{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T21:56:51Z","timestamp":1787003811286,"version":"build-2736575974"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":27,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-34757-y","type":"journal-article","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T15:47:53Z","timestamp":1767800873000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhanced RGB-D feature extraction for 6D pose estimation"],"prefix":"10.1038","volume":"16","author":[{"given":"Hongyuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianmin","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifeng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,7]]},"reference":[{"key":"34757_CR1","doi-asserted-by":"publisher","DOI":"10.3390\/s24041076","author":"J Guan","year":"2024","unstructured":"Guan, J., Hao, Y., Wu, Q., Li, S. & Fang, Y. A survey of 6DoF object pose estimation methods for different application scenarios. Sensors https:\/\/doi.org\/10.3390\/s24041076 (2024).","journal-title":"Sensors"},{"key":"34757_CR2","doi-asserted-by":"publisher","first-page":"4065","DOI":"10.1109\/TRO.2024.3433870","volume":"40","author":"S Thalhammer","year":"2024","unstructured":"Thalhammer, S. et al. Challenges for monocular 6-D object pose Estimation in robotics. IEEE Trans. Robot. 40, 4065\u20134084. https:\/\/doi.org\/10.1109\/TRO.2024.3433870 (2024).","journal-title":"IEEE Trans. Robot."},{"key":"34757_CR3","doi-asserted-by":"publisher","first-page":"143746","DOI":"10.1109\/ACCESS.2021.3114399","volume":"9","author":"S Hoque","year":"2021","unstructured":"Hoque, S., Arafat, M. Y., Xu, S., Maiti, A. & Wei, Y. A comprehensive review on 3D object detection and 6D pose Estimation with deep learning. IEEE Access. 9, 143746\u2013143770. https:\/\/doi.org\/10.1109\/ACCESS.2021.3114399 (2021).","journal-title":"IEEE Access."},{"key":"34757_CR4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.07801","author":"J Liu","year":"2024","unstructured":"Liu, J. et al. Deep Learning-Based object pose estimation: A comprehensive survey. ArXiv:2405 07801. https:\/\/doi.org\/10.48550\/arXiv.2405.07801 (2024).","journal-title":"ArXiv:2405 07801"},{"key":"34757_CR5","doi-asserted-by":"crossref","unstructured":"Wang, J., Rupprecht, C., & Novotny, D. PoseDiffusion solving pose estimation via diffusion-aided bundle adjustment. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), 9739\u20139749.","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"34757_CR6","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., & Birchfield, S. FoundationPose Unified 6D Pose Estimation and Tracking of Novel Objects. In 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 17868\u201317879 (IEEE, 2024).","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"34757_CR7","unstructured":"Li, C., Zhou, A. & Yao, A. Omni-Dimensional Dwynamic Convolution. In 2022 International Conference on Learning Representations (ICLR 2022)."},{"key":"34757_CR8","unstructured":"Yang, L., Zhang, R. Y., Li, L., & Xie, X. SimAM A Simple, Parameter-Free Attention Module for Convolutional Neural Networks. In Proceedings of the 38th International Conference on Machine Learning, Vol. 139 (eds Marina, M. & Tong, Z.) 11863\u201311874 (PMLR, Proceedings of Machine Learning Research, 2021)."},{"key":"34757_CR9","doi-asserted-by":"crossref","unstructured":"He, Y. et al. IEEE,. 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),\u00a011629\u201311638 (2020).","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"34757_CR10","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zand, M., Etemad, A. & Greenspan, M. Vote from the center: 6 DoF pose Estimation in RGB-D images by radial keypoint voting. In Computer Vision \u2013 ECCV 2022, 335\u2013352 (Springer Nature Switzerland, 2022).","DOI":"10.1007\/978-3-031-20080-9_20"},{"key":"34757_CR11","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., & Cipolla, R. PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization. In 2015 IEEE International Conference on Computer Vision (ICCV), 2938\u20132946.","DOI":"10.1109\/ICCV.2015.336"},{"key":"34757_CR12","doi-asserted-by":"crossref","unstructured":"Wang, H. et al. 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), 2637\u20132646.","DOI":"10.1109\/CVPR.2019.00275"},{"key":"34757_CR13","doi-asserted-by":"crossref","unstructured":"Peng, S. et al. Pixel-Wise Voting Network for 6DoF Pose Estimation. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4556\u20134565.","DOI":"10.1109\/CVPR.2019.00469"},{"key":"34757_CR14","doi-asserted-by":"crossref","unstructured":"Rusu, R. B., Blodow, N. & Beetz, M. Fast Point Feature Histograms (FPFH) for 3D registration. In 2009 IEEE International Conference on Robotics and Automation, 3212\u20133217.","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"34757_CR15","doi-asserted-by":"crossref","unstructured":"Segal, A. V., H\u00e4hnel, D. & Thrun, S. Generalized-ICP. In Robotics: Science and Systems\u00a0(2009).","DOI":"10.15607\/RSS.2009.V.021"},{"key":"34757_CR16","doi-asserted-by":"crossref","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 Conference on Computer Vision and Pattern Recognition (CVPR), 77\u201385.","DOI":"10.1109\/CVPR.2017.16"},{"key":"34757_CR17","unstructured":"Qi, C. R., Yi, L., Su, H., Guibas, L. J. & Pointnet++ Deep hierarchical feature learning on point sets in a metric space. In\u00a0Advances in neural information processing systems,\u00a030 (2017)."