{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T13:16:23Z","timestamp":1761570983972,"version":"build-2065373602"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11432-024-4543-3","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:44:31Z","timestamp":1761561871000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Memory-based diverse-category single-view 3D reconstruction"],"prefix":"10.1007","volume":"69","author":[{"given":"Haoyu","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyan","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,23]]},"reference":[{"key":"4543_CR1","doi-asserted-by":"publisher","first-page":"182305","DOI":"10.1007\/s11432-024-4056-8","volume":"67","author":"C Wang","year":"2024","unstructured":"Wang C, Li X, Gu Y F, et al. An adaptive 3D reconstruction method for asymmetric dual-angle multispectral stereo imaging system on UAV platform. Sci China Inf Sci, 2024, 67: 182305","journal-title":"Sci China Inf Sci"},{"key":"4543_CR2","first-page":"767","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Y Yao","year":"2018","unstructured":"Yao Y, Luo Z, Li S, et al. MVSNet: depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision (ECCV), 2018. 767\u2013783"},{"key":"4543_CR3","doi-asserted-by":"publisher","first-page":"112106","DOI":"10.1007\/s11432-021-3323-2","volume":"66","author":"Z Zhou","year":"2023","unstructured":"Zhou Z, Meng M, Zhou Y, et al. Model-guided 3D stitching for augmented virtual environment. Sci China Inf Sci, 2023, 66: 112106","journal-title":"Sci China Inf Sci"},{"key":"4543_CR4","doi-asserted-by":"publisher","first-page":"202206","DOI":"10.1007\/s11432-021-3425-8","volume":"65","author":"C X Liu","year":"2022","unstructured":"Liu C X, Qin J H, Wang S, et al. Accurate RGB-D SLAM in dynamic environments based on dynamic visual feature removal. Sci China Inf Sci, 2022, 65: 202206","journal-title":"Sci China Inf Sci"},{"key":"4543_CR5","first-page":"2463","volume-title":"Proceedings of the 30th IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"H Q Fan","year":"2017","unstructured":"Fan H Q, Su H, Guibas L, et al. A point set generation network for 3D object reconstruction from a single image. In: Proceedings of the 30th IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017. 2463\u20132471"},{"key":"4543_CR6","first-page":"628","volume-title":"Proceedings of the 14th European Conference on Computer Vision (ECCV)","author":"C B Choy","year":"2016","unstructured":"Choy C B, Xu D F, Gwak J Y, et al. 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Proceedings of the 14th European Conference on Computer Vision (ECCV), Amsterdam, 2016. 628\u2013644"},{"key":"4543_CR7","first-page":"52","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"N Wang","year":"2018","unstructured":"Wang N, Zhang Y, Li Z, et al. Pixel2Mesh: generating 3D mesh models from single RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), 2018. 52\u201367"},{"key":"4543_CR8","first-page":"1696","volume-title":"Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS)","author":"X C Yan","year":"2016","unstructured":"Yan X C, Yang J M, Yumer E, et al. Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. In: Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS), Barcelona, 2016. 1696\u20131704"},{"key":"4543_CR9","first-page":"209","volume-title":"Proceedings of the 30th IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"S Tulsiani","year":"2017","unstructured":"Tulsiani S, Zhou T H, Efros A A, et al. Multi-view supervision for single-view reconstruction via differentiable ray consistency. In: Proceedings of the 30th IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017. 209\u2013217"},{"key":"4543_CR10","first-page":"7708","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"S Liu","year":"2019","unstructured":"Liu S, Li T, Chen W, et al. Soft rasterizer: a differentiable renderer for image-based 3D reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019. 7708\u20137717"},{"key":"4543_CR11","first-page":"18","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"K L Navaneet","year":"2019","unstructured":"Navaneet K L, Mandikal P, Jampani V, et al. Differ: moving beyond 3D reconstruction with differentiable feature rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. 18\u201324"},{"key":"4543_CR12","first-page":"2807","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"E Insafutdinov","year":"2018","unstructured":"Insafutdinov E, Dosovitskiy A. Unsupervised learning of shape and pose with differentiable point clouds. In: Proceedings of Advances in Neural Information Processing Systems, 2018. 2807\u20132817"},{"key":"4543_CR13","first-page":"1536","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Duggal","year":"2022","unstructured":"Duggal S, Pathak D. Topologically-aware deformation fields for single-view 3D reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 1536\u20131546"},{"key":"4543_CR14","first-page":"673","volume-title":"Proceedings of European Conference on Computer Vision","author":"J Zhang","year":"2022","unstructured":"Zhang J, Ren D, Cai Z, et al. Monocular 3D object reconstruction with GAN inversion. In: Proceedings of European Conference on Computer Vision, 2022. 673\u2013689"},{"key":"4543_CR15","first-page":"1129","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"K L Navaneet","year":"2020","unstructured":"Navaneet K L, Mathew A, Kashyap S, et al. From image collections to point clouds with self-supervised shape and pose networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 1129\u20131137"},{"key":"4543_CR16","first-page":"285","volume-title":"Proceedings of European Conference on Computer Vision","author":"T Monnier","year":"2022","unstructured":"Monnier T, Fisher M, Efros A A, et al. Share with thy neighbors: single-view reconstruction by cross-instance consistency. In: Proceedings of European Conference on Computer Vision, 2022. 