{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:05:50Z","timestamp":1784307950256,"version":"3.55.0"},"reference-count":123,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Graphics"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cag.2026.104636","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T23:59:55Z","timestamp":1780012795000},"page":"104636","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["GroundUpV2: Sketch-based 3D modeling of multi-building scenes from prototyping to vertex-efficient representations"],"prefix":"10.1016","volume":"138","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8599-7051","authenticated-orcid":false,"given":"Gizem Esra","family":"\u00dcnl\u00fc","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Sayed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulia","family":"Gryaditskaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Brostow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cag.2026.104636_b1","series-title":"CVPR tutorial on human-centered AI for computer vision","author":"Zhou","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b2","series-title":"Drawing architecture and the urban","isbn-type":"print","author":"Jacoby","year":"2016","ISBN":"https:\/\/id.crossref.org\/isbn\/9781118879498"},{"key":"10.1016\/j.cag.2026.104636_b3","doi-asserted-by":"crossref","unstructured":"Pitts G, Luther M. A parametric approach to 3D massing and density modelling. In: Digital physicality: proceedings of the 30th eCAADe conference. 2012, p. 157\u201365.","DOI":"10.52842\/conf.ecaade.2012.1.157"},{"key":"10.1016\/j.cag.2026.104636_b4","isbn-type":"print","first-page":"p366","volume":"vol. 2145","author":"Leyton","year":"2001","ISBN":"https:\/\/id.crossref.org\/isbn\/9783540427179"},{"key":"10.1016\/j.cag.2026.104636_b5","series-title":"Computer vision - ECCV 2024 - 18th European conference, milan, Italy, September 29-October 4, 2024, proceedings, part LXXI","first-page":"215","article-title":"Groundup: Rapid sketch-based 3D city massing","volume":"vol. 15129","author":"\u00dcnl\u00fc","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b6","doi-asserted-by":"crossref","unstructured":"Duzceker A, Galliani S, Vogel C, Speciale P, Dusmanu M, Pollefeys M. DeepVideoMVS: Multi-view stereo on video with recurrent spatio-temporal fusion. In: CVPR. 2021.","DOI":"10.1109\/CVPR46437.2021.01507"},{"key":"10.1016\/j.cag.2026.104636_b7","series-title":"2021 international conference on 3D vision","first-page":"218","article-title":"Raft-stereo: Multilevel recurrent field transforms for stereo matching","author":"Lipson","year":"2021"},{"key":"10.1016\/j.cag.2026.104636_b8","series-title":"Computer vision - ECCV 2022 - 17th European conference, tel aviv, Israel, October 23-27, 2022, proceedings, part XXXIII","first-page":"1","article-title":"SimpleRecon: 3D reconstruction without 3D convolutions","volume":"vol. 13693","author":"Sayed","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b9","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19615","article-title":"Meshgpt: Generating triangle meshes with decoder-only transformers","author":"Siddiqui","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b10","series-title":"MeshAnything V2: artist-created mesh generation with adjacent mesh tokenization","author":"Chen","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b11","series-title":"The thirteenth international conference on learning representations","article-title":"MeshAnything: Artist-created mesh generation with autoregressive transformers","author":"Chen","year":"2025"},{"issue":"1","key":"10.1016\/j.cag.2026.104636_b12","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/0004-3702(71)90005-1","article-title":"On seeing things","volume":"2","author":"Clowes","year":"1971","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.cag.2026.104636_b13","first-page":"295","article-title":"Impossible objects as nonsense sentences","volume":"6","author":"Huffman","year":"1971","journal-title":"Mach Intell"},{"key":"10.1016\/j.cag.2026.104636_b14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0890060419000349","article-title":"Sketch-based interaction and modeling: where do we stand?","volume":"33","author":"Bonnici","year":"2019","journal-title":"Artif Intell Eng Des Anal