{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:01:22Z","timestamp":1780495282200,"version":"3.54.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017592","name":"Key Science and Technology Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2025ZC- KJXX-25"],"award-info":[{"award-number":["2025ZC- KJXX-25"]}],"id":[{"id":"10.13039\/501100017592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302369"],"award-info":[{"award-number":["62302369"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373293"],"award-info":[{"award-number":["62373293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62463020"],"award-info":[{"award-number":["62463020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2570205"],"award-info":[{"award-number":["U2570205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Jiangxi Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["20242B AB20050"],"award-info":[{"award-number":["20242B AB20050"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113531","type":"journal-article","created":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T07:32:31Z","timestamp":1774078351000},"page":"113531","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Learning coherent matrixized representation in latent space for volumetric 4D generation"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2643-2368","authenticated-orcid":false,"given":"Qitong","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0384-3743","authenticated-orcid":false,"given":"Mingtao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0675-6525","authenticated-orcid":false,"given":"Zijie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4043-8448","authenticated-orcid":false,"given":"Shijie","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0631-918X","authenticated-orcid":false,"given":"Weisheng","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7984-0448","authenticated-orcid":false,"given":"Yaonan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9534-7629","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113531_bib0001","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.patcog.2026.113531_bib0002","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7341","article-title":"Video interpolation with diffusion models","author":"Jain","year":"2024"},{"key":"10.1016\/j.patcog.2026.113531_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112008","article-title":"LiteNeRFAvatar: a lightweight NeRF with local feature learning for dynamic human avatar","volume":"170","author":"Pan","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111774","article-title":"MMoFusion: multi-modal co-speech motion generation with diffusion model","volume":"169","author":"Wang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111994","article-title":"FacialTalk: audio-driven high-fidelity facial portrait generation using 3D facial prior","volume":"171","author":"Yang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0006","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.patcog.2017.12.004","article-title":"Tensor-based linear dynamical systems for action recognition from 3D skeletons","volume":"77","author":"Ding","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109444","article-title":"Segmentation of 3D point cloud data representing full human body geometry: a review","volume":"139","author":"Krawczyk","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0008","series-title":"Seminal Graphics Papers: Pushing the Boundaries","first-page":"851","article-title":"SMPL: a skinned multi-person linear model","volume":"Vol. 2","author":"Loper","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0009","series-title":"International Conference on Learning Representations","article-title":"Consistent4D: consistent 360 {\\deg} dynamic object generation from monocular video","author":"Jiang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111426","article-title":"3D Points splatting for real-time dynamic hand reconstruction","volume":"162","author":"Jiang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4456","article-title":"SDFusion: multimodal 3D shape completion, reconstruction, and generation","author":"Cheng","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112069","article-title":"3D portrait stylization with adaptive semantic editing based on GAN latent codes","volume":"171","author":"Song","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0013","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8929","article-title":"Sketch and text guided diffusion model for colored point cloud generation","author":"Wu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision","article-title":"InfiniCity: infinite-scale city synthesis","author":"Lin","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6012","article-title":"Sketch2Model: view-aware 3D modeling from single free-hand sketches","author":"Zhang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113531_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112071","article-title":"High-fidelity 3D reconstruction via unified NeRF-mesh optimization with geometric and color consistency","volume":"170","author":"Neupane","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0017","unstructured":"J. Ren, L. Pan, J. Tang, C. Zhang, A. Cao, G. Zeng, Z. Liu, DreamGaussian4D: generative 4d Gaussian splatting, arXiv: 2312.17142(2023)."},{"key":"10.1016\/j.patcog.2026.113531_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20310","article-title":"4D Gaussian splatting for real-time dynamic scene rendering","author":"Wu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113531_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110729","article-title":"CTNeRF: cross-time transformer for dynamic neural radiance field from monocular video","volume":"156","author":"Miao","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110758","article-title":"Efficient neural implicit representation for 3D human reconstruction","volume":"156","author":"Huang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113531_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12375","article-title":"SUDS: scalable urban dynamic scenes","author":"Turki","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0022","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5975","article-title":"ParticleNeRF: a particle-based encoding for online neural radiance fields","author":"Abou-Chakra","year":"2024"},{"issue":"6","key":"10.1016\/j.patcog.2026.113531_bib0023","first-page":"1","article-title":"Robust dual gaussian splatting for immersive human-centric volumetric videos","volume":"43","author":"Jiang","year":"2024","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10.1016\/j.patcog.2026.113531_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"130","article-title":"HexPlane: a fast representation for dynamic scenes","author":"Cao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12479","article-title":"K-planes: explicit radiance fields in space, time, and appearance","author":"Fridovich-Keil","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7996","article-title":"4D-fy: text-to-4D generation using hybrid score distillation sampling","author":"Bahmani","year":"2024"},{"key":"10.1016\/j.patcog.2026.113531_bib0027","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"3","key":"10.1016\/j.patcog.2026.113531_bib0028","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1109\/TVCG.2020.3016645","article-title":"Surface remeshing: a systematic literature review of methods and research directions","volume":"28","author":"Khan","year":"2020","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"10.1016\/j.patcog.2026.113531_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6624","article-title":"CaDeX: learning canonical deformation coordinate space for dynamic surface representation via neural homeomorphism","author":"Lei","year":"2022"},{"key":"10.1016\/j.patcog.2026.113531_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"165","article-title":"DeepSDF: learning continuous signed distance functions for shape representation","author":"Park","year":"2019"},{"key":"10.1016\/j.patcog.2026.113531_bib0031","unstructured":"A.X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su, et al., ShapeNet: an information-rich 3D model repository, arXiv: 1512.03012(2015)."},{"key":"10.1016\/j.patcog.2026.113531_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12825","article-title":"RaBit: parametric modeling of 3D biped cartoon characters with a topological-consistent dataset","author":"Luo","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0033","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12706","article-title":"4DComplete: non-rigid motion estimation beyond the observable surface","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2026.113531_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13142","article-title":"Objaverse: a universe of annotated 3D objects","author":"Deitke","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"14300","article-title":"HyperDiffusion: generating implicit neural fields with weight-space diffusion","author":"Erko\u00e7","year":"2023"},{"key":"10.1016\/j.patcog.2026.113531_bib0036","series-title":"European Conference on Computer Vision","first-page":"163","article-title":"STAG4D: spatial-temporal anchored generative 4D Gaussians","author":"Zeng","year":"2024"},{"key":"10.1016\/j.patcog.2026.113531_bib0037","first-page":"56828","article-title":"L4GM: Large 4D Gaussian reconstruction model","volume":"37","author":"Ren","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113531_bib0038","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"22067","article-title":"Robust multi-object 4D generation for in-the-wild videos","author":"Chu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113531_bib0039","first-page":"15272","article-title":"4Diffusion: multi-view video diffusion model for 4d generation","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004978?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004978?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:01:48Z","timestamp":1780491708000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":39,"alternative-id":["S0031320326004978"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113531","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Learning coherent matrixized representation in latent space for volumetric 4D generation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113531","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113531"}}