285\u2013303"},{"key":"4543_CR17","first-page":"10208","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Szymanowicz","year":"2024","unstructured":"Szymanowicz S, Rupprecht C, Vedaldi A. Splatter image: ultra-fast single-view 3D reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024. 10208\u201310217"},{"key":"4543_CR18","unstructured":"Xu D, Yuan Y, Mardani M, et al. AGG: amortized generative 3D Gaussians for single image to 3D. 2024. ArXiv:2401.04099"},{"key":"4543_CR19","first-page":"10061","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Huang","year":"2024","unstructured":"Huang Z, Stojanov S, Thai A, et al. ZeroShape: regression-based zero-shot shape reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024. 10061\u201310071"},{"key":"4543_CR20","first-page":"3773","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K V Alwala","year":"2022","unstructured":"Alwala K V, Gupta A, Tulsiani S. Pre-train, self-train, distill: a simple recipe for supersizing 3D reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 3773\u20133782"},{"key":"4543_CR21","first-page":"12912","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Huang","year":"2023","unstructured":"Huang Z, Jampani V, Thai A, et al. Shapeclipper: scalable 3D shape learning from single-view images via geometric and clip-based consistency. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023. 12912\u201312922"},{"key":"4543_CR22","unstructured":"Chang A X, Funkhouser T, Guibas L, et al. ShapeNet: an information-rich 3D model repository. 2015. ArXiv:1512.03012"},{"key":"4543_CR23","first-page":"2974","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"X Sun","year":"2018","unstructured":"Sun X, Wu J, Zhang X, et al. Pix3D: dataset and methods for single-image 3D shape modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 2974\u20132983"},{"key":"4543_CR24","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/WACV.2014.6836101","volume-title":"Proceedings of IEEE Winter Conference on Applications of Computer Vision","author":"Y Xiang","year":"2014","unstructured":"Xiang Y, Mottaghi R, Savarese S. Beyond Pascal: a benchmark for 3D object detection in the wild. In: Proceedings of IEEE Winter Conference on Applications of Computer Vision, 2014. 75\u201382"},{"key":"4543_CR25","unstructured":"Di Y, Zhang C, Wang P, et al. CCD-3DR: consistent conditioning in diffusion for single-image 3D reconstruction. 2023. ArXiv:2308.07837"},{"key":"4543_CR26","first-page":"12923","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Melas-Kyriazi","year":"2023","unstructured":"Melas-Kyriazi L, Rupprecht C, Vedaldi A. PC2: projection-conditioned point cloud diffusion for single-image 3D reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023. 12923\u201312932"},{"key":"4543_CR27","doi-asserted-by":"publisher","first-page":"4523","DOI":"10.1007\/s42835-024-01812-z","volume":"19","author":"T Kim","year":"2024","unstructured":"Kim T, Lee J, Lee K T, et al. Single-view 3D reconstruction based on gradient-applied weighted loss. J Electr Eng Technol, 2024, 19: 4523\u20134535","journal-title":"J Electr Eng Technol"},{"key":"4543_CR28","unstructured":"Tochilkin D, Pankratz D, Liu Z, et al. TripoSR: fast 3D object reconstruction from a single image. 2024. ArXiv:2403.02151"},{"key":"4543_CR29","doi-asserted-by":"publisher","first-page":"3746","DOI":"10.1109\/TIP.2023.3279661","volume":"32","author":"X Yang","year":"2023","unstructured":"Yang X, Lin G, Zhou L. Single-view 3D mesh reconstruction for seen and unseen categories. IEEE Trans Image Process, 2023, 32: 3746\u20133758","journal-title":"IEEE Trans Image Process"},{"key":"4543_CR30","first-page":"1","volume-title":"Proceedings of International Conference on Control, Automation and Diagnosis (ICCAD)","author":"N E H Kaiber","year":"2024","unstructured":"Kaiber N E H, Mekhaznia T, Lakhdara Z. Transfer learning-based approach for 3D reconstruction from a single 2D image. In: Proceedings of International Conference on Control, Automation and Diagnosis (ICCAD), 2024. 1\u20136"},{"key":"4543_CR31","first-page":"371","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"A Kanazawa","year":"2018","unstructured":"Kanazawa A, Tulsiani S, Efros A A, et al. Learning category-specific mesh reconstruction from image collections. In: Proceedings of the European Conference on Computer Vision (ECCV), 2018. 371\u2013386"},{"key":"4543_CR32","first-page":"2897","volume-title":"Proceedings of the 31st IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"S Tulsiani","year":"2018","unstructured":"Tulsiani S, Efros A A, Malik J, et al. Multi-view consistency as supervisory signal for learning shape and pose prediction. In: Proceedings of the 31st IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, 2018. 2897\u20132905"},{"key":"4543_CR33","first-page":"11453","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"C H Lin","year":"2020","unstructured":"Lin C H, Wang C, Lucey S. SDF-SRN: learning signed distance 3D object reconstruction from static images. In: Proceedings of Advances in Neural Information Processing Systems, 2020. 11453\u201311464"},{"key":"4543_CR34","unstructured":"Hong Y, Zhang K, Gu J, et al. LRM: large reconstruction model for single image to 3D. 2023. ArXiv:2311.04400"},{"key":"4543_CR35","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"M Liu","year":"2024","unstructured":"Liu M, Xu C, Jin H, et al. One-2-3-45: any single image to 3D mesh in 45 seconds without per-shape optimization. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4543_CR36","first-page":"6002","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"T Hu","year":"2021","unstructured":"Hu T, Wang L, Xu X, et al. Self-supervised 3D mesh reconstruction from single images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021. 6002\u20136011"},{"key":"4543_CR37","first-page":"88","volume-title":"Proceedings of the 16th European Conference on Computer Vision","author":"S Goel","year":"2020","unstructured":"Goel S, Kanazawa A, Malik J. Shape and viewpoint without keypoints. In: Proceedings of the 16th European Conference on Computer Vision, Glasgow, 2020. 88\u2013104"},{"key":"4543_CR38","first-page":"677","volume-title":"Proceedings of the 16th European Conference on Computer Vision","author":"X Li","year":"2020","unstructured":"Li X, Liu S, Kim K, et al. Self-supervised single-view 3D reconstruction via semantic consistency. In: Proceedings of the 16th European Conference on Computer Vision, Glasgow, 2020. 677\u2013693"},{"key":"4543_CR39","unstructured":"Tulsiani S, Kulkarni N, Gupta A. Implicit mesh reconstruction from unannotated image collections. 2020. ArXiv:2007.08504"},{"key":"4543_CR40","first-page":"8843","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Ye","year":"2021","unstructured":"Ye Y, Tulsiani S, Gupta A. Shelf-supervised mesh prediction in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021. 8843\u20138852"},{"key":"4543_CR41","first-page":"2921","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"B Zhou","year":"2016","unstructured":"Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 2921\u20132929"},{"key":"4543_CR42","first-page":"132","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"J Xie","year":"2021","unstructured":"Xie J, Luo C, Zhu X, et al. Online refinement of low-level feature based activation map for weakly supervised object localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021. 132\u2013141"},{"key":"4543_CR43","first-page":"14228","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"P Wu","year":"2022","unstructured":"Wu P, Zhai W, Cao Y. Background activation suppression for weakly supervised object localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. 14228\u201314237"},{"key":"4543_CR44","doi-asserted-by":"crossref","unstructured":"Xie J, Xiang J, Chen J, et al. Contrastive learning of class-agnostic activation map for weakly supervised object localization and semantic segmentation. 2022. ArXiv:2203.13505","DOI":"10.1109\/CVPR52688.2022.00106"},{"key":"4543_CR45","first-page":"8748","volume-title":"Proceedings of International Conference on Machine Learning","author":"A Radford","year":"2021","unstructured":"Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision. In: Proceedings of International Conference on Machine Learning, 2021. 8748\u20138763"},{"key":"4543_CR46","doi-asserted-by":"publisher","first-page":"107404","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin X, Zhang Z, Huang C, et al. U2-Net: going deeper with nested U-structure for salient object detection. Pattern Recogn, 2020, 106: 107404","journal-title":"Pattern Recogn"},{"key":"4543_CR47","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis, 2015, 115: 211\u2013252","journal-title":"Int J Comput Vis"},{"key":"4543_CR48","first-page":"317","volume-title":"Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques","author":"M Desbrun","year":"1999","unstructured":"Desbrun M, Meyer M, Schroder P, et al. Implicit fairing of irregular meshes using diffusion and curvature flow. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, 1999. 317\u2013324"},{"key":"4543_CR49","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/1174429.1174494","volume-title":"Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia","author":"A Nealen","year":"2006","unstructured":"Nealen A, Igarashi T, Sorkine O, et al. Laplacian mesh optimization. In: Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, 2006. 381\u2013389"},{"key":"4543_CR50","first-page":"3907","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"H Kato","year":"2018","unstructured":"Kato H, Ushiku Y, Harada T. Neural 3D mesh renderer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 3907\u20133916"},{"key":"4543_CR51","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/34.121791","volume":"14","author":"P J Besl","year":"1992","unstructured":"Besl P J, McKay N D. A method for registration of 3-D shapes. IEEE Trans Pattern Anal Mach Intell, 1992, 14: 239\u2013256","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4543_CR52","first-page":"3504","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"M Niemeyer","year":"2020","unstructured":"Niemeyer M, Mescheder L, Oechsle M, et al. Differentiable volumetric rendering: learning implicit 3D representations without 3D supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020. 3504\u20133515"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4543-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4543-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4543-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T12:04:06Z","timestamp":1761566646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4543-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,23]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["4543"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4543-3","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"type":"print","value":"1674-733X"},{"type":"electronic","value":"1869-1919"}],"subject":[],"published":{"date-parts":[[2025,10,23]]},"assertion":[{"value":"8 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"122106"}}