[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-450309-105":59,"doc-detail-450309-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","deep-learning-based-high-dynamic-range-3d-reconstruction","Deep learning-based high dynamic range 3D reconstruction","","Fringe projection profilometry (FPP) enables high-precision 3D reconstruction, yet HDR scenes often suffer from overexposure when object reflectance and illumination vary, which degrades reconstruction accuracy by saturating captured fringes. A deep learning-based fringe image restoration approach is proposed using U-Net derivative networks to recover saturated fringes for subsequent 3D reconstruction. The method improves accuracy without adding hardware or requiring multiple additional image sets. Three architectures—UNet, Res-U-Net, and SE-U-Net—are compared quantitatively, with SE-U-Net best at restoring missing regions.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/deep-learning-based-high-dynamic-range-3d-reconstruction/450309/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/deep-learning-based-high-dynamic-range-3d-reconstruction/450309.png","ImageObject",300,407,{"name":92,"@type":93},"Aurelia","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-07","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why does overexposure occur in HDR fringe projection measurements?","Question",{"text":112,"@type":113},"Overexposure happens because highly reflective areas can exceed the camera’s grayscale dynamic range, causing fringe images to saturate and lose surface information.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is the proposed solution for saturated fringes in HDR scenes?",{"text":117,"@type":113},"A deep learning-based fringe image restoration method using U-Net derivative networks restores saturated fringes so that accurate 3D reconstruction can follow.",{"name":119,"@type":110,"acceptedAnswer":120},"How do UNet, Res-U-Net, and SE-U-Net compare for fringe repair?",{"text":121,"@type":113},"All three networks can repair saturated fringes, and SE-U-Net performs best, especially in restoring missing regions, according to quantitative experiments.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},450309,1790818897,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},1099514068365,"https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDeep learning-based high dynamic range 3D reconstruction  \nYifan Wang  \nThree-dimensional (3D) reconstruction based on fringe projection profilometry (FPP) is a crucial technique for capturing surface topography in high-precision industrial manufacturing. However, overexposure phenomenon frequently occurs in captured images due to variations in object reflectance and lighting conditions, leading to reduced 3D reconstruction accuracy. This represents the most challenging issue in high dynamic range (HDR) environments. To this end, I propose a deep learning-based fringe image restoration method. It utilizes the derivative networks of U-Net to restore saturated fringes, enabling subsequent 3D reconstruction. This method significantly enhances reconstruction accuracy without requiring additional hardware or capturing multiple extra image sets for prediction. I further systematically compared the performance of three network architectures—UNet, Res-U-Net, and SE-U-Net—in the fringe repair task, revealing their respective capabilities through quantitative experimental analysis. Comparative experiments show that all three networks in this paper can effectively repair saturated fringes, with SE-U-Net exhibiting superior performance in restoring missing regions. This study not only validates the effectiveness of deep learning for repairing saturated fringe images in HDR scenes, but also provides guidance for selecting network models ingrating fringe restoration.  \nKeywords Three-dimensional, Fringe projection profilometry, Overexposure phenomenon, Deep learning, U-Net  \nThree-dimensional (3D) imaging techniques1 achieve 3D reconstruction by comprehensively capturing the spatial geometric information of objects—including their depth, shape, and spatial structure. They have been widely applied in fields such as medical diagnosis, industrial inspection, and reverse engineering2. Typically, 3D imaging techniques are categorized into contact measurement3 and non-contact measurement with the latter primarily relying on optical methods. Among these, structured light scanning technology4, owing to its high accuracy and resolution, has become a focus of both research and practical applications.  \nAs a significant branch of structured light scanning5, Fringe Projection Profilometry (FPP) projects a set of known structured fringe images onto the object’s6. A camera captures the deformed fringe images, which undergo phase demodulation, phase unwrapping, and 2D-3D using calibration parameters7. The most common methods for phase demonstration include transform profilometry based on single frame fringe projection, such as Fourier transform profilometry (FTP)8 and wavelet transform profilometry (WTP)9, and phase-shifting profilometry (PSP)10, 11 based on multi frame fringe projection. The phase demodulation accuracy of FTP and WTP is low, suitable for simple continuous shapes, and sensitive to noise. PSP has high precision and robustness, but requires three or more fringes. FTP, WTP, and PSP algorithms do not obtain continuous phases, but are folded into wrapped phases from-π to π, requiring further phase unwrapping.  \nPhase unwrapping methods are generally categorized into Temporal Phase Unwrapping (TPU)12, 13 and Spatial Phase Unwrapping (SPU)14, 15. TPU is often combined with Phase-shifting Profilometry (PSP)16 to achieve high-precision, pixel-by-pixel phase extraction. In contrast, SPU typically employs Fourier transforms to extract phase information17, 18, relying on phase values from adjacent pixels for unwrapping, which makes it unsuitable for isolated or complex objects. Furthermore, in practical measurements, SPU is susceptible to factors such as noise, abrupt changes, and loss of detail in shadowed regions, resulting in low reconstruction accuracy.  \nIn addition, the diversity of surface colors and textures on objects leads to varying reflectivity. Constrained by","cbCaid6hg6iAvvow","https://ap.wps.com/l/cbCaid6hg6iAvvow","pdf",3293248,13,"English","# Introduction\n## 3D reconstruction and structured light scanning\n## Fringe Projection Profilometry (FPP)\n## Phase demodulation and unwrapping\n## HDR measurement challenges and overexposure\n## Related HDR approaches and limitations\n## Proposed deep learning-based restoration method","[{\"question\":\"Why does overexposure occur in HDR fringe projection measurements?\",\"answer\":\"Overexposure happens because highly reflective areas can exceed the camera’s grayscale dynamic range, causing fringe images to saturate and lose surface information.\"},{\"question\":\"What is the proposed solution for saturated fringes in HDR scenes?\",\"answer\":\"A deep learning-based fringe image restoration method using U-Net derivative networks restores saturated fringes so that accurate 3D reconstruction can follow.\"},{\"question\":\"How do UNet, Res-U-Net, and SE-U-Net compare for fringe repair?\",\"answer\":\"All three networks can repair saturated fringes, and SE-U-Net performs best, especially in restoring missing regions, according to quantitative experiments.\"}]","Deep learning-based high dynamic range 3D reconstruction | PDF",1790732846,33]