{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:11:50Z","timestamp":1777594310683,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T00:00:00Z","timestamp":1700870400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T00:00:00Z","timestamp":1700870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Technology Planning Project of Guangdong Province, China","award":["2019A050520001"],"award-info":[{"award-number":["2019A050520001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s00371-023-03113-4","type":"journal-article","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T04:21:55Z","timestamp":1700886115000},"page":"5421-5434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["6D object pose estimation based on dense convolutional object center voting with improved accuracy and efficiency"],"prefix":"10.1007","volume":"40","author":[{"given":"Faheem","family":"Ullah","sequence":"first","affiliation":[]},{"given":"Wu","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Zhun","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Qiuda","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,25]]},"reference":[{"key":"3113_CR1","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q. V.: EfficientDet : Scalable and Efficient Object Detection, in IEEE\/CVF conference on computer vision and pattern recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"3113_CR2","unstructured":"Lepetit V.: BB8\u202f: a scalable, accurate, robust to partial occlusion method for predicting. Proc. IEEE Int. Conf. Comput. Vis., pp. 3828\u20133836, (2017)"},{"key":"3113_CR3","doi-asserted-by":"publisher","unstructured":"Tekin, B., Sinha, S. N., & Fua, P.: Real-time seamless single shot 6d object pose prediction. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 292-301). (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00038.","DOI":"10.1109\/CVPR.2018.00038"},{"key":"3113_CR4","doi-asserted-by":"crossref","unstructured":"Xiang Y., Schmidt T., Narayanan V., and Fox D.: PoseCNN\u202f: a convolutional neural network for 6D object pose estimation in cluttered scenes. (2018)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"3113_CR5","doi-asserted-by":"publisher","unstructured":"Capellen C., Schwarz M., and Behnke S.: ConvPoseCNN: Dense convolutional 6D object pose estimation. VISIGRAPP 2020 - Proc. 15th Int. Jt. Conf. Comput. Vision, Imaging Comput. Graph. Theory Appl., 5, 162\u2013172, (2020). https:\/\/doi.org\/10.5220\/0008990901620172.","DOI":"10.5220\/0008990901620172"},{"key":"3113_CR6","doi-asserted-by":"publisher","unstructured":"Periyasamy, A. S., Capellen, C., Schwarz, M., & Behnke, S.: ConvPoseCNN2: Prediction and Refinement of Dense 6D Object Pose. In:\u00a0International Joint Conference on Computer Vision, Imaging and Computer Graphics\u00a0(pp. 353-371). Cham: Springer International Publishing. (2020). https:\/\/doi.org\/10.1007\/978-3-030-94893-1.","DOI":"10.1007\/978-3-030-94893-1"},{"key":"3113_CR7","doi-asserted-by":"publisher","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: Pvnet: Pixel-wise voting network for 6dof pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(pp. 4561-4570). (2019) https:\/\/doi.org\/10.1109\/CVPR.2019.00469.","DOI":"10.1109\/CVPR.2019.00469"},{"key":"3113_CR8","unstructured":"Yu, X., Zhuang, Z., Koniusz, P., Li, H.: 6dof object pose estimation via differentiable proxy voting loss. (2020).\u00a0arXiv preprint arXiv:2002.03923."},{"key":"3113_CR9","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In:\u00a0International conference on machine learning\u00a0(pp. 6105-6114). PMLR (2019)"},{"issue":"6","key":"3113_CR10","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). https:\/\/doi.org\/10.1145\/358669.358692","journal-title":"Commun. ACM"},{"key":"3113_CR11","doi-asserted-by":"publisher","unstructured":"Cao, Z., Sheikh, Y., Banerjee, N. K.: Real-time scalable 6DOF pose estimation for textureless objects. In:\u00a02016 IEEE International conference on Robotics and Automation (ICRA)\u00a0(pp. 2441-2448). IEEE. (2016). https:\/\/doi.org\/10.1109\/ICRA.2016.7487396.","DOI":"10.1109\/ICRA.2016.7487396"},{"issue":"5","key":"3113_CR12","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1109\/TPAMI.2011.206","volume":"34","author":"S Hinterstoisser","year":"2012","unstructured":"Hinterstoisser, S., et al.: Gradient response maps for real-time detection of textureless objects. