{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T23:04:03Z","timestamp":1772060643625,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-026-21437-w","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:34:08Z","timestamp":1772058848000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fusing shape descriptors and geometric details for robust category-level object pose estimation"],"prefix":"10.1007","volume":"85","author":[{"given":"Yun","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9068-0227","authenticated-orcid":false,"given":"Weiming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fu Lee","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingqiang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,25]]},"reference":[{"key":"21437_CR1","doi-asserted-by":"publisher","unstructured":"Ansary SI, Mishra A, Deb S et al (2024) A framework for robotic grasping of 3D objects in a tabletop environment. Multimedia Tools and Applications. https:\/\/doi.org\/10.1007\/s11042-024-20178-y","DOI":"10.1007\/s11042-024-20178-y"},{"key":"21437_CR2","doi-asserted-by":"publisher","first-page":"90089","DOI":"10.1007\/s11042-024-19081-3","volume":"83","author":"B Wang","year":"2024","unstructured":"Wang B, Zhang G, Zhang M et al (2024) PEC: Human-robot collaborative dataset for behavior recognition in pathology examination scenes. Multimedia Tools and Applications 83:90089\u201390103. https:\/\/doi.org\/10.1007\/s11042-024-19081-3","journal-title":"Multimedia Tools and Applications"},{"key":"21437_CR3","doi-asserted-by":"publisher","first-page":"51541","DOI":"10.1007\/s11042-023-17618-6","volume":"83","author":"X Liu","year":"2024","unstructured":"Liu X, Yan WQ, Kasabov N (2024) Moving vehicle tracking and scene understanding: A hybrid approach. Multimedia Tools and Applications 83:51541\u201351558. https:\/\/doi.org\/10.1007\/s11042-023-17618-6","journal-title":"Multimedia Tools and Applications"},{"key":"21437_CR4","doi-asserted-by":"publisher","unstructured":"Chen K, Dou Q (2021) SGPA: Structure-guided prior adaptation for category-level 6D object pose estimation. In: 2021 IEEE\/CVF International conference on computer vision (ICCV), pp 2753\u20132762. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00277","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"21437_CR5","doi-asserted-by":"publisher","unstructured":"Lin J, Wei Z, Ding C et al (2022) Category-level 6D object pose and size estimation using self-supervised deep prior deformation networks. In: Computer vision (ECCV), pp 19\u201334. https:\/\/doi.org\/10.48550\/arXiv.2207.05444","DOI":"10.48550\/arXiv.2207.05444"},{"key":"21437_CR6","doi-asserted-by":"publisher","unstructured":"Lee T, Lee B, Shin I et al (2022) UDA-COPE: Unsupervised domain adaptation for category-level object pose estimation. In: 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 14871\u201314880. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01447","DOI":"10.1109\/CVPR52688.2022.01447"},{"key":"21437_CR7","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang W, Wang FL et al (2024) Shape descriptor guided learning for category-level object pose estimation. In: Computer graphics international (CGI)","DOI":"10.1007\/978-3-031-82024-3_4"},{"key":"21437_CR8","doi-asserted-by":"publisher","unstructured":"Xiang Y, Schmidt T, Narayanan V et al (2017) PoseCNN: A convolutional neural network for 6D object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199, https:\/\/doi.org\/10.48550\/arXiv.1711.00199","DOI":"10.48550\/arXiv.1711.00199"},{"key":"21437_CR9","doi-asserted-by":"publisher","unstructured":"He Y, Sun W, Huang H et al (2020) PVN3D: A deep point-wise 3d keypoints voting network for 6dof pose estimation. In: IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 11632\u201311641. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01165","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"21437_CR10","doi-asserted-by":"publisher","unstructured":"He Y, Huang H, Fan H et al (2021) FFB6D: A full flow bidirectional fusion network for 6D pose estimation. In: IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 3003\u20133013. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00302","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"21437_CR11","doi-asserted-by":"publisher","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: 2019 IEEE\/CVF International conference on computer vision (ICCV), pp 7677\u20137686. https:\/\/doi.org\/10.1109\/ICCV.2019.00777","DOI":"10.1109\/ICCV.2019.00777"},{"key":"21437_CR12","doi-asserted-by":"publisher","unstructured":"Wang H, Sridhar S, Huang J et al (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), pp 2637\u20132646. https:\/\/doi.org\/10.1109\/CVPR.2019.00275","DOI":"10.1109\/CVPR.2019.00275"},{"key":"21437_CR13","doi-asserted-by":"publisher","unstructured":"Di Y, Zhang R, Lou Z et al (2022) GPV-Pose: Category-level object pose estimation via geometry-guided point-wise voting. In: 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 6771\u20136781. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00666","DOI":"10.1109\/CVPR52688.2022.00666"},{"key":"21437_CR14","doi-asserted-by":"publisher","unstructured":"Zheng L, Wang C, Sun Y et al (2023) HS-Pose: Hybrid scope feature extraction for category-level object pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 17163\u201317173. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01646","DOI":"10.1109\/CVPR52729.2023.01646"},{"key":"21437_CR15","doi-asserted-by":"publisher","unstructured":"Wang R, Wang X, Li T et al (2023) Query6DoF: Learning sparse queries as implicit shape prior for category-level 6DoF pose estimation. In: 2023 IEEE\/CVF International conference on computer vision (ICCV), pp 14009\u201314018. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01292","DOI":"10.1109\/ICCV51070.2023.01292"},{"key":"21437_CR16","doi-asserted-by":"publisher","unstructured":"Liu J, Chen Y, Ye X et al (2023) IST-Net: Prior-free category-level pose estimation with implicit space transformation. In: 2023 IEEE\/CVF International conference on computer vision (ICCV), pp 13932\u201313942. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01285","DOI":"10.1109\/ICCV51070.2023.01285"},{"key":"21437_CR17","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24:381\u2013395. https:\/\/doi.org\/10.1145\/358669.358692","journal-title":"Commun ACM"},{"key":"21437_CR18","doi-asserted-by":"publisher","first-page":"5421","DOI":"10.1007\/s00371-023-03113-4","volume":"40","author":"F Ullah","year":"2024","unstructured":"Ullah F, Wei W, Fan Z et al (2024) 6D object pose estimation based on dense convolutional object center voting with improved accuracy and efficiency. Vis Comput 40:5421\u20135434. https:\/\/doi.org\/10.1007\/s00371-023-03113-4","journal-title":"Vis Comput"},{"key":"21437_CR19","doi-asserted-by":"publisher","unstructured":"Peng S, Liu Y, Huang Q et al (2019) PVNet: Pixel-wise voting network for 6dof pose estimation. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 4556\u20134565. https:\/\/doi.org\/10.1109\/CVPR.2019.00469","DOI":"10.1109\/CVPR.2019.00469"},{"key":"21437_CR20","doi-asserted-by":"publisher","unstructured":"Pan H, Zhou J, Liu Y et al (2022) SO(3)-Pose: SO(3)-equivariance learning for 6D object pose estimation. In: Computer graphics forum, pp 371\u2013381. https:\/\/doi.org\/10.1111\/cgf.14684","DOI":"10.1111\/cgf.14684"},{"key":"21437_CR21","doi-asserted-by":"publisher","unstructured":"Wang C, Xu D, Zhu Y et al (2019) DenseFusion: 6D object pose estimation by iterative dense fusion. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 3338\u20133347. https:\/\/doi.org\/10.1109\/CVPR.2019.00346","DOI":"10.1109\/CVPR.2019.00346"},{"key":"21437_CR22","doi-asserted-by":"publisher","unstructured":"Sahin C, Kim TK (2018) Category-level 6D object pose recovery in depth images. In: Proceedings of the european conference on computer vision (ECCV) workshops, pp 1\u201316. https:\/\/doi.org\/10.48550\/arXiv.1808.00255","DOI":"10.48550\/arXiv.1808.00255"},{"key":"21437_CR23","doi-asserted-by":"publisher","unstructured":"Jeng KY, Liu YC, Liu Z et al (2020) GDN: A coarse-to-fine (C2F) representation for end-to-end 6-DoF grasp detection. In: Conference on robot learning, pp 220\u2013231. https:\/\/doi.org\/10.48550\/arXiv.2010.10695","DOI":"10.48550\/arXiv.2010.10695"},{"key":"21437_CR24","doi-asserted-by":"publisher","unstructured":"Zhang R, Di Y, Manhardt F et al (2022) SSP-Pose: Symmetry-aware shape prior deformation for direct category-level object pose estimation. In: 2022 IEEE\/RSJ International conference on intelligent robots and systems (IROS), pp 7452\u20137459. https:\/\/doi.org\/10.1109\/IROS47612.2022.9981506","DOI":"10.1109\/IROS47612.2022.9981506"},{"key":"21437_CR25","doi-asserted-by":"publisher","unstructured":"Tian M, Ang MH, Lee GH (2020) Shape prior deformation for categorical 6D object pose and size estimation. In: Computer vision \u2013 ECCV 2020, lecture notes in computer science, pp 530\u2013546. https:\/\/doi.org\/10.48550\/arXiv.2007.08454","DOI":"10.48550\/arXiv.2007.08454"},{"key":"21437_CR26","doi-asserted-by":"publisher","unstructured":"Lin J, Wei Z, Li