{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T07:46:30Z","timestamp":1786088790056,"version":"3.56.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52571332"],"award-info":[{"award-number":["52571332"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Graphics"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.cag.2026.104705","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:22:09Z","timestamp":1784820129000},"page":"104705","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Of-GS: Overlap-free Gaussian Splatting via visual geometry grounded transformer for few-shot novel view synthesis"],"prefix":"10.1016","volume":"139","author":[{"given":"Qianjun","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jubo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runsheng","family":"Diao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3218-1486","authenticated-orcid":false,"given":"Xiaosheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cag.2026.104705_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103661","article-title":"Image amodal completion: A survey","volume":"229","author":"Ao","year":"2023","journal-title":"Comput Vis Image Underst"},{"issue":"1","key":"10.1016\/j.cag.2026.104705_b2","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Commun ACM"},{"issue":"4","key":"10.1016\/j.cag.2026.104705_b3","doi-asserted-by":"crossref","DOI":"10.1145\/3592433","article-title":"3D Gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans Graph"},{"key":"10.1016\/j.cag.2026.104705_b4","article-title":"Scene representation networks: Continuous 3d-structure-aware neural scene representations","volume":"32","author":"Sitzmann","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.cag.2026.104705_b5","doi-asserted-by":"crossref","unstructured":"Yu A, Ye V, Tancik M, Kanazawa A. pixelnerf: Neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2021, p. 4578\u201387.","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"10.1016\/j.cag.2026.104705_b6","doi-asserted-by":"crossref","unstructured":"Sajjadi MS, Meyer H, Pot E, Bergmann U, Greff K, Radwan N, Vora S, Lu\u010di\u0107 M, Duckworth D, Dosovitskiy A, et al. Scene representation transformer: Geometry-free novel view synthesis through set-latent scene representations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, p. 6229\u201338.","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"10.1016\/j.cag.2026.104705_b7","doi-asserted-by":"crossref","unstructured":"Lin K-E, Lin Y-C, Lai W-S, Lin T-Y, Shih Y-C, Ramamoorthi R. Vision transformer for nerf-based view synthesis from a single input image. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 2023, p. 806\u201315.","DOI":"10.1109\/WACV56688.2023.00087"},{"key":"10.1016\/j.cag.2026.104705_b8","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.cag.2023.08.009","article-title":"TSNeRF: Text-driven stylized neural radiance fields via semantic contrastive learning","volume":"116","author":"Wang","year":"2023","journal-title":"Comput Graph"},{"key":"10.1016\/j.cag.2026.104705_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.112262","article-title":"Feature radiance fields (FeRF): A multi-level feature fusion method with deep neural network for image synthesis","volume":"167","author":"Chen","year":"2024","journal-title":"Appl Soft Comput"},{"key":"10.1016\/j.cag.2026.104705_b10","doi-asserted-by":"crossref","unstructured":"Charatan D, Li SL, Tagliasacchi A, Sitzmann V. pixelsplat: 3d gaussian splats from image pairs for scalable generalizable 3d reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2024, p. 19457\u201367.","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"10.1016\/j.cag.2026.104705_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103889","article-title":"A spatial-spectral multi-view contrastive learning framework for scene representation learning","volume":"127","author":"Chen","year":"2026","journal-title":"Inf Fusion"},{"key":"10.1016\/j.cag.2026.104705_b12","doi-asserted-by":"crossref","unstructured":"Schonberger JL, Frahm J-M. Structure-from-motion revisited. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, p. 4104\u201313.","DOI":"10.1109\/CVPR.2016.445"},{"key":"10.1016\/j.cag.2026.104705_b13","doi-asserted-by":"crossref","unstructured":"Huang R, Mikolajczyk K. No pose at all: Self-supervised pose-free 3d gaussian splatting from sparse views. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2025, p. 27947\u201357.","DOI":"10.1109\/ICCV51701.2025.02594"},{"key":"10.1016\/j.cag.2026.104705_b14","doi-asserted-by":"crossref","unstructured":"Xu J, Gao S, Shan Y. Freesplatter: Pose-free gaussian splatting for sparse-view 3d reconstruction. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2025, p. 25442\u201352.","DOI":"10.1109\/ICCV51701.2025.02360"},{"issue":"6","key":"10.1016\/j.cag.2026.104705_b15","first-page":"1","article-title":"Anysplat: Feed-forward 3d gaussian splatting from unconstrained views","volume":"44","author":"Jiang","year":"2025","journal-title":"ACM Trans Graph"},{"key":"10.1016\/j.cag.2026.104705_b16","doi-asserted-by":"crossref","unstructured":"Wang J, Chen M, Karaev N, Vedaldi A, Rupprecht C, Novotny D. Vggt: Visual geometry grounded transformer. In: Proceedings of the computer vision and pattern recognition conference. 2025, p. 5294\u2013306.","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"10.1016\/j.cag.2026.104705_b17","series-title":"European conference on computer vision","first-page":"93","article-title":"Capturing, reconstructing, and simulating: the urbanscene3d dataset","author":"Lin","year":"2022"},{"issue":"4","key":"10.1016\/j.cag.2026.104705_b18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3322980","article-title":"Local light field fusion: Practical view synthesis with prescriptive sampling guidelines","volume":"38","author":"Mildenhall","year":"2019","journal-title":"ACM Trans Graph (ToG)"},{"issue":"4","key":"10.1016\/j.cag.2026.104705_b19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073599","article-title":"Tanks and temples: Benchmarking large-scale scene reconstruction","volume":"36","author":"Knapitsch","year":"2017","journal-title":"ACM Trans Graph (ToG)"},{"key":"10.1016\/j.cag.2026.104705_b20","doi-asserted-by":"crossref","unstructured":"Xu Q, Xu Z, Philip J, Bi S, Shu Z, Sunkavalli K, Neumann U. Point-nerf: Point-based neural radiance fields. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, p. 5438\u201348.","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"10.1016\/j.cag.2026.104705_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2025.104171","article-title":"FreqSpace-NeRF: A fourier-enhanced neural radiance fields method via dual-domain contrastive learning for novel view synthesis","volume":"127","author":"Yu","year":"2025","journal-title":"Comput Graph"},{"key":"10.1016\/j.cag.2026.104705_b22","doi-asserted-by":"crossref","unstructured":"Liang Z, Zhang Q, Feng Y, Shan Y, Jia K. Gs-ir: 3d gaussian splatting for inverse rendering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2024, p. 21644\u201353.","DOI":"10.1109\/CVPR52733.2024.02045"},{"key":"10.1016\/j.cag.2026.104705_b23","series-title":"European conference on computer vision","first-page":"37","article-title":"Mvsgaussian: Fast generalizable gaussian splatting reconstruction from multi-view stereo","author":"Liu","year":"2024"},{"key":"10.1016\/j.cag.2026.104705_b24","series-title":"Sparsegs: Real-time 360\u00b0 sparse view synthesis using gaussian splatting","author":"Xiong","year":"2023"},{"key":"10.1016\/j.cag.2026.104705_b25","series-title":"Sfm-net: Learning of structure and motion from video","author":"Vijayanarasimhan","year":"2017"},{"key":"10.1016\/j.cag.2026.104705_b26","doi-asserted-by":"crossref","unstructured":"Yin Z, Shi J. Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 1983\u201392.","DOI":"10.1109\/CVPR.2018.00212"},{"key":"10.1016\/j.cag.2026.104705_b27","series-title":"2018 international conference on 3d vision (3DV)","first-page":"248","article-title":"Mvdepthnet: Real-time multiview depth estimation neural network","author":"Wang","year":"2018"},{"key":"10.1016\/j.cag.2026.104705_b28","doi-asserted-by":"crossref","unstructured":"Wang F, Galliani S, Vogel C, Speciale P, Pollefeys M. Patchmatchnet: Learned multi-view patchmatch stereo. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2021, p. 14194\u2013203.","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"10.1016\/j.cag.2026.104705_b29","series-title":"European conference on computer vision","first-page":"1","article-title":"Lgm: Large multi-view gaussian model for high-resolution 3d content creation","author":"Tang","year":"2024"},{"key":"10.1016\/j.cag.2026.104705_b30","doi-asserted-by":"crossref","unstructured":"Xu X, Ge W, Qiu D, Chen Z, Yan D, Liu Z, Zhao H, Zhao H, Zhang S, Liang J, et al. Gaussianproperty: Integrating physical properties to 3d gaussians with lmms. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2025, p. 7231\u201340.","DOI":"10.1109\/ICCV51701.2025.00679"},{"key":"10.1016\/j.cag.2026.104705_b31","series-title":"Sail-recon: Large sfm by augmenting scene regression with localization","author":"Deng","year":"2025"},{"key":"10.1016\/j.cag.2026.104705_b32","doi-asserted-by":"crossref","unstructured":"Wang S, Leroy V, Cabon Y, Chidlovskii B, Revaud J. Dust3r: Geometric 3d vision made easy. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2024, p. 20697\u2013709.","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"10.1016\/j.cag.2026.104705_b33","series-title":"European conference on computer vision","first-page":"71","article-title":"Grounding image matching in 3d with mast3r","author":"Leroy","year":"2024"},{"key":"10.1016\/j.cag.2026.104705_b34","series-title":"Splatt3r: Zero-shot gaussian splatting from uncalibrated image pairs","author":"Smart","year":"2024"},{"issue":"3","key":"10.1016\/j.cag.2026.104705_b35","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","article-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","volume":"44","author":"Ranftl","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.cag.2026.104705_b36","doi-asserted-by":"crossref","unstructured":"Chung J, Oh J, Lee KM. Depth-regularized optimization for 3d gaussian splatting in few-shot images. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2024, p. 811\u201320.","DOI":"10.1109\/CVPRW63382.2024.00086"},{"key":"10.1016\/j.cag.2026.104705_b37","doi-asserted-by":"crossref","unstructured":"Matsuki H, Murai R, Kelly PH, Davison AJ. Gaussian splatting slam. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2024, p. 18039\u201348.","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"10.1016\/j.cag.2026.104705_b38","series-title":"A comprehensive survey on point cloud registration","author":"Huang","year":"2021"},{"key":"10.1016\/j.cag.2026.104705_b39","series-title":"ICP algorithm: Theory, practice and its SLAM-oriented taxonomy","author":"Bai","year":"2022"},{"key":"10.1016\/j.cag.2026.104705_b40","series-title":"2021 IEEE international conference on robotics and automation","first-page":"5654","article-title":"Ndt-transformer: Large-scale 3d point cloud localisation using the normal distribution transform representation","author":"Zhou","year":"2021"},{"key":"10.1016\/j.cag.2026.104705_b41","doi-asserted-by":"crossref","unstructured":"Sucar E, Liu S, Ortiz J, Davison AJ. imap: Implicit mapping and positioning in real-time. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021, p. 6229\u201338.","DOI":"10.1109\/ICCV48922.2021.00617"},{"key":"10.1016\/j.cag.2026.104705_b42","doi-asserted-by":"crossref","unstructured":"Wang H, Wang J, Agapito L. Co-slam: Joint coordinate and sparse parametric encodings for neural real-time slam. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023, p. 13293\u2013302.","DOI":"10.1109\/CVPR52729.2023.01277"},{"key":"10.1016\/j.cag.2026.104705_b43","series-title":"Gaussian-slam: Photo-realistic dense slam with gaussian splatting","author":"Yugay","year":"2023"},{"issue":"7","key":"10.1016\/j.cag.2026.104705_b44","first-page":"3450","article-title":"Fast and robust iterative closest point","volume":"44","author":"Zhang","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"10.1016\/j.cag.2026.104705_b45","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1109\/72.883408","article-title":"Local PCA algorithms","volume":"11","author":"Weingessel","year":"2000","journal-title":"IEEE Trans Neural Netw"},{"key":"10.1016\/j.cag.2026.104705_b46","series-title":"Lie groups: An introduction through linear groups","author":"Rossmann","year":"2006"},{"key":"10.1016\/j.cag.2026.104705_b47","series-title":"Numerical analysis: Proceedings of the biennial conference held at Dundee, June 28\u2013July 1, 1977","first-page":"105","article-title":"The Levenberg-Marquardt algorithm: implementation and theory","author":"Mor\u00e9","year":"2006"},{"key":"10.1016\/j.cag.2026.104705_b48","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.cag.2026.104705_b49","series-title":"Ceres solver","author":"Agarwal","year":"2023"},{"key":"10.1016\/j.cag.2026.104705_b50","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.cag.2026.104705_b51","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O. The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 586\u201395.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"10.1016\/j.cag.2026.104705_b52","series-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"}],"container-title":["Computers & Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001767?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001767?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T07:08:26Z","timestamp":1786086506000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0097849326001767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":52,"alternative-id":["S0097849326001767"],"URL":"https:\/\/doi.org\/10.1016\/j.cag.2026.104705","relation":{},"ISSN":["0097-8493"],"issn-type":[{"value":"0097-8493","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Of-GS: Overlap-free Gaussian Splatting via visual geometry grounded transformer for few-shot novel view synthesis","name":"articletitle","label":"Article Title"},{"value":"Computers & Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cag.2026.104705","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":"104705"}}