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 876\u2013888 (2012). https:\/\/doi.org\/10.1109\/TPAMI.2011.206","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3113_CR13","doi-asserted-by":"publisher","unstructured":"Hinterstoisser S., Lepetit V., Ilic S., and Holzer S.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: 12th Int. Conf. Comput. Vis., vol. 3, pp. 548\u2013562, 2012, [Online]. http:\/\/link.springer.com\/https:\/\/doi.org\/10.1007\/978-3-642-33868-7.","DOI":"10.1007\/978-3-642-33868-7"},{"issue":"5","key":"3113_CR14","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1016\/0262-5075(81)90042-7","volume":"2","author":"DG Lowe","year":"1999","unstructured":"Lowe, D.G.: Object recognition from local scale invariant features. IEEE Int Conf Comput Vision (ICCV) 2(5), 1150\u20131157 (1999). https:\/\/doi.org\/10.1016\/0262-5075(81)90042-7","journal-title":"IEEE Int Conf Comput Vision (ICCV)"},{"key":"3113_CR15","first-page":"2011","volume":"2017","author":"G Pavlakos","year":"2017","unstructured":"Pavlakos, G., Zhou, X., Chan, A., Derpanis, K.G., Daniilidis, K.: \u201c6-DoF object pose from semantic keypoints\u201d, in. IEEE Int Conf Robot Autom (ICRA) 2017, 2011\u20132018 (2017)","journal-title":"IEEE Int Conf Robot Autom (ICRA)"},{"issue":"3","key":"3113_CR16","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s11263-005-3674-1","volume":"66","author":"F Rothganger","year":"2006","unstructured":"Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int. J. Comput. Vis. 66(3), 231\u2013259 (2006). https:\/\/doi.org\/10.1007\/s11263-005-3674-1","journal-title":"Int. J. Comput. Vis."},{"key":"3113_CR17","doi-asserted-by":"crossref","unstructured":"Tulsiani S. and Malik J.: Viewpoints and Keypoints. Cvpr, pp. 1\u20138, (2015)","DOI":"10.1109\/CVPR.2015.7298758"},{"key":"3113_CR18","doi-asserted-by":"publisher","unstructured":"Krull, A., Brachmann, E., Michel, F., Yang, M. Y., Gumhold, S., Rother, C.: Learning analysis-by-synthesis for 6D pose estimation in RGB-D images. In:\u00a0Proceedings of the IEEE international conference on computer vision\u00a0(pp. 954-962). (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.115.","DOI":"10.1109\/ICCV.2015.115"},{"key":"3113_CR19","doi-asserted-by":"publisher","unstructured":"Li, Z., Wang, G., & Ji, X.: Cdpn: Coordinates-based disentangled pose network for real-time rgb-based 6-dof object pose estimation. In:\u00a0Proceedings of the IEEE\/CVF International Conference on Computer Vision\u00a0(pp. 7678-7687). (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00777.","DOI":"10.1109\/ICCV.2019.00777"},{"key":"3113_CR20","doi-asserted-by":"publisher","unstructured":"Park, K., Patten, T., & Vincze, M.: Pix2pose: Pixel-wise coordinate regression of objects for 6d pose estimation. In:\u00a0Proceedings of the IEEE\/CVF International Conference on Computer Vision\u00a0(pp. 7668-7677). (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00776.","DOI":"10.1109\/ICCV.2019.00776"},{"key":"3113_CR21","doi-asserted-by":"publisher","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: Dpod: 6d pose object detector and refiner. In:\u00a0Proceedings of the IEEE\/CVF international conference on computer vision\u00a0(pp. 1941-1950). (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00203.","DOI":"10.1109\/ICCV.2019.00203"},{"key":"3113_CR22","doi-asserted-by":"publisher","unstructured":"Girshick R.: Fast R-CNN (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169.","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"3113_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN\u202f: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1\u201314 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3113_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., Berg, A. C.: Ssd: single shot multibox detector. In:\u00a0Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14\u00a0(pp. 21-37). Springer International Publishing. (2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3113_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A. You only look once: Unified, real-time object detection. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 779-788). (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"3113_CR26","doi-asserted-by":"publisher","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:\u00a0Proceedings of the IEEE international conference on computer vision\u00a0(pp. 2686-2694). (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.308.","DOI":"10.1109\/ICCV.2015.308"},{"key":"3113_CR27","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:\u00a0Proceedings of the IEEE \u0130nternational Conference On Computer Vision\u00a0(pp. 1521-1529), (2017).","DOI":"10.1109\/ICCV.2017.169"},{"key":"3113_CR28","unstructured":"Bukschat Y. and Vetter M.: EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach [Online]. (2020). http:\/\/arxiv.org\/abs\/2011.04307."},{"key":"3113_CR29","doi-asserted-by":"crossref","unstructured":"Ullah, F., Wei, W., Daradkeh, Y. I., Javed, M., Rabbi, I., & Al Juaid, H.: A Robust convolutional neural network for 6D Object Pose Estimation from RGB Image with Distance Regularization Voting Loss.\u00a0Scientific Programming,\u00a02022. (2022).","DOI":"10.1155\/2022\/2037141"},{"key":"3113_CR30","doi-asserted-by":"crossref","unstructured":"Su, Y., Saleh, M., Fetzer, T., Rambach, J., Navab, N., Busam, B., Tombari, F.: Zebrapose: coarse to fine surface encoding for 6dof object pose estimation. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(pp. 6738-6748). (2022).","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"3113_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02082-w","author":"Y Yu","year":"2021","unstructured":"Yu, Y., Niu, C., Li, J., Xu, K.: Multi-view 2D\u20133D alignment with hybrid bundle adjustment for visual metrology. Vis. Comput. (2021). https:\/\/doi.org\/10.1007\/s00371-021-02082-w","journal-title":"Vis. Comput."},{"key":"3113_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-016-1326-9","author":"X Zabulis","year":"2016","unstructured":"Zabulis, X., Lourakis, M.I.A., Koutlemanis, P.: Correspondence-free pose estimation for 3D objects from noisy. Vis. Comput. (2016). https:\/\/doi.org\/10.1007\/s00371-016-1326-9","journal-title":"Vis. Comput."},{"key":"3113_CR33","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02135-0","author":"X Liu","year":"2021","unstructured":"Liu, X., Yin, J., Liu, H., Yin, Y.: PISEP 2: pseudo-image sequence evolution-based 3D pose prediction. Vis. Comput. (2021). https:\/\/doi.org\/10.1007\/s00371-021-02135-0","journal-title":"Vis. Comput."},{"key":"3113_CR34","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T. J., Yuan, J., Thalmann, N. M.: Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks. In:\u00a0Proceedings of the IEEE\/CVF international conference on computer vision\u00a0(pp. 2272-2281). (2019).","DOI":"10.1109\/ICCV.2019.00236"},{"key":"3113_CR35","doi-asserted-by":"publisher","unstructured":"Song, C., Song, J., & Huang, Q.: Hybridpose: 6d object pose estimation under hybrid representations. In:\u00a0Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition\u00a0(pp. 431-440). (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00051.","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"3113_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S.: Feature pyramid networks for object detection. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 2117-2125). (2017).","DOI":"10.1109\/CVPR.2017.106"},{"key":"3113_CR37","unstructured":"Zoph B., V Le Q.: Searching for activation functions. In: 6th Int. Conf. Learn. Represent. ICLR 2018-Work. Track Proc., pp. 1\u201313, (2018)"},{"key":"3113_CR38","doi-asserted-by":"crossref","unstructured":"Chollet F.: Xception: deep learning with depthwise separable convolutions. In: CVPR, pp. 1251\u20131258 (2017).","DOI":"10.1109\/CVPR.2017.195"},{"key":"3113_CR39","doi-asserted-by":"publisher","unstructured":"Brachmann, E., Michel, F., Krull, A., Yang, M. Y., Gumhold, S.: Uncertainty-driven 6d pose estimation of objects and scenes from a single rgb image. In:\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(pp. 3364-3372). (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.366.","DOI":"10.1109\/CVPR.2016.366"},{"key":"3113_CR40","unstructured":"Billings G. and Johnson-roberson M.: SilhoNet: an RGB method for 3D object pose estimation and grasp planning."