{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T12:08:45Z","timestamp":1779970125448,"version":"3.53.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Displays"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.displa.2026.103539","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T15:11:41Z","timestamp":1779289901000},"page":"103539","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SSA-Pose: Spatial shape awareness for RGB-based category-level object pose estimation"],"prefix":"10.1016","volume":"95","author":[{"given":"Hongzhi","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruida","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Di","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ze","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbiao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jigui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.displa.2026.103539_b1","doi-asserted-by":"crossref","unstructured":"Y. Di, C. Zhang, C. Wang, R. Zhang, G. Zhai, Y. Li, B. Fu, X. Ji, S. Gao, Shapematcher: Self-supervised joint shape canonicalization segmentation retrieval and deformation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21017\u201321028.","DOI":"10.1109\/CVPR52733.2024.01986"},{"key":"10.1016\/j.displa.2026.103539_b2","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.displa.2018.10.003","article-title":"Designing of marker-based augmented reality learning environment for kids using convolutional neural network architecture","volume":"55","author":"Dash","year":"2018","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103539_b3","first-page":"1","article-title":"Se(3)-equivariance learning for category-level object pose estimation","volume":"74","author":"Du","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.displa.2026.103539_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2025.103069","article-title":"From visual understanding to 6D pose reconstruction: A cutting-edge review of deep learning-based object pose estimation","volume":"89","author":"Wang","year":"2025","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103539_b5","series-title":"Street Gaussians without 3d object tracker","author":"Zhang","year":"2024"},{"key":"10.1016\/j.displa.2026.103539_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2025.103224","article-title":"Less is more: An effective method to extract object features for visual dynamic SLAM","volume":"91","author":"Zhang","year":"2026","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103539_b7","doi-asserted-by":"crossref","unstructured":"Y. Di, F. Manhardt, G. Wang, X. Ji, N. Navab, F. Tombari, So-pose: Exploiting self-occlusion for direct 6d pose estimation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 12396\u201312405.","DOI":"10.1109\/ICCV48922.2021.01217"},{"key":"10.1016\/j.displa.2026.103539_b8","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6708","article-title":"ES6D: A computation efficient and symmetry-aware 6D pose regression framework","author":"Mo","year":"2022"},{"key":"10.1016\/j.displa.2026.103539_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2022.3148812","article-title":"EPro-PnP: Generalized end-to-end probabilistic perspective-N-points for monocular object pose estimation","author":"Chen","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.displa.2026.103539_b10","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2637","article-title":"Normalized object coordinate space for category-level 6D object pose and size estimation","author":"Wang","year":"2019"},{"key":"10.1016\/j.displa.2026.103539_b11","doi-asserted-by":"crossref","DOI":"10.1109\/34.88573","article-title":"Least-squares estimation of transformation parameters between two point patterns","author":"Umeyama","year":"1991","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.displa.2026.103539_b12","doi-asserted-by":"crossref","unstructured":"M. Tian, M.H. Ang Jr., G.H. Lee, Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2020.","DOI":"10.1007\/978-3-030-58589-1_32"},{"issue":"4","key":"10.1016\/j.displa.2026.103539_b13","doi-asserted-by":"crossref","first-page":"9597","DOI":"10.1109\/LRA.2022.3189792","article-title":"SDFEst: Categorical pose and shape estimation of objects from RGB-D using signed distance fields","volume":"7","author":"Bruns","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"10.1016\/j.displa.2026.103539_b14","doi-asserted-by":"crossref","first-page":"1784","DOI":"10.1109\/LRA.2022.3142441","article-title":"iCaps: Iterative category-level object pose and shape estimation","volume":"7","author":"Deng","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.displa.2026.103539_b15","series-title":"International Conference on Machine Learning","first-page":"1945","article-title":"Grammar variational autoencoder","author":"Kusner","year":"2017"},{"key":"10.1016\/j.displa.2026.103539_b16","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1581","article-title":"FS-net: Fast shape-based network for category-level 6D object pose estimation with decoupled rotation mechanism","author":"Chen","year":"2021"},{"key":"10.1016\/j.displa.2026.103539_b17","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6771","article-title":"GPV-pose: Category-level object pose estimation via geometry-guided point-wise voting","author":"Di","year":"2022"},{"key":"10.1016\/j.displa.2026.103539_b18","doi-asserted-by":"crossref","unstructured":"R. Zhang, Y. Di, Z. Lou, F. Manhardt, F. Tombari, X. Ji, RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation, in: European Conference on Computer Vision, 2022, pp. 655\u2013672.","DOI":"10.1007\/978-3-031-19769-7_38"},{"key":"10.1016\/j.displa.2026.103539_b19","doi-asserted-by":"crossref","unstructured":"L. Zheng, C. Wang, Y. Sun, E. Dasgupta, H. Chen, A. Leonardis, W. Zhang, H.J. Chang, 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, 2023, pp. 17163\u201317173.","DOI":"10.1109\/CVPR52729.2023.01646"},{"issue":"4","key":"10.1016\/j.displa.2026.103539_b20","doi-asserted-by":"crossref","first-page":"8575","DOI":"10.1109\/LRA.2021.3110538","article-title":"Category-level metric scale object shape and pose estimation","volume":"6","author":"Lee","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.displa.2026.103539_b21","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"220","article-title":"Object level depth reconstruction for category level 6D object pose estimation from monocular RGB image","author":"Fan","year":"2022"},{"key":"10.1016\/j.displa.2026.103539_b22","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"2036","article-title":"RGB-based category-level object pose estimation via decoupled metric scale recovery","author":"Wei","year":"2024"},{"issue":"6","key":"10.1016\/j.displa.2026.103539_b23","doi-asserted-by":"crossref","first-page":"5377","DOI":"10.1109\/LRA.2025.3559841","article-title":"RGB-based category-level object pose estimation via depth recovery and adaptive refinement","volume":"10","author":"Yang","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.displa.2026.103539_b24","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"467","article-title":"LaPose: Laplacian mixture shape modeling for RGB-based category-level object pose estimation","author":"Zhang","year":"2025"},{"key":"10.1016\/j.displa.2026.103539_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2023.102553","article-title":"Self-supervised deep monocular visual odometry and depth estimation with observation variation","volume":"80","author":"Zhao","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103539_b26","doi-asserted-by":"crossref","unstructured":"E.R. Chan, C.Z. Lin, M.A. Chan, K. Nagano, B. Pan, S. De Mello, O. Gallo, L.J. Guibas, J. Tremblay, S. Khamis, et al., Efficient geometry-aware 3d generative adversarial networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16123\u201316133.","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"10.1016\/j.displa.2026.103539_b27","unstructured":"A. Jaegle, F. Gimeno, A. Brock, O. Vinyals, A. Zisserman, J. Carreira, Perceiver: General perception with iterative attention, in: Proc. Inf. Mach. Learn., 2021, pp. 4651\u20134664."},{"key":"10.1016\/j.displa.2026.103539_b28","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3338","article-title":"DenseFusion: 6D object pose estimation by iterative dense fusion","author":"Wang","year":"2019"},{"key":"10.1016\/j.displa.2026.103539_b29","unstructured":"C.R. Qi, H. Su, K. Mo, L.J. Guibas, Pointnet: Deep learning on point sets for 3d classification and segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 652\u2013660."},{"key":"10.1016\/j.displa.2026.103539_b30","doi-asserted-by":"crossref","unstructured":"Y. He, W. Sun, H. Huang, J. Liu, H. Fan, J. Sun, Pvn3d: A deep point-wise 3d keypoints voting network for 6dof pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11632\u201311641.","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"10.1016\/j.displa.2026.103539_b31","doi-asserted-by":"crossref","unstructured":"Y. He, H. Huang, H. Fan, Q. Chen, J. Sun, FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 3003\u20133013.","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"10.1016\/j.displa.2026.103539_b32","doi-asserted-by":"crossref","unstructured":"G. Wang, F. Manhardt, F. Tombari, X. Ji, GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 16611\u201316621.","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"10.1016\/j.displa.2026.103539_b33","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4556","article-title":"PVNet: Pixel-wise voting network for 6dof pose estimation","author":"Peng","year":"2019"},{"key":"10.1016\/j.displa.2026.103539_b34","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1797","article-title":"Convolution in the cloud: Learning deformable