{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:52:35Z","timestamp":1761598355621,"version":"3.37.3"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T00:00:00Z","timestamp":1626134400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T00:00:00Z","timestamp":1626134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973065","52075531"],"award-info":[{"award-number":["61973065","52075531"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["N182612002","N2026002"],"award-info":[{"award-number":["N182612002","N2026002"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s13042-021-01364-y","type":"journal-article","created":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T12:05:59Z","timestamp":1626177959000},"page":"2795-2807","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LHFF-Net: Local heterogeneous feature fusion network for 6DoF pose estimation"],"prefix":"10.1007","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8296-8039","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhenquan","family":"He","sequence":"additional","affiliation":[]},{"given":"Xing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,13]]},"reference":[{"key":"1364_CR1","doi-asserted-by":"crossref","unstructured":"Hinterstoisser S, et al. (2011) Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: International Conference on Computer Vision, Barcelona, 2011, pp 858\u2013865","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"1364_CR2","doi-asserted-by":"crossref","unstructured":"Hu Y, Fua P, Wang W, Salzmann M (2020) Single-Stage 6D Object Pose Estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp 2927\u20132936","DOI":"10.1109\/CVPR42600.2020.00300"},{"key":"1364_CR3","doi-asserted-by":"crossref","unstructured":"Qi Charles R, et al. (2016) Volumetric and multi-view cnns for object classification on 3d data. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.609"},{"key":"1364_CR4","doi-asserted-by":"crossref","unstructured":"Brachmann E, Krull A, Michel F, Gumhold S, Shotton J, Rother C (2014) Learning 6d object pose estimation using 3d object coordinates. In: European conference on computer vision, Springer, pp 536\u2013551","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"1364_CR5","doi-asserted-by":"crossref","unstructured":"Hinterstoisser S , Lepetit V , Rajkumar N, Konolige K (2016) Going further with point pair features. In: European Conference on Computer Vision, Springer, pp 834\u2013848","DOI":"10.1007\/978-3-319-46487-9_51"},{"issue":"8","key":"1364_CR6","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TPAMI.2003.1217599","volume":"25","author":"Xiao-Shan Gao","year":"2003","unstructured":"Gao Xiao-Shan, Hou Xiao-Rong, Tang Jianliang, Cheng Hang-Fei (2003) Complete solution classifification for the perspective-three-point problem. IEEE Trans Pattern Anal Mach Intell 25(8):930\u2013943","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1364_CR7","doi-asserted-by":"crossref","unstructured":"Szegedy C et al. (2015) Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1364_CR8","doi-asserted-by":"crossref","unstructured":"Engelcke M, Rao D, Wang DZ, Tong CH, Posner I (2017) Vote3deep: Fast object detection in 3d point clouds using effificient convolutional neural networks. In: Robotics and Automation (ICRA), 2017 IEEE International Conference on. IEEE, pp 1355\u20131361","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"1364_CR9","doi-asserted-by":"crossref","unstructured":"Kehl W, Manhardt F, Tombari F, Ilic S, Navab N (2017) Ssd-6d: Making rgb-based 3d detection and 6d pose estimation great again. In: Proceedings of the IEEE International Conference on Computer Vision 1521\u20131529","DOI":"10.1109\/ICCV.2017.169"},{"key":"1364_CR10","doi-asserted-by":"crossref","unstructured":"Li Z, Wang G, Ji X (2019) Cdpn: Coordinates-based disentangled pose network for real-time rgb-based 6-dof object pose estimation. In: The IEEE International Conference on Computer Vision (ICCV), October","DOI":"10.1109\/ICCV.2019.00777"},{"key":"1364_CR11","doi-asserted-by":"crossref","unstructured":"Hinterstoisser Stefan , Lepetit Vincent , Ilic Slobodan , Holzer Stefan , Bradski Gary , Konolige Kurt , Navab Nassir (2012) Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Asian conference on computer vision, pages 548-562. Springer","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"1364_CR12","doi-asserted-by":"crossref","unstructured":"Drost B, Ulrich M, Navab N, Ilic S (2010) Model globally, match locally: Effificient and robust 3d object recognition. In: Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, Ieee, pp 998\u20131005","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"1364_CR13","doi-asserted-by":"crossref","unstructured":"Wang C, et al. (2019) DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 3338\u20133347","DOI":"10.1109\/CVPR.2019.00346"},{"key":"1364_CR14","doi-asserted-by":"crossref","unstructured":"Buch AG, Kiforenko L, Kraft D (2017) Rotational subgroup voting and pose clustering for robust 3d object