},{"key":"3113_CR41","doi-asserted-by":"publisher","unstructured":"Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., and Rother, C.: Learning 6d object pose estimation using 3d object coordinates. In:\u00a0Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part II 13\u00a0(pp. 536-551). Springer International Publishing. (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_35.","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"3113_CR42","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1007\/s12559-021-09966-y","volume":"14","author":"T Chen","year":"2022","unstructured":"Chen, T., Gu, D.: CSA6D-channel-spatial attention networks for 6D object pose estimation. Cognit. Comput. 14, 702\u2013713 (2022). https:\/\/doi.org\/10.1007\/s12559-021-09966-y","journal-title":"Cognit. Comput."},{"key":"3113_CR43","doi-asserted-by":"publisher","unstructured":"Iwase S., Liu X., Khirodkar R., Yokota R., and Kitani K. M.: RePOSE: Fast 6D object pose refinement via deep texture rendering. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 3283\u20133292, (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00329.","DOI":"10.1109\/ICCV48922.2021.00329"},{"issue":"2","key":"3113_CR44","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.1109\/LRA.2021.3062304","volume":"6","author":"W Hua","year":"2021","unstructured":"Hua, W., Zhou, Z., Wu, J., Huang, H., Wang, Y., Xiong, R.: REDE: end-to-end object 6D pose robust estimation using differentiable outliers elimination. IEEE Robot. Autom. Lett. 6(2), 2886\u20132893 (2021). https:\/\/doi.org\/10.1109\/LRA.2021.3062304","journal-title":"IEEE Robot. Autom. Lett."},{"key":"3113_CR45","doi-asserted-by":"publisher","unstructured":"Feng H., Zhang L., Yang X., and Liu Z.: MixedFusion: 6D Object pose estimation from decoupled RGB-depth features. In: Proc. Int. Conf. Pattern Recognit., pp. 685\u2013691, (2020). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412494.","DOI":"10.1109\/ICPR48806.2021.9412494"},{"key":"3113_CR46","doi-asserted-by":"publisher","unstructured":"He Y., Sun W., Huang H., Liu J., Fan H., and Sun J.: PVN3D: A deep point-wise 3D keypoints voting network for 6DoF pose estimation. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 11629\u201311638, (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01165.","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"3113_CR47","doi-asserted-by":"crossref","unstructured":"Wu J., Liu L., Wang Y., and Xiong R.: Towards two-view 6D object pose estimation: a comparative study on fusion strategy. [Online] (2022). http:\/\/arxiv.org\/abs\/2207.00260.","DOI":"10.1109\/IROS47612.2022.9981630"},{"key":"3113_CR48","doi-asserted-by":"crossref","unstructured":"Xu Z., Zhang Y., Chen K., and Jia K.: BiCo-net: regress globally, match locally for robust 6D pose estimation. no. c, [Online] (2022). http:\/\/arxiv.org\/abs\/2205.03536.","DOI":"10.24963\/ijcai.2022\/210"},{"key":"3113_CR49","unstructured":"Arge FORL., and Mage CI.: Very deep convolut\u0131onal networks for large-scale \u0131mage recogn\u0131t\u0131on. in ICLR, pp. 1\u201314 (2015)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03113-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-03113-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03113-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T13:39:04Z","timestamp":1721828344000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-03113-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,25]]},"references-count":49,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["3113"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-03113-4","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,25]]},"assertion":[{"value":"1 September 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}