Z et al (2021) DualPoseNet: Category-level 6D object pose and size estimation using dual pose network with refined learning of pose consistency. In: 2021 IEEE\/CVF International conference on computer vision (ICCV), pp 3540\u20133549. https:\/\/doi.org\/10.48550\/arXiv.2103.06526","DOI":"10.48550\/arXiv.2103.06526"},{"key":"21437_CR27","doi-asserted-by":"publisher","unstructured":"He K, Gkioxari G, Dollar P et al (2020) Mask R-CNN. In: IEEE Transactions on pattern analysis and machine intelligence, pp 386\u2013397. https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"21437_CR28","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on computer vision and pattern recognition (CVPR), pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"21437_CR29","unstructured":"Qi CR, Yi L, Su H et al (2017) PointNet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30"},{"key":"21437_CR30","doi-asserted-by":"publisher","unstructured":"Liu C, Yu S, Yu M et al (2021) Adaptive smooth L1 loss: A better way to regress scene texts with extreme aspect ratios. In: 2021 IEEE Symposium on computers and communications (ISCC), pp 1\u20137. https:\/\/doi.org\/10.1109\/ISCC53001.2021.9631466","DOI":"10.1109\/ISCC53001.2021.9631466"},{"key":"21437_CR31","doi-asserted-by":"publisher","unstructured":"Li G, Li Y, Ye Z et al (2022) Generative category-level shape and pose estimation with semantic primitives. In: Conference on robot learning, pp 1390\u20131400. https:\/\/doi.org\/10.48550\/arXiv.2210.01112","DOI":"10.48550\/arXiv.2210.01112"},{"key":"21437_CR32","doi-asserted-by":"publisher","unstructured":"Lin ZH, Huang SY, Wang YCF (2020) Convolution in the cloud: Learning deformable kernels in 3D graph convolution networks for point cloud analysis. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 1800\u20131809. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00187","DOI":"10.1109\/CVPR42600.2020.00187"},{"key":"21437_CR33","doi-asserted-by":"publisher","unstructured":"Zhao H, Shi J, Qi X et al (2017) Pyramid scene parsing network. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 6230\u20136239. https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"21437_CR34","doi-asserted-by":"publisher","unstructured":"Wang J, Chen K, Dou Q (2021) Category-level 6D object pose estimation via cascaded relation and recurrent reconstruction networks. In: 2021 IEEE\/RSJ International conference on intelligent robots and systems (IROS), pp 4807\u20134814. https:\/\/doi.org\/10.1109\/IROS51168.2021.9636212","DOI":"10.1109\/IROS51168.2021.9636212"},{"key":"21437_CR35","unstructured":"Lin H, Liu Z, Cheang C et al (2021) DONet: Learning category-level 6d object pose and size estimation from depth observation. arXiv preprint arXiv:2106.14193 2"},{"key":"21437_CR36","doi-asserted-by":"publisher","unstructured":"Zhang R, Di Y, Lou Z et al (2022) RPB-Pose: Residual bounding box projection for category-level pose estimation. In: European conference on computer vision, pp 655\u2013672. https:\/\/doi.org\/10.1007\/978-3-031-19769-7_38","DOI":"10.1007\/978-3-031-19769-7_38"},{"key":"21437_CR37","doi-asserted-by":"publisher","unstructured":"Chen D, Li J, Wang Z et al (2020) Learning canonical shape space for category-level 6D object pose and size estimation. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 11973\u201311982. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01199","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"21437_CR38","doi-asserted-by":"publisher","unstructured":"Lin H, Liu Z, Cheang C et al (2022) SAR-Net: Shape alignment and recovery network for category-level 6D object pose and size estimation. In: 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 6697\u20136707. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00659","DOI":"10.1109\/CVPR52688.2022.00659"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21437-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21437-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21437-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:34:10Z","timestamp":1772058850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21437-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,25]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["21437"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21437-w","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,25]]},"assertion":[{"value":"11 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare that there are no conflict of interest regarding the publication of this paper.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"185"}}