[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84547-en":3,"doc-seo-84547-105":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},84547,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring","Image deblurring methods typically reconstruct the spatial image directly, yet phase estimation critically determines recovery of sharp details. This work introduces amplitude and phase decomposition that explicitly estimates Fourier amplitude and phase for a blurred, noisy observation. It develops linear minimum mean squared error (LMMSE) estimators for amplitude/phase, then uses an iterative optimization procedure to reconstruct the sharp image. UPADNet unrolls the phase-amplitude recovery iterations and learns fixed matrix parameters end-to-end via training, improving performance especially under high noise and limited data.","arXiv :2607 .00251v1 [ cs .CV] 30 Jun 2026  \nLeveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring  \nSamira Malek 1, Haichuan Zhang 1, Chul Lee2, and Vishal Monga 1  \n1 Pennsylvania State University, University Park, PA 16802, USA  \n{sxm6547,hzz5333,[vum4}@psu.edu](vum4}@psu.edu)  \n2 Dongguk University, Seoul 04620, South Korea  \n[chullee@dongguk.edu](chullee@dongguk.edu)  \nAbstract. While most image deblurring techniques directly restore the spatial image variable, we propose an amplitude and phase decomposition recognizing the importance of accurate phase estimation in recovering sharp image details. To that end, we first develop novel linear minimum mean squared (LMMSE) estimators of the amplitude and phase of the blurred, noisy image observation. An iterative optimization algorithm follows that recovers the sharp image using the aforementioned LMMSE estimators. Finally, matrix parameters that are statistically determined and fixed in the iterative algorithm are now learned using a training dataset of clean and degraded observations. Our deblurring engine is dubbed UPADNet – Unrolled Phase and Amplitude Decomposition Network, such that each iteration of the underlying phase and amplitude recovery algorithm is parameterized and trained end-to-end.  \nExperiments over benchmark evaluation datasets such as GoPro, RealBlur and COCO datasets confirm that UPADNet outperforms state of the art deep networks including those based on algorithm unrolling in the image domain. The benefits of UPADNet are even more pronounced in high noise and limited training data regimes.  \nKeywords: Image Deblurring · Image restoration · Fourier Phase and Amplitude Decomposition · Phase Unrolling · Deep Unrolling  \n1 Introduction  \nImage deblurring, a sub-problem of image restoration, aims to recover a sharp image from a blurred observation. In real-world imaging, blur artifacts arise from various sources such as atmospheric turbulence, diffraction, optical defocusing, and camera motion [22] .  \nVarious approaches have been developed to address blind image deblurring, one of which is leveraging mathematical modeling and statistical estimation techniques [22] . Some methods focus on estimating the blur kernel using sharp edge prediction [17] and sparsity constraints in the image domain [43, 67] . A common strategy has been to incorporate strong regularizations, such as ℓ0-norm sparsity [43, 67], normalized sparsity [21], and total variation constraints [46], to  \n2 S. Malek et al.  \nmitigate the ill-posed nature of the problem. Several studies have explored novel priors, including patch priors [57], dark channel priors [44], and extreme channel priors [68], which exploit natural image statistics to enhance sharp image estimation. Bayesian inference has also been widely used, employing marginalization over the high-dimensional image space [65] and general sparse image priors [2] to improve robustness. A notable contribution in this line is [55], which introduced a unified probabilistic framework for joint blur kernel estimation and image restoration. Framelet-based methods [4] offer alternative strategies by leveraging transform-domain representations. Some works analyze the fundamental limitations of existing marginal likelihood optimization approaches and provide a broader theoretical evaluation of blind deconvolution algorithms, introducing efficient MAP-based methods [27, 28] . In [14], an iterative refinement framework was proposed that categorizes kernel types by alternating between kernel and image updates to achieve improved results. A modified Newton integration algorithm is presented from a control perspective, offering noise tolerance and fast convergence [32] . Additionally, in [9], Polyblur was introduced as a non-iterative method for removing mild blur by leveraging polynomial reblurring, which offers practical benefits for lightly degraded images.  \nRecent advances in image deblurring have largely focused on ","cbCaiaL5F6cangyr","https://ap.wps.com/l/cbCaiaL5F6cangyr","pdf",16837468,1,26,"English","en",105,"# Abstract\n# Introduction\n## Image deblurring problem setting\n## Blind deblurring and statistical estimation\n## Priors and Bayesian inference\n## Framelet and optimization-based methods\n## Data-driven deep learning approaches\n## Transformer and frequency-domain methods\n## GAN and generative models","[{\"question\":\"What core idea does the document propose for image deblurring?\",\"answer\":\"It decomposes the image into Fourier amplitude and phase, emphasizing that accurate phase estimation is essential for recovering sharp details.\"},{\"question\":\"How does UPADNet integrate estimation and learning?\",\"answer\":\"It uses LMMSE-based amplitude and phase estimators inside an iterative optimization scheme, then unrolls these iterations and learns fixed matrix parameters end-to-end with training data.\"},{\"question\":\"What experimental settings show UPADNet’s advantages?\",\"answer\":\"Results on benchmark datasets such as GoPro, RealBlur, and COCO show better performance than state-of-the-art deep unrolling methods, with larger gains in high-noise and limited-training-data regimes.\"}]",1784196581,66,{"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},"leveraging-phase-information-to-boost-unrolled-network-learning-for-image-deblurring","",{"@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/leveraging-phase-information-to-boost-unrolled-network-learning-for-image-deblurring/84547/",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 core idea does the document propose for image deblurring?","Question",{"text":75,"@type":76},"It decomposes the image into Fourier amplitude and phase, emphasizing that accurate phase estimation is essential for recovering sharp details.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does UPADNet integrate estimation and learning?",{"text":80,"@type":76},"It uses LMMSE-based amplitude and phase estimators inside an iterative optimization scheme, then unrolls these iterations and learns fixed matrix parameters end-to-end with training data.",{"name":82,"@type":73,"acceptedAnswer":83},"What experimental settings show UPADNet’s advantages?",{"text":84,"@type":76},"Results on benchmark datasets such as GoPro, RealBlur, and COCO show better performance than state-of-the-art deep unrolling methods, with larger gains in high-noise and limited-training-data regimes.","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"]