kernels in 3D graph convolution networks for point cloud analysis","author":"Lin","year":"2020"},{"key":"10.1016\/j.displa.2026.103539_b35","doi-asserted-by":"crossref","unstructured":"C. Deng, O. Litany, Y. Duan, A. Poulenard, A. Tagliasacchi, L.J. Guibas, Vector neurons: A general framework for so (3)-equivariant networks, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 12200\u201312209.","DOI":"10.1109\/ICCV48922.2021.01198"},{"key":"10.1016\/j.displa.2026.103539_b36","series-title":"Conference on Robot Learning","first-page":"1390","article-title":"Generative category-level shape and pose estimation with semantic primitives","author":"Li","year":"2023"},{"key":"10.1016\/j.displa.2026.103539_b37","doi-asserted-by":"crossref","unstructured":"Y. Chen, Y. Di, G. Zhai, F. Manhardt, C. Zhang, R. Zhang, F. Tombari, N. Navab, B. Busam, Secondpose: Se (3)-consistent dual-stream feature fusion for category-level pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 9959\u20139969.","DOI":"10.1109\/CVPR52733.2024.00950"},{"key":"10.1016\/j.displa.2026.103539_b38","doi-asserted-by":"crossref","unstructured":"J. Liu, Y. Chen, X. Ye, X. Qi, Ist-net: Prior-free category-level pose estimation with implicit space transformation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 13978\u201313988.","DOI":"10.1109\/ICCV51070.2023.01285"},{"key":"10.1016\/j.displa.2026.103539_b39","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21040","article-title":"Instance-adaptive and geometric-aware keypoint learning for category-level 6D object pose estimation","author":"Lin","year":"2024"},{"issue":"2","key":"10.1016\/j.displa.2026.103539_b40","doi-asserted-by":"crossref","first-page":"p.155","DOI":"10.1007\/s11263-008-0152-6","article-title":"EPnP: An accurate o(n) solution to the PnP problem","volume":"81","author":"Lepetit","year":"2009","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.displa.2026.103539_b41","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.displa.2026.103539_b42","article-title":"Mask R-CNN","author":"He","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.displa.2026.103539_b43","doi-asserted-by":"crossref","unstructured":"Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, S. Xie, A ConvNet for the 2020s, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"10.1016\/j.displa.2026.103539_b44","series-title":"The Twelfth International Conference on Learning Representations","article-title":"LRM: Large reconstruction model for single image to 3D","author":"Hong","year":"2024"},{"key":"10.1016\/j.displa.2026.103539_b45","series-title":"Real3D: Scaling up large reconstruction models with real-world images","author":"Jiang","year":"2024"},{"key":"10.1016\/j.displa.2026.103539_b46","doi-asserted-by":"crossref","unstructured":"L. Mescheder, M. Oechsle, M. Niemeyer, S. Nowozin, A. Geiger, Occupancy networks: Learning 3d reconstruction in function space, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., 2019, pp. 4460\u20134470.","DOI":"10.1109\/CVPR.2019.00459"},{"key":"10.1016\/j.displa.2026.103539_b47","doi-asserted-by":"crossref","unstructured":"Y. Chen, L. Tai, K. Sun, M. Li, MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"10.1016\/j.displa.2026.103539_b48","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume":"vol. 30","author":"Kendall","year":"2017"},{"key":"10.1016\/j.displa.2026.103539_b49","series-title":"2019 International Conference on 3D Vision","first-page":"614","article-title":"On object symmetries and 6D pose estimation from images","author":"Pitteri","year":"2019"},{"key":"10.1016\/j.displa.2026.103539_b50","series-title":"Intelligent Autonomous Systems 17: Proceedings of the 17th International Conference IAS-17","first-page":"360","article-title":"On the evaluation of RGB-D-based categorical pose and shape estimation","author":"Bruns","year":"2023"},{"key":"10.1016\/j.displa.2026.103539_b51","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, et al., Segment anything, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["Displays"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226002027?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226002027?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T11:46:46Z","timestamp":1779968806000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0141938226002027"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":51,"alternative-id":["S0141938226002027"],"URL":"https:\/\/doi.org\/10.1016\/j.displa.2026.103539","relation":{},"ISSN":["0141-9382"],"issn-type":[{"value":"0141-9382","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SSA-Pose: Spatial shape awareness for RGB-based category-level object pose estimation","name":"articletitle","label":"Article Title"},{"value":"Displays","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.displa.2026.103539","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103539"}}