Dsc-posenet: Learning 6dof object pose estimation via dual-scale consistency. In CVPR, pp. 3906-3915.","DOI":"10.1109\/CVPR46437.2021.00390"},{"key":"2317_CR49","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Shugurov, I., & Ilic, S. (2019). Dpod: 6d pose object detector and refiner. In ICCV, pp. 1941-1950.","DOI":"10.1109\/ICCV.2019.00203"},{"key":"2317_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhao, W., Guan, Z., et\u00a0al. (2021). Keypoint-graph-driven learning framework for object pose estimation. In CVPR, pp. 1065-1073.","DOI":"10.1109\/CVPR46437.2021.00112"},{"key":"2317_CR51","unstructured":"Zhao, Z., Peng, G., Li, C., et\u00a0al. (2018). Estimating 6d pose from localizing designated surface keypoints. Preprint at arXiv:1812.01387."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02317-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02317-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02317-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T05:58:38Z","timestamp":1744869518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02317-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2317"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02317-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"12 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}