Manuf"},{"key":"10.1016\/j.cag.2026.104636_b15","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1111\/cgf.14024","article-title":"A survey on sketch based content creation: from the desktop to virtual and augmented reality","volume":"39","author":"Bhattacharjee","year":"2020","journal-title":"Comput Graph Forum"},{"key":"10.1016\/j.cag.2026.104636_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.cad.2022.103283","article-title":"Sketch-based modeling in mechanical engineering design: Current status and opportunities","volume":"150","author":"Camba","year":"2022","journal-title":"Computer-Aided Des"},{"issue":"7","key":"10.1016\/j.cag.2026.104636_b17","doi-asserted-by":"crossref","DOI":"10.1631\/FITEE.2000141","article-title":"A review of computer graphics approaches to urban modeling from a machine learning perspective","volume":"22","author":"Feng","year":"2021","journal-title":"Front Inf Technol Electron Eng"},{"key":"10.1016\/j.cag.2026.104636_b18","doi-asserted-by":"crossref","unstructured":"Benes B, Zhou X, Chang P, Cani M-PR. Urban brush: Intuitive and controllable urban layout editing. In: The 34th annual ACM symposium on user interface software and technology. 2021.","DOI":"10.1145\/3472749.3474787"},{"key":"10.1016\/j.cag.2026.104636_b19","doi-asserted-by":"crossref","unstructured":"He L, Aliaga D. GlobalMapper: Arbitrary-Shaped Urban Layout Generation. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2023, p. 454\u201364.","DOI":"10.1109\/ICCV51070.2023.00048"},{"key":"10.1016\/j.cag.2026.104636_b20","series-title":"CityGen: Infinite and controllable 3D city layout generation","author":"Deng","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b21","series-title":"European conference on computer vision","article-title":"Coho: Context-sensitive city-scale hierarchical urban layout generation","author":"He","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b22","series-title":"Controllable generation of large-scale 3D urban layouts with semantic and structural guidance","author":"Niu","year":"2025"},{"issue":"6","key":"10.1016\/j.cag.2026.104636_b23","doi-asserted-by":"crossref","DOI":"10.1145\/3130800.3130823","article-title":"BigSUR: Large-scale structured urban reconstruction","volume":"36","author":"Kelly","year":"2017","journal-title":"ACM Trans Graph"},{"issue":"6","key":"10.1016\/j.cag.2026.104636_b24","doi-asserted-by":"crossref","first-page":"1:1","DOI":"10.1145\/3272127.3275065","article-title":"FrankenGAN: Guided detail synthesis for building mass models using style-synchonized GANs","volume":"37","author":"Kelly","year":"2018","journal-title":"ACM Trans Graph"},{"key":"10.1016\/j.cag.2026.104636_b25","doi-asserted-by":"crossref","DOI":"10.1007\/s00371-019-01701-x","article-title":"CityCraft: 3D virtual city creation from a single image","volume":"36","author":"Kim","year":"2020","journal-title":"Vis Comput"},{"key":"10.1016\/j.cag.2026.104636_b26","series-title":"Citydreamer: Compositional generative model of unbounded 3d cities","author":"Xie","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b27","doi-asserted-by":"crossref","unstructured":"Lin CH, Lee H-Y, Menapace W, Chai M, Siarohin A, Yang M-H, Tulyakov S. InfiniCity: Infinite-Scale City Synthesis. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2023.","DOI":"10.1109\/ICCV51070.2023.02085"},{"key":"10.1016\/j.cag.2026.104636_b28","series-title":"Cityx: Controllable procedural content generation for unbounded 3d cities","author":"Zhang","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b29","series-title":"Citycraft: A real crafter for 3d city generation","author":"Deng","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b30","series-title":"Urbanworld: An urban world model for 3d city generation","author":"Shang","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b31","series-title":"ICASSP 2025-2025 IEEE international conference on acoustics, speech and signal processing","article-title":"Text-guided editable 3D city scene generation","author":"Feng","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b32","series-title":"IEEE conference on computer vision and pattern recognition workshops, CVPR workshops 2021, virtual, June 19-25, 2021","first-page":"1072","article-title":"Machine-learned 3D building vectorization from satellite