{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:13:25Z","timestamp":1778249605501,"version":"3.51.4"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133690","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T15:24:47Z","timestamp":1776525887000},"page":"133690","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["GeoDiffuser: A geometry-aware extension of pretrained diffusion models for consistent multi-view synthesis"],"prefix":"10.1016","volume":"686","author":[{"given":"Jiahao","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7672-7378","authenticated-orcid":false,"given":"Mingxuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuolei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongbin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133690_bib0005","series-title":"Computer Vision \u2013 ECCV 2020, Lecture Notes in Computer Science","first-page":"405","article-title":"NeRF: representing scenes as neural radiance fields for view synthesis","volume":"vol. 12346","author":"Mildenhall","year":"2020"},{"key":"10.1016\/j.neucom.2026.133690_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16123","article-title":"Efficient geometry-aware 3D generative adversarial networks","author":"Chan","year":"2022"},{"key":"10.1016\/j.neucom.2026.133690_bib0015","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2304","article-title":"PIFu: Pixel-Aligned implicit function for High-Resolution clothed human digitization","author":"Saito","year":"2019"},{"key":"10.1016\/j.neucom.2026.133690_bib0020","author":"Shi"},{"key":"10.1016\/j.neucom.2026.133690_bib0025","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4140","article-title":"3Dfuse: Depth-Conditioned stable diffusion for 3D-aware image synthesis","author":"Richardson","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0030","series-title":"Proceedings of the International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research","first-page":"30099","article-title":"Photorealistic Text-to-Image diffusion models with deep language understanding","volume":"vol. 202","author":"Saharia","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15904","article-title":"ViewDiff: 3D-consistent image generation with Text-to-Image models","author":"H\u00f6llein","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0040","series-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","article-title":"DreamFusion: text-to-3D using 2d diffusion","author":"Poole","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0045","series-title":"The Twelfth International Conference on Learning Representations (ICLR)","article-title":"DreamGaussian: generative Gaussian splatting for efficient 3D content creation","author":"Tang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0050","series-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","article-title":"SyncDreamer: generating Multiview-Consistent images from a Single-View image","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0055","series-title":"Advances in Neural Information Processing Systems 37 (NeurIPS 2024)","article-title":"Normal-GS: 3D Gaussian splatting with Normal-Involved rendering","author":"Wei","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9784","article-title":"EpiDiff: enhancing Multi-View synthesis via localized Epipolar-Constrained diffusion","author":"Huang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0065","series-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","article-title":"MVDream: multi-view diffusion for 3D generation","author":"Shi","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0070","series-title":"European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science","first-page":"236","article-title":"MVDD: Multi-View depth diffusion models","volume":"vol. 15239","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0075","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021"},{"key":"10.1016\/j.neucom.2026.133690_bib0080","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.133690_bib0085","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10684","article-title":"High-Resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neucom.2026.133690_bib0090","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"777","article-title":"NVComposer: boosting generative novel view synthesis with multiple sparse and unposed images","author":"Lingen","year":"2025"},{"key":"10.1016\/j.neucom.2026.133690_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9503","article-title":"EscherNet: a generative model for scalable view synthesis","author":"Kong","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0100","series-title":"European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science","first-page":"767","article-title":"MVSNet: depth inference for unstructured multi-view stereo","volume":"vol. 11214","author":"Yao","year":"2018"},{"key":"10.1016\/j.neucom.2026.133690_bib0105","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"14194","article-title":"PatchMatchNet: learned multi-view PatchMatch stereo","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133690_bib0110","series-title":"ACM SIGGRAPH 2023 Conference Proceedings, ACM","first-page":"1","article-title":"Nerfstudio: a modular framework for neural radiance field development","author":"Tancik","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0115","series-title":"European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science","first-page":"198","article-title":"ViewFormer: NeRF-free neural rendering from few images using transformers","volume":"vol. 13674","author":"Kulh\u00e1nek","year":"2022"},{"key":"10.1016\/j.neucom.2026.133690_bib0120","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1745","article-title":"Sketch-guided latent diffusion for localized image editing","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0125","series-title":"European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science","first-page":"431","article-title":"Paint by example: Exemplar-Based image editing with diffusion models","volume":"vol. 13690","author":"Yang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133690_bib0130","series-title":"Conference on Robot Learning (CoRL), Proceedings of Machine Learning Research","first-page":"1234","article-title":"Pose-Guided person image generation with diffusion models","volume":"vol. 