{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:15:20Z","timestamp":1768338920632,"version":"3.49.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Foundation of Ministry of Industry and Information Technology","award":["TC220H05X-04"],"award-info":[{"award-number":["TC220H05X-04"]}]},{"name":"Foundation of Ministry of Industry and Information Technology","award":["TC220H05X-04"],"award-info":[{"award-number":["TC220H05X-04"]}]},{"name":"Foundation of Ministry of Industry and Information Technology","award":["TC220H05X-04"],"award-info":[{"award-number":["TC220H05X-04"]}]},{"name":"Foundation of Ministry of Industry and Information Technology","award":["TC220H05X-04"],"award-info":[{"award-number":["TC220H05X-04"]}]},{"name":"Foundation of Ministry of Industry and Information Technology","award":["TC220H05X-04"],"award-info":[{"award-number":["TC220H05X-04"]}]},{"name":"National Natural Science Foundation of China under Grant nos","award":["U20A20197, 62306187"],"award-info":[{"award-number":["U20A20197, 62306187"]}]},{"name":"National Natural Science Foundation of China under Grant nos","award":["U20A20197, 62306187"],"award-info":[{"award-number":["U20A20197, 62306187"]}]},{"name":"National Natural Science Foundation of China under Grant nos","award":["U20A20197, 62306187"],"award-info":[{"award-number":["U20A20197, 62306187"]}]},{"name":"National Natural Science Foundation of China under Grant nos","award":["U20A20197, 62306187"],"award-info":[{"award-number":["U20A20197, 62306187"]}]},{"name":"National Natural Science Foundation of China under Grant nos","award":["U20A20197, 62306187"],"award-info":[{"award-number":["U20A20197, 62306187"]}]},{"name":"National Natural Science Foundation of China under Grant nos","award":["U20A20197, 62306187"],"award-info":[{"award-number":["U20A20197, 62306187"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00371-024-03520-1","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T21:01:46Z","timestamp":1718658106000},"page":"2011-2027","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["CMT-6D: a lightweight iterative 6DoF pose estimation network based on cross-modal Transformer"],"prefix":"10.1007","volume":"41","author":[{"given":"Suyi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengdong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianning","family":"Chi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaosheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longxing","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanjiang","family":"Leng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,17]]},"reference":[{"key":"3520_CR1","doi-asserted-by":"publisher","unstructured":"Zhu, M., Derpanis, K.G., Yang, Y., Brahmbhatt, S., Zhang, M., Phillips, C., Lecce, M., Daniilidis, K.: Single image 3d object detection and pose estimation for grasping. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 3936\u20133943 (2014). https:\/\/doi.org\/10.1109\/ICRA.2014.6907430","DOI":"10.1109\/ICRA.2014.6907430"},{"issue":"3","key":"3520_CR2","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1109\/TIV.2020.2966074","volume":"5","author":"A Rangesh","year":"2020","unstructured":"Rangesh, A., Trivedi, M.M.: Ground plane polling for 6dof pose estimation of objects on the road. IEEE Trans. Intel. Veh. 5(3), 449\u2013460 (2020). https:\/\/doi.org\/10.1109\/TIV.2020.2966074","journal-title":"IEEE Trans. Intel. Veh."},{"issue":"12","key":"3520_CR3","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.: Pose estimation for augmented reality: a hands-on survey. IEEE Trans. Visual Comput. Graph. 22(12), 2633\u20132651 (2016). https:\/\/doi.org\/10.1109\/TVCG.2015.2513408","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"3520_CR4","doi-asserted-by":"publisher","unstructured":"Xu, D., Anguelov, D., Jain, A.: Pointfusion: Deep sensor fusion for 3d bounding box estimation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00033","DOI":"10.1109\/CVPR.2018.00033"},{"key":"3520_CR5","doi-asserted-by":"publisher","unstructured":"Charles, R.Q., Su, H., Kaichun, M., Guibas, L.J.: Pointnet: Deep learning on point sets for 3d classification and segmentation. In: 2017 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 77\u201385 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"key":"3520_CR6","doi-asserted-by":"publisher","unstructured":"Wang, C., Xu, D., Zhu, Y., Mart\u00edn-Mart\u00edn, R., Lu, C., Fei-Fei, L., Savarese, S.: Densefusion: 6d object pose estimation by iterative dense fusion. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3338\u20133347 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00346","DOI":"10.1109\/CVPR.2019.00346"},{"key":"3520_CR7","doi-asserted-by":"publisher","unstructured":"He, Y., Huang, H., Fan, H., Chen, Q., Sun, J.: Ffb6d: A full flow bidirectional fusion network for 6d pose estimation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3002\u20133012 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00302","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"3520_CR8","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: efficient attention pyramid transformer for image processing. IEEE Transactions on Multimedia (2021)"},{"key":"3520_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, C., Wan, H., Shen, X., Wu, Z.: Patchformer: An efficient point transformer with patch attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11799\u201311808 (2022)","DOI":"10.1109\/CVPR52688.2022.01150"},{"key":"3520_CR10","doi-asserted-by":"publisher","unstructured":"He, Y., Sun, W., Huang, H., Liu, J., Fan, H., Sun, J.: 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), pp. 11629\u201311638 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01165","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"3520_CR11","doi-asserted-by":"publisher","unstructured":"Yan, X., Zheng, C., Li, Z., Wang, S., Cui, S.: Pointasnl: Robust point clouds processing using nonlocal neural networks with adaptive sampling. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5588\u20135597 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00563","DOI":"10.1109\/CVPR42600.2020.00563"},{"issue":"10","key":"3520_CR12","doi-asserted-by":"publisher","first-page":"256","DOI":"10.3390\/jimaging8100256","volume":"8","author":"D Tsourounis","year":"2022","unstructured":"Tsourounis, D., Kastaniotis, D., Theoharatos, C., Kazantzidis, A., Economou, G.: Sift-cnn: when convolutional neural networks meet dense sift descriptors for image and sequence classification. J. Imaging 8(10), 256 (2022). https:\/\/doi.org\/10.3390\/jimaging8100256","journal-title":"J. Imaging"},{"key":"3520_CR13","doi-asserted-by":"publisher","unstructured":"Chetverikov, D., Svirko, D., Stepanov, D., Krsek, P.: The trimmed iterative closest point algorithm. In: 2002 International Conference on Pattern Recognition, vol. 3, pp. 545\u20135483 (2002). https:\/\/doi.org\/10.1109\/ICPR.2002.1047997","DOI":"10.1109\/ICPR.2002.1047997"},{"key":"3520_CR14","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.: Ep n p: an accurate o (n) solution to the p n p problem. Int. J. Comput. Vis. 81, 155\u2013166 (2009). https:\/\/doi.org\/10.1007\/s11263-008-0152-6","journal-title":"Int. J. Comput. Vis."},{"key":"3520_CR15","doi-asserted-by":"publisher","unstructured":"Hinterstoisser, S., Lepetit, V., Ilic, S., Holzer, S., Bradski, G., Konolige, K., Navab, N.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Computer Vision\u2013ACCV 2012: 11th Asian Conference on Computer Vision, Daejeon, Korea, November 5-9, 2012, Revised Selected Papers, Part I 11, pp. 548\u2013562 (2013). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"3520_CR16","doi-asserted-by":"publisher","unstructured":"Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6d object pose estimation using 3d object coordinates. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part II 13, pp. 536\u2013551 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_35","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"3520_CR17","doi-asserted-by":"publisher","unstructured":"Hodan, T., Haluza, P., Obdrlek, ., 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 (2017). https:\/\/doi.org\/10.1109\/WACV.2017.103","DOI":"10.1109\/WACV.2017.103"},{"key":"3520_CR18","doi-asserted-by":"publisher","unstructured":"Calli, B., Singh, A., Walsman, A., Srinivasa, S., Abbeel, P., Dollar, A.M.: The ycb object and model set: Towards common benchmarks for manipulation research. In: 2015 International Conference on Advanced Robotics (ICAR), pp. 510\u2013517 (2015). https:\/\/doi.org\/10.1109\/ICAR.2015.7251504","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"3520_CR19","doi-asserted-by":"publisher","unstructured":"Sundermeyer, M., Marton, Z.-C., Durner, M., Brucker, M., Triebel, R.: Implicit 3d orientation learning for 6d object detection from rgb images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 699\u2013715 (2018). https:\/\/doi.org\/10.48550\/arXiv.1902.01275","DOI":"10.48550\/arXiv.1902.01275"},{"key":"3520_CR20","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 preprint arXiv:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"3520_CR21","doi-asserted-by":"publisher","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: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1530\u20131538 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.169","DOI":"10.1109\/ICCV.2017.169"},{"key":"3520_CR22","doi-asserted-by":"publisher","unstructured":"Bay, H., Tuytelaars, T., Van\u00a0Gool, L.: Surf: Speeded up robust features. In: Computer Vision\u2013ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part I 9, pp. 404\u2013417 (2006). https:\/\/doi.org\/10.1007\/11744023","DOI":"10.1007\/11744023"},{"key":"3520_CR23","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: 2016 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"3520_CR24","doi-asserted-by":"publisher","unstructured":"Zhao, W., Zhang, S., Guan, Z., Zhao, W., Peng, J., Fan, J.: Learning deep network for detecting 3d object keypoints and 6d poses. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14122\u201314130 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01414","DOI":"10.1109\/CVPR42600.2020.01414"},{"key":"3520_CR25","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: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7677\u20137686 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00777","DOI":"10.1109\/ICCV.2019.00777"},{"key":"3520_CR26","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arXiv.2004.00605","DOI":"10.48550\/arXiv.2004.00605"},{"key":"3520_CR27","doi-asserted-by":"publisher","unstructured":"Peng, S., Zhou, X., Liu, Y., Lin, H., Huang, Q., Bao, H.: Pvnet: Pixel-wise voting network for 6dof object pose estimation, vol. 44, pp. 3212\u20133223 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3047388","DOI":"10.1109\/TPAMI.2020.3047388"},{"key":"3520_CR28","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: End-to-end learning for point cloud based 3d object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"},{"key":"3520_CR29","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"3520_CR30","doi-asserted-by":"publisher","unstructured":"Song, S., Xiao, J.: Sliding shapes for 3d object detection in depth images. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part VI 13, pp. 634\u2013651 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_41","DOI":"10.1007\/978-3-319-10599-4_41"},{"key":"3520_CR31","doi-asserted-by":"crossref","unstructured":"Gao, G., Lauri, M., Hu, X., Zhang, J., Frintrop, S.: Cloudaae: Learning 6d object pose regression with on-line data synthesis on point clouds. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 11081\u201311087 (2021). IEEE","DOI":"10.1109\/ICRA48506.2021.9561475"},{"key":"3520_CR32","first-page":"1","volume":"72","author":"G Zhou","year":"2022","unstructured":"Zhou, G., Wang, D., Yan, Y., Liu, C., Chen, Q.: 6-d object pose estimation using multiscale point cloud transformer. IEEE Trans. Instrum. Meas. 72, 1\u201311 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"3\u20134","key":"3520_CR33","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1002\/cav.2078","volume":"33","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Wang, C.: Parallel-branch network for 3d human pose and shape estimation in video. Comput. Anim. Virtual Worlds 33(3\u20134), 2078 (2022)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"3520_CR34","doi-asserted-by":"publisher","unstructured":"Jiang, X., Li, D., Chen, H., Zheng, Y., Zhao, R., Wu, L.: Uni6d: A unified cnn framework without projection breakdown for 6d pose estimation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11164\u201311174 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01089","DOI":"10.1109\/CVPR52688.2022.01089"},{"key":"3520_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3150568","volume":"71","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Liu, Y., Wu, Q., Zhou, J., Gong, X., Wang, J.: Eanet: edge-attention 6d pose estimation network for texture-less objects. IEEE Trans. Instrum. Measur. 71, 1\u201313 (2022). https:\/\/doi.org\/10.1109\/TIM.2022.3150568","journal-title":"IEEE Trans. Instrum. Measur."},{"key":"3520_CR36","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017). https:\/\/doi.org\/10.1609\/aaai.v31i1.11231","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"3520_CR37","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234\u2013241 (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3520_CR38","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3327772","author":"S Lin","year":"2023","unstructured":"Lin, S., Wang, Z., Zhang, S., Ling, Y., Yang, C.: Deep fusion for multi-modal 6d pose estimation. IEEE Trans. Autom. Sci. Eng. (2023). https:\/\/doi.org\/10.1109\/TASE.2023.3327772","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"3520_CR39","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 (2021). IEEE","DOI":"10.1109\/IJCNN52387.2021.9534175"},{"key":"3520_CR40","doi-asserted-by":"publisher","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.-E., Marcotegui, B., Goulette, F., Guibas, L.: Kpconv: Flexible and deformable convolution for point clouds. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6410\u20136419 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00651","DOI":"10.1109\/ICCV.2019.00651"},{"issue":"5","key":"3520_CR41","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1109\/TPAMI.1987.4767965","volume":"9","author":"KS Arun","year":"1987","unstructured":"Arun, K.S., Huang, T.S., Blostein, S.D.: Least-squares fitting of two 3-d point sets. IEEE Trans. Pattern Anal. Mach. Intell. PAMI 9(5), 698\u2013700 (1987). https:\/\/doi.org\/10.1109\/TPAMI.1987.4767965","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. PAMI"},{"key":"3520_CR42","doi-asserted-by":"publisher","unstructured":"Hodan, T., Michel, F., Brachmann, E., Kehl, W., GlentBuch, A., Kraft, D., Drost, B., Vidal, J., Ihrke, S., Zabulis, X., et al.: Bop: Benchmark for 6d object pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19\u201334 (2018). https:\/\/doi.org\/10.48550\/arXiv.1808.08319","DOI":"10.48550\/arXiv.1808.08319"},{"key":"3520_CR43","first-page":"17721","volume":"33","author":"X Wang","year":"2020","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: Solov2: dynamic and fast instance segmentation. Adv. Neural Inf. Process. Syst. 33, 17721\u201317732 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3520_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3520_CR45","doi-asserted-by":"publisher","unstructured":"Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., Markham, A.: Randla-net: Efficient semantic segmentation of large-scale point clouds. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11105\u201311114 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01112","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"3520_CR46","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3520_CR47","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.cag.2021.04.018","volume":"97","author":"L Zou","year":"2021","unstructured":"Zou, L., Huang, Z., Wang, F., Yang, Z., Wang, G.: Cma: cross-modal attention for 6d object pose estimation. Comput. Graph. 97, 139\u2013147 (2021). https:\/\/doi.org\/10.1016\/j.cag.2021.04.018","journal-title":"Comput. Graph."},{"key":"3520_CR48","doi-asserted-by":"publisher","first-page":"6907","DOI":"10.1109\/TIP.2022.3216980","volume":"31","author":"L Zou","year":"2022","unstructured":"Zou, L., Huang, Z., Gu, N., Wang, G.: 6d-vit: category-level 6d object pose estimation via transformer-based instance representation learning. IEEE Trans. Image Process. 31, 6907\u20136921 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3216980","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"3520_CR49","doi-asserted-by":"publisher","first-page":"6526","DOI":"10.1109\/LRA.2022.3174261","volume":"7","author":"S Lin","year":"2022","unstructured":"Lin, S., Wang, Z., Ling, Y., Tao, Y., Yang, C.: E2ek: end-to-end regression network based on keypoint for 6d pose estimation. IEEE Robot. Autom. Lett. 7(3), 6526\u20136533 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"3520_CR50","doi-asserted-by":"publisher","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: Dpod: 6d pose object detector and refiner. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1941\u20131950 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00203","DOI":"10.1109\/ICCV.2019.00203"},{"issue":"2","key":"3520_CR51","doi-asserted-by":"publisher","first-page":"1840","DOI":"10.1109\/LRA.2021.3136873","volume":"7","author":"T Xie","year":"2022","unstructured":"Xie, T., Wang, K., Li, R., Tang, X., Zhao, L.: Panet: a pixel-level attention network for 6d pose estimation with embedding vector features. IEEE Robot. Autom. Lett. 7(2), 1840\u20131847 (2022). https:\/\/doi.org\/10.1109\/LRA.2021.3136873","journal-title":"IEEE Robot. Autom. Lett."},{"key":"3520_CR52","doi-asserted-by":"publisher","unstructured":"Park, K., Patten, T., Vincze, M.: Pix2pose: Pixel-wise coordinate regression of objects for 6d pose estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7667\u20137676 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00776","DOI":"10.1109\/ICCV.2019.00776"},{"key":"3520_CR53","doi-asserted-by":"publisher","unstructured":"Song, C., Song, J., Huang, Q.: Hybridpose: 6d object pose estimation under hybrid representations. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 428\u2013437 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00051","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"3520_CR54","doi-asserted-by":"publisher","unstructured":"Sundermeyer, M., Durner, M., Puang, E.Y., Marton, Z.-C., Vaskevicius, N., Arras, K.O., Triebel, R.: Multi-path learning for object pose estimation across domains. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13913\u201313922 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01393","DOI":"10.1109\/CVPR42600.2020.01393"},{"key":"3520_CR55","doi-asserted-by":"publisher","first-page":"4394","DOI":"10.1109\/TMM.2021.3117092","volume":"24","author":"D Wang","year":"2022","unstructured":"Wang, D., Zhou, G., Yan, Y., Chen, H., Chen, Q.: Geopose: dense reconstruction guided 6d object pose estimation with geometric consistency. IEEE Trans. Multimedia 24, 4394\u20134408 (2022). https:\/\/doi.org\/10.1109\/TMM.2021.3117092","journal-title":"IEEE Trans. Multimedia"},{"key":"3520_CR56","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30 (2017)"},{"key":"3520_CR57","doi-asserted-by":"publisher","unstructured":"Shi, Y., Huang, J., Xu, X., Zhang, Y., Xu, K.: Stablepose: Learning 6d object poses from geometrically stable patches. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15217\u201315226 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01497","DOI":"10.1109\/CVPR46437.2021.01497"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03520-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03520-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03520-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T14:55:26Z","timestamp":1739372126000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03520-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,17]]},"references-count":57,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["3520"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03520-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,17]]},"assertion":[{"value":"27 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2024","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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}