imagery","author":"Wang","year":"2021"},{"key":"10.1016\/j.cag.2026.104636_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.isprsjprs.2021.11.009","article-title":"ResDepth: A deep residual prior for 3D reconstruction from high-resolution satellite images","volume":"183","author":"Stucker","year":"2022","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"10.1016\/j.cag.2026.104636_b34","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.isprsjprs.2022.08.027","article-title":"Point2Roof: End-to-end 3D building roof modeling from airborne lidar point clouds","volume":"193","author":"Li","year":"2022","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"2","key":"10.1016\/j.cag.2026.104636_b35","doi-asserted-by":"crossref","DOI":"10.1080\/01431161.2023.2169844","article-title":"A review of 3D reconstruction from high-resolution urban satellite images","volume":"44","author":"Zhao","year":"2023","journal-title":"Int J Remote Sens"},{"issue":"5","key":"10.1016\/j.cag.2026.104636_b36","doi-asserted-by":"crossref","DOI":"10.1109\/LGRS.2018.2806945","article-title":"IMG2DSM: Height simulation from single imagery using conditional generative adversarial net","volume":"15","author":"Ghamisi","year":"2018","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"10.1016\/j.cag.2026.104636_b37","series-title":"IM2HEIGHT: Height estimation from single monocular imagery via fully residual convolutional-deconvolutional network","author":"Mou","year":"2018"},{"key":"10.1016\/j.cag.2026.104636_b38","doi-asserted-by":"crossref","unstructured":"Mahmud J, Price T, Bapat A, Frahm J-M. Boundary-aware 3D building reconstruction from a single overhead image. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020.","DOI":"10.1109\/CVPR42600.2020.00052"},{"key":"10.1016\/j.cag.2026.104636_b39","series-title":"HeightFormer: A multilevel interaction and image-adaptive classification-regression network for monocular height estimation with aerial images","author":"Chen","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b40","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3321255","article-title":"HTC-DC net: Monocular height estimation from single remote sensing images","volume":"61","author":"Chen","year":"2023","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"10.1016\/j.cag.2026.104636_b41","series-title":"Aerial height prediction and refinement neural networks with semantic and geometric guidance","author":"Mahdi","year":"2020"},{"key":"10.1016\/j.cag.2026.104636_b42","article-title":"Geometry-aware segmentation of remote sensing images via joint height estimation","volume":"19","author":"Li","year":"2021","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"10.1016\/j.cag.2026.104636_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.isprsjprs.2022.11.006","article-title":"Large-scale individual building extraction from open-source satellite imagery via super-resolution-based instance segmentation approach","volume":"195","author":"Chen","year":"2023","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"1","key":"10.1016\/j.cag.2026.104636_b44","doi-asserted-by":"crossref","DOI":"10.1145\/3203197","article-title":"3D sketching using multi-view deep volumetric prediction","volume":"1","author":"Delanoy","year":"2018","journal-title":"Proc ACM Comput Graph Interact Tech"},{"key":"10.1016\/j.cag.2026.104636_b45","series-title":"International conference on 3D vision","article-title":"Deep sketch-based modeling: Tips and tricks","author":"Zhong","year":"2020"},{"key":"10.1016\/j.cag.2026.104636_b46","series-title":"ECCV workshops","article-title":"3D shape reconstruction from free-hand sketches","author":"Wang","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2022.06.005","article-title":"A study of deep single sketch-based modeling: View\/style invariance, sparsity and latent space disentanglement","author":"Zhong","year":"2022","journal-title":"Comput Graph"},{"key":"10.1016\/j.cag.2026.104636_b48","doi-asserted-by":"crossref","unstructured":"Guillard B, Remelli E, Yvernay P, Fua P. Sketch2mesh: Reconstructing and editing 3d shapes from sketches. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021.","DOI":"10.1109\/ICCV48922.2021.01278"},{"key":"10.1016\/j.cag.2026.104636_b49","doi-asserted-by":"crossref","unstructured":"Chowdhury PN, Wang T, Ceylan D, Song Y-Z, Gryaditskaya Y. Garment Ideation: Iterative View-Aware Sketch-Based Garment Modeling. In: 2022 international conference on 3D vision (3DV). 