229","author":"Yixuan","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0135","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","first-page":"4296","article-title":"Adding conditional control to Text-to-Image diffusion models","volume":"vol. 38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0140","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","first-page":"4305","article-title":"T2i-adapter: learning adapters to dig out more controllable ability for Text-to-Image diffusion models","volume":"vol. 38","author":"Mou","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0145","first-page":"50648","article-title":"SyncDiffusion: coherent montage via synchronized joint diffusions","volume":"36","author":"Lee","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst. (neurips)"},{"key":"10.1016\/j.neucom.2026.133690_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"300","article-title":"Magic3D: High-Resolution text-to-3D content creation","author":"Lin","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0155","first-page":"8406","article-title":"ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation","volume":"36","author":"Wang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst. (neurips)"},{"key":"10.1016\/j.neucom.2026.133690_bib0160","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16578","article-title":"GaussianDreamer: fast generation from text to 3D gaussians by bridging 2d and 3D diffusion models","author":"Taoran","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0165","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1659","article-title":"Omniobject3D: large-vocabulary 3D object dataset for realistic perception, reconstruction and generation","author":"Tong","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0170","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2581","article-title":"Common objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction","author":"Reizenstein","year":"2021"},{"issue":"2","key":"10.1016\/j.neucom.2026.133690_bib0175","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s11263-016-0902-9","article-title":"Large-Scale data for Multiple-View stereopsis","volume":"120","author":"Aan\u00e6 s","year":"2016","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.133690_bib0180","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4104","article-title":"Structure-from-Motion revisited","author":"Sch\u00f6nberger","year":"2016"},{"key":"10.1016\/j.neucom.2026.133690_bib0185","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"501","article-title":"Pixelwise view selection for unstructured Multi-View stereo","volume":"vol. 9906","author":"Sch\u00f6nberger","year":"2016"},{"key":"10.1016\/j.neucom.2026.133690_bib0190","article-title":"MiDaS v3.1 \u2013 a model zoo for robust monocular relative depth estimation","volume":"145","author":"Birkl","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133690_bib0195","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5745","article-title":"On the continuity of rotation representations in neural networks","author":"Zhou","year":"2019"},{"key":"10.1016\/j.neucom.2026.133690_bib0200","series-title":"ACM SIGGRAPH 2023 Conference Proceedings (SIGGRAPH), ACM","first-page":"1","article-title":"3D Gaussian splatting for Real-Time radiance field rendering","author":"Kerbl","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5089","article-title":"MVEdit: a unified multi-view editing framework for 3D-aware diffusion","author":"Chen","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0210","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"439","article-title":"Sv3D: novel multi-view synthesis and 3D generation from a single image using latent video diffusion","volume":"vol. 15061","author":"Voleti","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0215","first-page":"6626","article-title":"GANs trained by a two Time-Scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133690_bib0220","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.133690_bib0225","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"22490","article-title":"LayoutDiffusion: controllable diffusion model for Layout-to-Image generation","author":"Zheng","year":"2023"},{"issue":"6","key":"10.1016\/j.neucom.2026.133690_bib0230","first-page":"6126","article-title":"SphereDiffusion: spherical Geometry-Aware distortion resilient diffusion model","volume":"38","author":"Tao","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133690_bib0235","series-title":"Proceedings of the Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","article-title":"SphereDrag: spherical Geometry-Aware panoramic image editing","author":"Feng","year":"2025"},{"key":"10.1016\/j.neucom.2026.133690_bib0240","series-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","first-page":"1104","article-title":"Sgat4pass: spherical Geometry-Aware transformer for panoramic semantic segmentation","author":"Xuwei","year":"2023"},{"key":"10.1016\/j.neucom.2026.133690_bib0245","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9970","article-title":"Wonder3D: single image to 3D using Cross-Domain diffusion","author":"Long","year":"2024"},{"key":"10.1016\/j.neucom.2026.133690_bib0250","series-title":"International Conference on Learning Representations (ICLR)","article-title":"LoRA: low-rank Adaptation of Large Language Models","author":"Edward","year":"2022"},{"key":"10.1016\/j.neucom.2026.133690_bib0255","series-title":"Proceedings of the International Conference on Machine Learning (ICML)","first-page":"2790","article-title":"Parameter-Efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.neucom.2026.133690_bib0260","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"20697","article-title":"Dust3r: geometric 3D vision made easy","author":"Wang","year":"2024"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010878?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010878?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T13:30:26Z","timestamp":1778247026000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226010878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":52,"alternative-id":["S0925231226010878"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133690","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GeoDiffuser: A geometry-aware extension of pretrained diffusion models for consistent multi-view synthesis","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133690","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":"133690"}}