[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-450306-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-450306-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","structure-from-motion-in-micro-image-domain-for-uncalibrated-plenoptic-20-cameras","Structure-from-motion in micro-image domain for uncalibrated plenoptic 2.0 cameras","","Introduces a structure-from-motion method tailored for raw micro-images captured by plenoptic 2.0 cameras. Unlike monocular setups, plenoptic cameras use a micro-lens array that provides depth-related disparity but increases the parameter space required for evaluation. The approach derives pinhole-camera-driven constraints and leverages inherent disparity to robustly initialize reconstruction, resolving classical low-angular-disparity ambiguity and scale ambiguity, without calibration patterns or subaperture view extraction. Validated on natural and synthetic datasets, it reaches ~10% relative-pose error, remains robust under coarse initialization, reconstructs scenes from multiple uncalibrated plenoptic cameras including parallel-facing viewpoints, and outperforms pinhole-conversion-based methods.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/structure-from-motion-in-micro-image-domain-for-uncalibrated-plenoptic-20-cameras/450306/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/structure-from-motion-in-micro-image-domain-for-uncalibrated-plenoptic-20-cameras/450306.png","ImageObject",300,407,{"name":42,"@type":43},"Genevieve","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-06","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the proposed method address for plenoptic 2.0 cameras?","Question",{"text":63,"@type":64},"It targets reconstruction from raw micro-images in an uncalibrated plenoptic 2.0 setting, where classical SfM ambiguities and the micro-image parameter complexity hinder robust metric reconstruction.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the method obtain a robust initialization for reconstruction?",{"text":68,"@type":64},"It uses pinhole-camera-driven constraints while leveraging disparity information inherent to plenoptic cameras to initialize reconstruction effectively.",{"name":70,"@type":61,"acceptedAnswer":71},"What validation results and capabilities are reported?",{"text":72,"@type":64},"Experiments on natural and synthetic datasets show about 10% relative pose error comparable to calibration-pattern-based methods. The method is robust to coarse initialization and can reconstruct scenes from multiple uncalibrated plenoptic cameras, including parallel facing cameras, without calibration patterns or subaperture extraction.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},450306,1790838311,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,100,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":55,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":98},1374391974585,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Structure-from-motion in micro-image domain for uncalibrated plenoptic 2.0 cameras  \nSarah Dury1 · Daniele Bonatto1 · Jaime Sancho2 · Eduardo Juarez2 · Mehrdad Teratani3 · Gauthier Lafruit1  \nReceived: 23 January 2025 / Accepted: 12 November 2025 / Published online: 6 January 2026 © The Author(s) 2025  \nAbstract  \nWe introduce a structure-from-motion method specifically designed to process the raw micro-images captured by plenoptic 2.0 cameras. Unlike traditional monocular cameras, plenoptic cameras incorporate a micro-lens array between the sensor and the main lens, capturing depth information at the expense of a more complex set of parameters to evaluate. Instead of simply integrating their projection model into the classical structure-from-motion pipeline, our contribution identifies the pinhole cameras-driven constraints and takes advantage of the inherent disparity information present in plenoptic cameras. This facilitates a robust initialization of the reconstruction. Our method shortcuts two of the limitations of the classical structure-from-motion: the ambiguity found in scenes captured with low angular disparity and the scale ambiguity. It enables the reconstruction of scenes captured by multiple uncalibrated plenoptic cameras, without using any calibration pattern or subaperture view extraction step. Our method undergoes experimental validation on both natural and synthetic datasets, showing a 10% error accuracy for relative pose estimation, which is comparable to calibration-pattern based methods. The results are robust to coarse initialization. Contrary to classical structure-from-motion, it is able to reconstruct scenes with parallel facing cameras. It also shows greater accuracy than reconstruction methods based on pinhole camera conversion.  \nKeywords Calibration · Plenoptic 2.0 cameras · Structure-from-motion · Micro-lens  \nCommunicated by D. Scharstein.  \nB Sarah Dury [sarah.dury@ulb.be](sarah.dury@ulb.be)  \nDaniele Bonatto  \n[daniele.bonatto@ulb.be](daniele.bonatto@ulb.be)  \nJaime Sancho  \n[jaime.sancho@upm.es](jaime.sancho@upm.es)  \nEduardo Juarez  \n[eduardo.juarez@upm.es](eduardo.juarez@upm.es)  \nMehrdad Teratani  \n[teratani.mehrdad.v5@f.mail.nagoya-u.ac.jp](teratani.mehrdad.v5@f.mail.nagoya-u.ac.jp)  \nGauthier Lafruit  \n[gauthier.lafruit@ulb.be](gauthier.lafruit@ulb.be)  \n1 LISA, Université Libre de Bruxelles, Brussels, Belgium  \n2 CITSEM, Universidad Politécnica de Madrid, Madrid, Spain  \n3 Department of Information and Communication Engineering, Nagoya University, Nagoya, Japan  \n1 Introduction  \nThis paper describes a structure-from-motion (SfM) algorithm designed for plenoptic cameras (plenoptic 2.0 camera) . Calibratedplenoptic cameras capture3D information ina single view with few space requirements, but there remain the problems of occlusions and field of view. On the other side, a moving regular camera can reconstruct the 3D geometry of a large scene, but only up to a scale, even when the camera is calibrated. This paper proposes to take the best of the two worlds, by introducing the first structure-from-motion algorithm that recovers the scene scale without calibration pattern, provided the nominal focal length of the main lens.  \nSfM is the reconstruction of 3D scenes from unstructured sets of images (Ullman, 1979; Mohr et al., 1995; Beardsley et al., 1996; Snavely et al., 2006; Schonberger and Frahm, 2016), which has been one of the most critical problems in computer vision since its early steps. SfM isnow the basis for advanced 3D applications such as view synthesis (Mildenhalletal., 2020; Kerbl et al., 2023), depth estimation (Li and Snavely, 2018), 3D scene understanding (Zuo et al., 2024)  \nFig. 1 Pipeline of our proposed method. 1) The input is a set of images in plenoptic format. 2) Plenoptic images allow to search for intra-image correspondences, conveying disparity information. The inter-images correspondences step is similar to the classical SfM pipeline. 3) The  \nreconstruction pipeline is","cbCaimprCRL6CZDP","https://ap.wps.com/l/cbCaimprCRL6CZDP","pdf",2454723,24,"English","# Abstract\n# Keywords\n# Introduction","[{\"question\":\"What problem does the proposed method address for plenoptic 2.0 cameras?\",\"answer\":\"It targets reconstruction from raw micro-images in an uncalibrated plenoptic 2.0 setting, where classical SfM ambiguities and the micro-image parameter complexity hinder robust metric reconstruction.\"},{\"question\":\"How does the method obtain a robust initialization for reconstruction?\",\"answer\":\"It uses pinhole-camera-driven constraints while leveraging disparity information inherent to plenoptic cameras to initialize reconstruction effectively.\"},{\"question\":\"What validation results and capabilities are reported?\",\"answer\":\"Experiments on natural and synthetic datasets show about 10% relative pose error comparable to calibration-pattern-based methods. The method is robust to coarse initialization and can reconstruct scenes from multiple uncalibrated plenoptic cameras, including parallel facing cameras, without calibration patterns or subaperture extraction.\"}]","Structure-from-motion in micro-image domain for uncalibrated plenoptic 2.0 cameras | PDF",1790732839]