2022, p. 22\u201331.","DOI":"10.1109\/3DV57658.2022.00015"},{"issue":"4","key":"10.1016\/j.cag.2026.104636_b50","doi-asserted-by":"crossref","DOI":"10.1145\/3592103","article-title":"Locally attentional SDF diffusion for controllable 3D shape generation","volume":"42","author":"Zheng","year":"2023","journal-title":"ACM Trans Graph"},{"key":"10.1016\/j.cag.2026.104636_b51","article-title":"SENS: Part-aware sketch-based implicit neural shape modeling","volume":"vol. 43","author":"Binninger","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b52","series-title":"PASTA: Part-aware sketch-to-3D shape generation with text-aligned prior","author":"Lee","year":"2025"},{"issue":"1","key":"10.1016\/j.cag.2026.104636_b53","doi-asserted-by":"crossref","DOI":"10.1145\/3203186","article-title":"Interactive sketch-based normal map generation with deep neural networks","volume":"1","author":"Su","year":"2018","journal-title":"Proc ACM Comput Graph Interact Tech"},{"key":"10.1016\/j.cag.2026.104636_b54","series-title":"ECCV","article-title":"Learning shape priors for single-view 3D completion and reconstruction","author":"Wu","year":"2018"},{"key":"10.1016\/j.cag.2026.104636_b55","series-title":"ECCV","article-title":"SketchSampler: Sketch-based 3D reconstruction via view-dependent depth sampling","author":"Gao","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b56","series-title":"Medical image computing and computer-assisted intervention\u2013mICCAI 2015: 18th international conference, munich, Germany, October 5-9, 2015, proceedings, part III 18","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.cag.2026.104636_b57","doi-asserted-by":"crossref","unstructured":"Lun Z, Gadelha M, Kalogerakis E, Maji S, Wang R. 3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks. In: International conference on 3D vision. 2017.","DOI":"10.1109\/3DV.2017.00018"},{"key":"10.1016\/j.cag.2026.104636_b58","article-title":"Towards practical sketch-based 3d shape generation: The role of professional sketches","author":"Zhong","year":"2020","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"6","key":"10.1016\/j.cag.2026.104636_b59","doi-asserted-by":"crossref","DOI":"10.1145\/3272127.3275051","article-title":"Robust flow-guided neural prediction for sketch-based freeform surface modeling","volume":"37","author":"Li","year":"2018","journal-title":"ACM Trans Graph"},{"issue":"6","key":"10.1016\/j.cag.2026.104636_b60","doi-asserted-by":"crossref","DOI":"10.1145\/3618361","article-title":"Reconstruction of machine-made shapes from bitmap sketches","volume":"42","author":"Puhachov","year":"2023","journal-title":"ACM Trans Graph"},{"key":"10.1016\/j.cag.2026.104636_b61","doi-asserted-by":"crossref","unstructured":"Zhang S-H, Guo Y-C, Gu Q-W. Sketch2model: View-aware 3d modeling from single free-hand sketches. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2021, p. 6012\u201321.","DOI":"10.1109\/CVPR46437.2021.00595"},{"key":"10.1016\/j.cag.2026.104636_b62","series-title":"Cross-modal 3D shape generation and manipulation","isbn-type":"print","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/978-3-031-20062-5_18","author":"Cheng","year":"2022","ISBN":"https:\/\/id.crossref.org\/isbn\/9783031200618"},{"key":"10.1016\/j.cag.2026.104636_b63","doi-asserted-by":"crossref","unstructured":"Yao Y, Schertler N, Rosales E, Rhodin H, Sigal L, Sheffer A. Front2back: Single view 3d shape reconstruction via front to back prediction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020.","DOI":"10.1109\/CVPR42600.2020.00061"},{"key":"10.1016\/j.cag.2026.104636_b64","doi-asserted-by":"crossref","unstructured":"H\u00e4hnlein F, Gryaditskaya Y, Sheffer A, Bousseau A. Symmetry-driven 3D Reconstruction from Concept Sketches. In: ACM SIGGRAPH 2022 conference proceedings. 