recognition. In: Computer Vision (ICCV), 2017 IEEE International Conference on, IEEE, pp 4137\u20134145","DOI":"10.1109\/ICCV.2017.443"},{"key":"1364_CR15","doi-asserted-by":"crossref","unstructured":"Pajarre E, Ritoniemi T, Tenhunen H (1991) G2L: system for converting low-level geometrical designs to a higher level representation, Euro ASIC \u201991. France, Paris, pp 366\u2013371","DOI":"10.1109\/EUASIC.1991.212835"},{"key":"1364_CR16","doi-asserted-by":"crossref","unstructured":"Capellen CMS, Behnke S (2020) ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation. In: 15th International Conference on Computer Vision Theory and Applications","DOI":"10.5220\/0008990901620172"},{"key":"1364_CR17","doi-asserted-by":"crossref","unstructured":"Kehl W, Milletari F, Tombari F, Ilic S, Navab N (2016) Deep learning of local rgb-d patches for 3d object detection and 6d pose estimation. In: European Conference on Computer Vision, Springer, pp 205\u2013220","DOI":"10.1007\/978-3-319-46487-9_13"},{"key":"1364_CR18","unstructured":"Tremblay J, To T, Sundaralingam B, Xiang Y, Fox D, Birchfifield S (2018) Deep object pose estimation for semantic robotic grasping of household objects, arXiv preprint arXiv:1809.10790"},{"key":"1364_CR19","doi-asserted-by":"crossref","unstructured":"Wang Yue , Sun Yongbin , Liu Ziwei (2018) Dynamic Graph CNN for Learning on Point Clouds. ACM Transactions on Graphics 38.5","DOI":"10.1145\/3326362"},{"key":"1364_CR20","doi-asserted-by":"crossref","unstructured":"Hu Y, Hugonot J, Fua P, Salzmann M (2019) Segmentation-Driven 6D Object Pose Estimation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 3380\u20133389","DOI":"10.1109\/CVPR.2019.00350"},{"key":"1364_CR21","unstructured":"Qi CR, Su H, Mo K, et al. (2017) PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 77\u201385, Honolulu, HI, USA, 21-26 July"},{"issue":"12","key":"1364_CR22","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1109\/TVCG.2015.2513408","volume":"22","author":"E Marchand","year":"2016","unstructured":"Marchand E, Uchiyama H, Spindler F (2016) Pose estimation for augmented reality: a hands-on survey. IEEE Trans Vis Comput Graph 22(12):2633\u20132651","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"1364_CR23","unstructured":"Zhang K , Hao M , Wang J, et al. (2019) Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features,"},{"key":"1364_CR24","doi-asserted-by":"crossref","unstructured":"Wang C, et al. (2020) 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, pp 10059\u201310066","DOI":"10.1109\/ICRA40945.2020.9196679"},{"key":"1364_CR25","doi-asserted-by":"crossref","unstructured":"Rios-Cabrera R, Tuytelaars T (2013) Discriminatively trained templates for 3d object detection: A real time scalable approach. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 2048\u20132055","DOI":"10.1109\/ICCV.2013.256"},{"issue":"3","key":"1364_CR26","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 (2006) 3d object modeling and recognition using local affifine-invariant image descriptors and multi-view spatial constraints. Int J Comput Vis 66(3):231\u2013259","journal-title":"Int J Comput Vis"},{"key":"1364_CR27","doi-asserted-by":"crossref","unstructured":"Wang H, Sridhar S, Huang J, Valentin J, Song S, Guibas LJ (2019) Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 2637\u20132646","DOI":"10.1109\/CVPR.2019.00275"},{"key":"1364_CR28","doi-asserted-by":"crossref","unstructured":"Peng S, Liu Y, Huang Q, Zhou X, Bao H (2019) PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 4556\u20134565","DOI":"10.1109\/CVPR.2019.00469"},{"key":"1364_CR29","doi-asserted-by":"crossref","unstructured":"Qi Charles R, et al. (2018) Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00102"},{"issue":"2","key":"1364_CR30","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"Vincent Lepetit","year":"2009","unstructured":"Lepetit Vincent, Moreno-Noguer Francesc, Fua Pascal (2009) Epnp: An accurate o (n) solution to the pnp problem. Int J Comput Vis 81(2):155","journal-title":"Int J Comput Vis"},{"key":"1364_CR31","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2017) Multi-view 3d object detection network for autonomous driving. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1907-1915","DOI":"10.1109\/CVPR.2017.691"},{"key":"1364_CR32","doi-asserted-by":"crossref","unstructured":"Tejani A, Tang D, Kouskouridas R, Kim T-K (2014) Latent-class hough forests for 3d object detection and pose estimation. In: Proceedings of the European Conference on Computer Vision, Springer, pp 462\u2013477","DOI":"10.1007\/978-3-319-10599-4_30"},{"key":"1364_CR33","doi-asserted-by":"crossref","unstructured":"Vidal Joel CY Lin, Marti R (2018) 6D pose estimation using an improved method based on point pair features. In: 2018 4th International Conference on Control, Automation and Robotics (ICCAR) IEEE","DOI":"10.1109\/ICCAR.2018.8384709"},{"key":"1364_CR34","doi-asserted-by":"crossref","unstructured":"Xu D, Anguelov D, Jain A (2018) PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, pp 244\u2013253","DOI":"10.1109\/CVPR.2018.00033"},{"key":"1364_CR35","doi-asserted-by":"crossref","unstructured":"Wohlhart P, Lepetit V (2015) Learning descriptors for object recognition and 3d pose estimation. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR), pp 3109\u20133118","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"1364_CR36","doi-asserted-by":"crossref","unstructured":"Shin Younghak, Balasingham Ilangko (2017) Comparison of hand-craft feature based svm and cnn based deep learning framework for automatic polyp classifification. In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, pp 3277\u20133280","DOI":"10.1109\/EMBC.2017.8037556"},{"key":"1364_CR37","doi-asserted-by":"crossref","unstructured":"Zakharov Sergey, Shugurov Ivan, Ilic Slobodan (2019) Dpod: 6d pose object detector and refifiner. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1941\u20131950","DOI":"10.1109\/ICCV.2019.00203"},{"key":"1364_CR38","doi-asserted-by":"crossref","unstructured":"Tekin Bugra, Sinha Sudipta N, Fua Pascal (2018) Real-time seamless single shot 6d object pose prediction. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00038"},{"key":"1364_CR39","doi-asserted-by":"crossref","unstructured":"Wang Peng-Shuai, et al. (2017) O-cnn: Octree-based convolutional neural networks for 3d shape analysis. In: ACM Transactions on Graphics (TOG), 36(4):72","DOI":"10.1145\/3072959.3073608"},{"key":"1364_CR40","doi-asserted-by":"crossref","unstructured":"Xiang Y, Schmidt T, Narayanan V, Fox D (2017) Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes. ArXiv preprint arXiv:1711.00199","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"1364_CR41","doi-asserted-by":"crossref","unstructured":"Li Y, Wang G, Ji X, Xiang Y, Fox D (2018) Deepim: Deep iterative matching for 6d pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 683\u2013698","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"1364_CR42","doi-asserted-by":"crossref","unstructured":"Chen W, Duan J, Basevi H, Chang HJ , Leonardis A (2020) Ponitposenet: Point pose network for robust 6d object pose estimation. In: The IEEE Winter Conference on Applications of Computer Vision, pp 2824\u20132833","DOI":"10.1109\/WACV45572.2020.9093272"},{"key":"1364_CR43","doi-asserted-by":"crossref","unstructured":"Zhu M., Derpanis KG, Yang Y, Brahmbhatt S, Zhang M, Phillips C, Lecce M, Daniilidis K (2014) Single image 3d object detection and pose estimation for grasping. In: Robotics and Automation (ICRA), 2014 IEEE International Conference on, IEEE, pp 3936\u20133943","DOI":"10.1109\/ICRA.2014.6907430"},{"key":"1364_CR44","doi-asserted-by":"crossref","unstructured":"Yang B, Luo W, Urtasun R (2018) Pixor: Realtime 3d object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7652\u20137660","DOI":"10.1109\/CVPR.2018.00798"},{"key":"1364_CR45","doi-asserted-by":"crossref","unstructured":"He Y, Sun W, Huang H, Liu J, Fan H, Sun J (2020) PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp 11629\u201311638","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"1364_CR46","doi-asserted-by":"crossref","unstructured":"Zhou Y , Tuzel O (2018) Voxelnet: End-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4490\u20134499","DOI":"10.1109\/CVPR.2018.00472"},{"key":"1364_CR47","unstructured":"Li Yangyan, Bu Rui, Sun Mingchao, Wu Wei, et al. (2018)PointCNN: Convolution On $$X$$-Transformed Points. arXiv:1801.07791, Nov"},{"key":"1364_CR48","doi-asserted-by":"crossref","unstructured":"Park Kiru T Patten, Vincze M (2020) Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) IEEE","DOI":"10.1109\/ICCV.2019.00776"},{"key":"1364_CR49","doi-asserted-by":"crossref","unstructured":"Schwarz M, Schulz H, Behnke S (2015) RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features. In: IEEE International Conference on Robotics & Automation. IEEE: 1329\u20131335","DOI":"10.1109\/ICRA.2015.7139363"},{"key":"1364_CR50","doi-asserted-by":"crossref","unstructured":"Tulsiani S, Malik J (2015) Viewpoints and keypoints. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR), pp 1510\u20131519","DOI":"10.1109\/CVPR.2015.7298758"},{"key":"1364_CR51","doi-asserted-by":"crossref","unstructured":"Li C, Bai J, Hager G D (2018) A Unified Framework for Multi-View Multi-Class Object Pose Estimation","DOI":"10.1007\/978-3-030-01270-0_16"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-021-01364-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-021-01364-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-021-01364-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,22]],"date-time":"2021-08-22T05:15:39Z","timestamp":1629609339000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-021-01364-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,13]]},"references-count":51,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["1364"],"URL":"https:\/\/doi.org\/10.1007\/s13042-021-01364-y","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2021,7,13]]},"assertion":[{"value":"7 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}