},{"key":"34757_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P. & Koltun, V. Point Transformer. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 16239\u201316248 (IEEE).","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"34757_CR19","doi-asserted-by":"crossref","unstructured":"Wang, C. et al. DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3338\u20133347.","DOI":"10.1109\/CVPR.2019.00346"},{"key":"34757_CR20","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 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3002\u20133012.","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"34757_CR21","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 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR),\u00a016606\u201316616 (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"34757_CR22","doi-asserted-by":"crossref","unstructured":"Shotton, J. et al. Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images. In 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2930\u20132937.","DOI":"10.1109\/CVPR.2013.377"},{"key":"34757_CR23","doi-asserted-by":"crossref","unstructured":"Kerl, C., Sturm, J. & Cremers, D. Dense visual SLAM for RGB-D cameras. In 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, 2100\u20132106.","DOI":"10.1109\/IROS.2013.6696650"},{"key":"34757_CR24","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:1711.00199 (2017). https:\/\/ui.adsabs.harvard.edu\/abs\/2017arXiv171100199X","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"34757_CR25","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L. & Sun, G. Squeeze-and-Excitation Networks. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition,\u00a07132\u20137141 (IEEE, 2018).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"34757_CR26","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y. & Kweon, I. S. CBAM: convolutional block attention module. In Computer Vision \u2013 ECCV 2018, 3\u201319 (Springer International Publishing, 2018).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"34757_CR27","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, S. & Maaten, L. v. d. & Weinberger, K. Q. CondenseNet: An Efficient DenseNet Using Learned Group Convolutions. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2752\u20132761.","DOI":"10.1109\/CVPR.2018.00291"},{"key":"34757_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770\u2013778 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"34757_CR29","doi-asserted-by":"crossref","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,\u00a0244\u2013253.","DOI":"10.1109\/CVPR.2018.00033"},{"key":"34757_CR30","doi-asserted-by":"crossref","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), 7667\u20137676.","DOI":"10.1109\/ICCV.2019.00776"},{"key":"34757_CR31","doi-asserted-by":"publisher","first-page":"5742","DOI":"10.1109\/TPAMI.2025.3553485","volume":"47","author":"X Liu","year":"2025","unstructured":"Liu, X. et al. A Geometry-Guided and fully Learning-Based object pose estimator. IEEE Trans. Pattern Anal. Mach. Intell. 47, 5742\u20135759. https:\/\/doi.org\/10.1109\/TPAMI.2025.3553485 (2025).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34757_CR32","doi-asserted-by":"crossref","unstructured":"Brachmann, E. et al. Learning 6D object pose Estimation using 3D object coordinates. In Computer Vision \u2013 ECCV 2014, 536\u2013551 (Springer International Publishing, 2014).","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"34757_CR33","doi-asserted-by":"crossref","unstructured":"Hodan, T. et al. T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects. In 2017\u00a0IEEE Winter Conference on Applications of Computer Vision (WACV). 880\u2013888 (IEEE, 2017).","DOI":"10.1109\/WACV.2017.103"},{"key":"34757_CR34","doi-asserted-by":"crossref","unstructured":"Kaskman, R., Zakharov, S., Shugurov, I., & Ilic, S. HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects. In 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW),\u00a02767\u20132776 (IEEE, 2019).","DOI":"10.1109\/ICCVW.2019.00338"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34757-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34757-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34757-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T09:30:03Z","timestamp":1770111003000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34757-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,7]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["34757"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-34757-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,7]]},"assertion":[{"value":"10 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2026","order":3,"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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"4656"}}