2022, p. 1\u20138.","DOI":"10.1145\/3528233.3530723"},{"issue":"4","key":"10.1016\/j.cag.2026.104636_b65","doi-asserted-by":"crossref","DOI":"10.1145\/2897824.2925951","article-title":"Interactive sketching of urban procedural models","volume":"35","author":"Nishida","year":"2016","journal-title":"ACM Trans Graph"},{"key":"10.1016\/j.cag.2026.104636_b66","series-title":"Geocode: Interpretable shape programs","author":"Pearl","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b67","article-title":"Free2CAD: Parsing freehand drawings into CAD commands","author":"Li","year":"2022","journal-title":"ACM TOG"},{"key":"10.1016\/j.cag.2026.104636_b68","series-title":"Deep learning assisted optimization for 3D reconstruction from single 2D line drawings","author":"Zheng","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b69","series-title":"IEEE international symposium on mixed and augmented reality","article-title":"Buildingsketch: Freehand mid-air sketching for building modeling","author":"Liu","year":"2021"},{"key":"10.1016\/j.cag.2026.104636_b70","series-title":"Vitruvio: 3d building meshes via single perspective sketches","author":"Tono","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b71","series-title":"IEEE conference on computer vision and pattern recognition, CVPR 2019, long beach, CA, USA, June 16-20, 2019","first-page":"4460","article-title":"Occupancy networks: Learning 3D reconstruction in function space","author":"Mescheder","year":"2019"},{"key":"10.1016\/j.cag.2026.104636_b72","doi-asserted-by":"crossref","unstructured":"Park JJ, Florence P, Straub J, Newcombe R, Lovegrove S. Deepsdf: Learning continuous signed distance functions for shape representation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"10.1016\/j.cag.2026.104636_b73","doi-asserted-by":"crossref","unstructured":"Luo L, Chowdhury PN, Xiang T, Song Y-Z, Gryaditskaya Y. 3D VR Sketch Guided 3D Shape Prototyping and Exploration. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2023.","DOI":"10.1109\/ICCV51070.2023.00850"},{"key":"10.1016\/j.cag.2026.104636_b74","series-title":"3D-ldm: Neural implicit 3d shape generation with latent diffusion models","author":"Nam","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b75","series-title":"CVPR","article-title":"A space-sweep approach to true multi-image matching","author":"Collins","year":"1996"},{"key":"10.1016\/j.cag.2026.104636_b76","article-title":"Stereo matching by training a convolutional neural network to compare image patches","author":"\u017dbontar","year":"2016","journal-title":"JMLR"},{"key":"10.1016\/j.cag.2026.104636_b77","series-title":"CVPR","article-title":"Handling occlusions in dense multi-view stereo","author":"Kang","year":"2001"},{"key":"10.1016\/j.cag.2026.104636_b78","series-title":"CVPR","article-title":"Multi-view stereo revisited","author":"Goesele","year":"2006"},{"issue":"1\u20132","key":"10.1016\/j.cag.2026.104636_b79","first-page":"1","article-title":"Multi-view stereo: A tutorial","volume":"9","author":"Furukawa","year":"2015","journal-title":"Found Trends\u00ae Comput Graph Vis"},{"key":"10.1016\/j.cag.2026.104636_b80","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, amsterdam, the netherlands, October 11-14, 2016, proceedings, part III 14","first-page":"501","article-title":"Pixelwise view selection for unstructured multi-view stereo","author":"Sch\u00f6nberger","year":"2016"},{"key":"10.1016\/j.cag.2026.104636_b81","series-title":"Advances in neural information processing systems 27: annual conference on neural information processing systems 2014","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014"},{"issue":"9","key":"10.1016\/j.cag.2026.104636_b82","doi-asserted-by":"crossref","DOI":"10.1007\/s11431-020-1582-8","article-title":"Monocular depth estimation based on deep learning: An overview","volume":"63","author":"Zhao","year":"2020","journal-title":"Sci China Technol Sci"},{"key":"10.1016\/j.cag.2026.104636_b83","series-title":"CVPR","article-title":"Unsupervised monocular depth estimation with left-right consistency","author":"Godard","year":"2017"},{"key":"10.1016\/j.cag.2026.104636_b84","doi-asserted-by":"crossref","unstructured":"Yin W, Zhang J, Wang O, Niklaus S, Mai L, Chen S, Shen C. Learning to recover 3d scene shape from a single image. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2021, p. 204\u201313.","DOI":"10.1109\/CVPR46437.2021.00027"},{"issue":"3","key":"10.1016\/j.cag.2026.104636_b85","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.2026.104636_b86","doi-asserted-by":"crossref","unstructured":"Fu H, Gong M, Wang C, Batmanghelich K, Tao D. Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.","DOI":"10.1109\/CVPR.2018.00214"},{"key":"10.1016\/j.cag.2026.104636_b87","series-title":"Repurposing diffusion-based image generators for monocular depth estimation","author":"Ke","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b88","series-title":"DiffusionDepth: Diffusion denoising approach for monocular depth estimation","author":"Duan","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b89","series-title":"Monocular depth estimation using diffusion models","author":"Saxena","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b90","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5294","article-title":"VGGT: visual geometry grounded transformer","author":"Wang","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b91","series-title":"Depth anything 3: Recovering the visual space from any views","author":"Lin","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b92","series-title":"MapAnything: Universal feed-forward metric 3D reconstruction","author":"Keetha","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b93","series-title":"Meshtron: High-fidelity, artist-like 3D mesh generation at scale","author":"Hao","year":"2024"},{"issue":"5","key":"10.1016\/j.cag.2026.104636_b94","doi-asserted-by":"crossref","first-page":"146:1","DOI":"10.1145\/3326362","article-title":"Dynamic graph CNN for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans Graph"},{"key":"10.1016\/j.cag.2026.104636_b95","series-title":"Generative and discriminative voxel modeling with convolutional neural networks","author":"Brock","year":"2016"},{"key":"10.1016\/j.cag.2026.104636_b96","series-title":"The eleventh international conference on learning representations","article-title":"DreamFusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b97","series-title":"Computer vision - ECCV 2024 - 18th European conference, milan, Italy, September 29-October 4, 2024, proceedings, part IV","first-page":"1","article-title":"LGM: large multi-view Gaussian model for high-resolution 3D content creation","volume":"vol. 15062","author":"Tang","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b98","series-title":"Proceedings of the 14th annual conference on computer graphics and interactive techniques","first-page":"163","article-title":"Marching cubes: A high resolution 3D surface construction algorithm","author":"Lorensen","year":"1987"},{"key":"10.1016\/j.cag.2026.104636_b99","series-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b100","series-title":"Advances in neural information processing systems 38: annual conference on neural information processing systems 2024","article-title":"MeshXL: Neural coordinate field for generative 3D foundation models","author":"Chen","year":"2024"},{"key":"10.1016\/j.cag.2026.104636_b101","series-title":"The thirteenth international conference on learning representations","article-title":"PivotMesh: Generic 3D mesh generation via pivot vertices guidance","author":"Weng","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b102","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26608","article-title":"TreeMeshGPT: Artistic mesh generation with autoregressive tree sequencing","author":"Lionar","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b103","series-title":"The thirteenth international conference on learning representations","article-title":"EdgeRunner: Auto-regressive auto-encoder for artistic mesh generation","author":"Tang","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b104","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11093","article-title":"Scaling mesh generation via compressive tokenization","author":"Weng","year":"2025"},{"key":"10.1016\/j.cag.2026.104636_b105","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-00889-5_1","article-title":"Unet++: A nested u-net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"10.1016\/j.cag.2026.104636_b106","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.cag.2026.104636_b107","series-title":"2009 IEEE conference on computer vision and pattern recognition","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"4","key":"10.1016\/j.cag.2026.104636_b108","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1145\/321356.321357","article-title":"Sequential operations in digital picture processing","volume":"13","author":"Rosenfeld","year":"1966","journal-title":"J ACM"},{"key":"10.1016\/j.cag.2026.104636_b109","series-title":"ECCV","article-title":"MVSNet: Depth inference