[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82378-en":3,"doc-seo-82378-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82378,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion","Global Structure-from-Motion (SfM) recovers camera poses and sparse 3D structure from unordered images, yet scale-ambiguous epipolar geometry makes global positioning sensitive to noisy baselines and weak view-graph constraints. False edges from visually ambiguous pairs can further harm reconstruction quality. DGSfM introduces a depth-aware global SfM pipeline that uses monocular depth maps as a scalable prior, converting epipolar constraints into scale-aware relative pose constraints and filtering false correspondences via view-graph and depth-consistency pruning. Global scale averaging and depth-guided initialization stabilize bundle adjustment, improving pose accuracy on ETH3D and IMC2021.","arXiv :2607 .09507v1 [ cs .CV] 10 Jul 2026  \nDGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion  \nSithu Aung 1 , Viktor Kocur2 , Yaqing Ding3 , Torsten Sattler4 , and Zuzana Kukelova 1  \n1 VRG, FEE, Czech Technical University in Prague  \n2 FMPH, Comenius University in Bratislava  \n3 Southeast University  \n4 CIIRC, Czech Technical University in Prague  \nAbstract. Global Structure-from-Motion (SfM) is an efficient paradigm for recovering camera poses and sparse 3D structure from unordered images. However, its reliance on scale-ambiguous epipolar geometry makes global positioning sensitive to noisy baseline estimates and weak viewgraph constraints, while false edges from visually ambiguous pairs can further degrade reconstruction. We propose DGSfM, a depth-aware global SfM pipeline that uses monocular depth maps as a scalable prior while preserving explicit multi-view optimization. For each image pair, we use a depth-aware relative pose solver to convert scale-ambiguous epipolar constraints into scale-aware relative pose constraints. We further improve robustness through view-graph filtering and depth-consistencybased correspondence pruning, which suppress false edges and matches that remain plausible under epipolar geometry alone. Finally, global scale averaging and depth-guided pose-point initialization align monocular depth maps into a common reconstruction scale and provide stable initialization for global positioning and bundle adjustment. Experiments on ETH3D and IMC2021 show that DGSfM consistently improves over strong global SfM baselines across sparse and dense matching frontends, achieving substantial gains in pose accuracy. Code is available at [https://github.com/sithu31296/DGSfM](https://github.com/sithu31296/DGSfM).  \nKeywords: Structure-from-Motion · Global SfM · Monocular Depth  \n1 Introduction  \nStructure-from-Motion (SfM) is a core tool for recovering camera poses and sparse 3D structure from images, with applications in 3D reconstruction, localization, visual mapping, and spatial data generation. Among SfM paradigms [1, 33, 49, 61], global SfM [7, 60] is particularly attractive because it estimates camera poses jointly from a view graph, avoiding the sequential registration order and repeated local optimization of incremental pipelines. Recent works such as GLOMAP [35] show that global SfM can be both scalable and accurate when the input view graph is reliable. However, global SfM still largely relies on pairwise epipolar geometry, where relative translations are known only up to scale and  \n2 S. Aung et al.  \nFig. 1: Reconstruction results of DGSfM using RoMa [14] matches on the full image sets from the IMC2021 [20] dataset. DGSfM integrates monocular depth into global SfM to improve scale estimation, view-graph robustness, and pose-point initialization, producing globally consistent camera poses and sparse/semi-dense 3D structure.  \nwhere visually plausible but incorrect image pairs can survive geometric verification. This makes global positioning vulnerable to noisy baseline estimates, ambiguous matches, and inconsistent local geometry, especially in unordered image collections with repeated structures, weak overlap, or limited parallax.  \nRecent learned methods provide powerful geometric cues, but they do not by themselves remove the need for explicit multi-view optimization. Dense matchers [13,14,68] and detector-free SfM methods [18,23,24] improve correspondence coverage and robustness in low-texture or wide-baseline settings, yet the subsequent SfM optimization often remains governed by scale-ambiguous relative poses and track consistency. Feed-forward reconstruction models [21,26,53,55,59] can predict cameras and dense structure directly from images, but their accuracy, scalability, and global consistency may degrade for large unordered collections or scenes outside their training distribution compared to classical feature-based SfM methods [32, 36] . Monocular depth estimators [5, 19, 56, 57,","cbCain5vD721fx5l","https://ap.wps.com/l/cbCain5vD721fx5l","pdf",11469792,1,26,"English","en",105,"# Introduction\n## Depth-Aware Global SfM Motivation\n## Depth-Guided Relative Pose and Constraints\n## Robust View-Graph and Correspondence Filtering\n## Depth-Guided Initialization and Global Optimization","[{\"question\":\"What problem does DGSfM address in global Structure-from-Motion?\",\"answer\":\"Global SfM often relies on scale-ambiguous epipolar geometry, making positioning sensitive to noisy baseline estimates and weak view-graph constraints. Visually ambiguous pairs can also create false edges that degrade reconstruction.\"},{\"question\":\"How does DGSfM use monocular depth within the global SfM pipeline?\",\"answer\":\"DGSfM uses monocular depth maps as a scalable prior and employs a depth-aware relative pose solver per verified image pair to obtain scale-aware relative translation and supporting geometric constraints. It then uses depth to guide filtering and initialization rather than treating monocular depth as final geometry.\"},{\"question\":\"What robustness steps improve reconstruction quality in DGSfM?\",\"answer\":\"DGSfM filters the view graph and correspondences using depth-aware consistency. It prunes edges via triplet-guided edge pruning and removes matches that disagree under reprojection and target-view depth constraints.\"}]",1784180015,66,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"dgsfm-depth-guided-scale-aware-global-structure-from-motion","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/dgsfm-depth-guided-scale-aware-global-structure-from-motion/82378/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does DGSfM address in global Structure-from-Motion?","Question",{"text":75,"@type":76},"Global SfM often relies on scale-ambiguous epipolar geometry, making positioning sensitive to noisy baseline estimates and weak view-graph constraints. Visually ambiguous pairs can also create false edges that degrade reconstruction.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does DGSfM use monocular depth within the global SfM pipeline?",{"text":80,"@type":76},"DGSfM uses monocular depth maps as a scalable prior and employs a depth-aware relative pose solver per verified image pair to obtain scale-aware relative translation and supporting geometric constraints. It then uses depth to guide filtering and initialization rather than treating monocular depth as final geometry.",{"name":82,"@type":73,"acceptedAnswer":83},"What robustness steps improve reconstruction quality in DGSfM?",{"text":84,"@type":76},"DGSfM filters the view graph and correspondences using depth-aware consistency. It prunes edges via triplet-guided edge pruning and removes matches that disagree under reprojection and target-view depth constraints.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]