for unstructured multi-view stereo","author":"Yao","year":"2018"},{"key":"10.1016\/j.cag.2026.104636_b110","series-title":"2017 IEEE conference on computer vision and pattern recognition","first-page":"6602","article-title":"Unsupervised monocular depth estimation with left-right consistency","author":"Godard","year":"2017"},{"key":"10.1016\/j.cag.2026.104636_b111","series-title":"2019 IEEE\/CVF international conference on computer vision","first-page":"3827","article-title":"Digging into self-supervised monocular depth estimation","author":"Godard","year":"2019"},{"key":"10.1016\/j.cag.2026.104636_b112","series-title":"2018 IEEE conference on computer vision and pattern recognition","first-page":"2041","article-title":"MegaDepth: Learning single-view depth prediction from internet photos","author":"Li","year":"2018"},{"key":"10.1016\/j.cag.2026.104636_b113","series-title":"2019 IEEE\/CVF international conference on computer vision","first-page":"5683","article-title":"Enforcing geometric constraints of virtual normal for depth prediction","author":"Yin","year":"2019"},{"key":"10.1016\/j.cag.2026.104636_b114","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10674","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b115","series-title":"Computer vision - ECCV 2022 - 17th European conference, tel aviv, Israel, October 23-27, 2022, proceedings, part VIII","first-page":"93","article-title":"Capturing, reconstructing, and simulating: The UrbanScene3D dataset","volume":"vol. 13668","author":"Lin","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b116","series-title":"Blender - a 3D modelling and rendering package","author":"Blender Online Community","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b117","series-title":"IEEE\/CVF winter conference on applications of computer vision","first-page":"5839","article-title":"Heightfields for efficient scene reconstruction for AR","author":"Watson","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b118","series-title":"International conference on 3D vision","first-page":"700","article-title":"Interactive sketching of mannequin poses","author":"\u00dcnl\u00fc","year":"2022"},{"key":"10.1016\/j.cag.2026.104636_b119","series-title":"Advances in neural information processing systems 36: annual conference on neural information processing systems 2023","article-title":"Michelangelo: Conditional 3D shape generation based on shape-image-text aligned latent representation","author":"Zhao","year":"2023"},{"key":"10.1016\/j.cag.2026.104636_b120","series-title":"Advances in neural information processing systems 32: annual conference on neural information processing systems 2019","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"10.1016\/j.cag.2026.104636_b121","series-title":"International conference on machine learning","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.cag.2026.104636_b122","article-title":"TransformerFusion: Monocular RGB scene reconstruction using transformers","author":"Bozic","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cag.2026.104636_b123","series-title":"Human-centered AI","isbn-type":"print","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780192845290.001.0001","author":"Shneiderman","year":"2022","ISBN":"https:\/\/id.crossref.org\/isbn\/9780192845290"}],"container-title":["Computers & Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S009784932600107X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S009784932600107X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:33:04Z","timestamp":1784305984000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S009784932600107X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":123,"alternative-id":["S009784932600107X"],"URL":"https:\/\/doi.org\/10.1016\/j.cag.2026.104636","relation":{},"ISSN":["0097-8493"],"issn-type":[{"value":"0097-8493","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GroundUpV2: Sketch-based 3D modeling of multi-building scenes from prototyping to vertex-efficient representations","name":"articletitle","label":"Article Title"},{"value":"Computers & Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cag.2026.104636","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"simple-article","name":"content_type","label":"Content Type"},{"name":"copyright","label":"Copyright"}],"article-number":"104636"}}