[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-138794-en":3,"doc-seo-138794-105":30,"detail-sidebar-cat-0-en-105":92},{"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":27,"seo_description":14,"update_tm":28,"read_time":29},138794,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",6,"Technology","Reference-based Image Super-Resolution with Deformable Attention Transformer - Paper","Reference-based image super-resolution (RefSR) leverages auxiliary reference images to reconstruct high-resolution details from low-resolution inputs. This work targets two persistent issues: establishing reliable correspondence between low-resolution and reference images when their distributions differ, and transferring useful textures from references without amplifying mismatches. The proposed deformable attention Transformer (DATSR) uses a multi-scale design with a texture feature encoder for transformation-insensitive features, a reference-based deformable attention module to exploit multiple relevant textures, and a residual feature aggregation module to produce visually pleasing outputs. Extensive experiments show state-of-the-art results on benchmark datasets.","Reference-based Image Super-Resolution with Deformable Attention Transformer  \nJiezhang Cao 1 , Jingyun Liang 1 , Kai Zhang 1 , Yawei Li 1 , Yulun Zhang 1 ⋆ , Wenguan Wang 1 , and Luc Van Gool 1 ,2  \n1 Computer Vision Lab, ETH Z¨urich, Switzerland 2 KU Leuven, Belgium  \n{jiezhang.cao, jingyun.liang, kai.zhang, [yawei.li](yawei.li) , yulun.zhang, [wenguan.wang](wenguan.wang) , [vangool](vangool}@vision.ee.ethz.ch)[}](vangool}@vision.ee.ethz.ch)[@vision.ee.ethz.ch](vangool}@vision.ee.ethz.ch)  \n[https://github.com/caojiezhang/DATSR](https://github.com/caojiezhang/DATSR)  \nAbstract. Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images. Recently, RefSR has been attracting great attention as it provides an alternative way to surpass single image SR. However, addressing the RefSR problem has two critical challenges: (i) It is difficult to match the correspondence between LR and Ref images when they are significantly different; (ii) How to transfer the relevant texture from Ref images to compensate the details for LR images is very challenging. To address these issues of RefSR, this paper proposes a deformable attention Transformer, namely DATSR, with multiple scales, each of which consists of a texture feature encoder (TFE) module, a reference-based deformable attention (RDA) module and a residual feature aggregation (RFA) module. Specifically, TFE first extracts image transformation (e.g., brightness) insensitive features for LR and Ref images, RDA then can exploit multiple relevant textures to compensate more information for LR features, and RFA lastly aggregates LR features and relevant textures to get a more visually pleasant result. Extensive experiments demonstrate that our DATSR achieves state-of-the-art performance on benchmark datasets quantitatively and qualitatively.  \nKeywords: Reference-based Image Super-Resolution, Correspondence Matching, Texture Transfer, Deformable Attention Transformer  \n1 Introduction  \nSingle image super-resolution (SISR), which aims at recovering a high-resolution (HR) image from a low-resolution (LR) input, is an active research topic due to its high practical values [13,51 , 18 ,49 ,41 , 15 ,46 ,21 , 16 , 14 ,9 ,20] . However, SISR is a highly ill-posed problem since there exist multiple HR images that can degrade to the same LR image [38,8] . While real LR images usually have no corresponding HR ground-truth (GT) images, one can easily find a high-quality image asa reference (Ref) image with high-frequency details from various sources, such  \n⋆ Corresponding author.  \n2 Jiezhang Cao et al.  \nFig. 1: Comparison with the state-of-the-art RefSR method C2-Matching [12] . When the brightness of LR and Ref image is different, our method performs better than C2-Matching [12] in transferring relevant textures from the Ref image to the SR image, which is closer to the ground-truth image.  \nas photo albums, video frames, and web image search, which has similar semantic information (such as content and texture) to the LR image. Such an alternative SISR method is referred to as reference-based super-resolution (RefSR), which aims to transfer HR textures from the Ref images to super-resolved images and has shown promising results over SISR. Although various RefSR methods [12,27 ,47 ,45] have been recently proposed, two challenges remain unsolved for SR performance improvement.  \nFirst, it is difficult to match the correspondence between the LR and Ref images especially when their distributions are different. For example, the brightness of the Ref images is different from that of the LR images. Existing methods [56,48] mostly match the correspondence by estimating the pixel or patch similarity of texture features between LR and Ref images. However, such similarity metric is sensitive to image transformations, such as brightness and color of images. Recently, the state-of-the-art (SOTA) method C2-Matching [12] trains a fe","cbCaim14R2eC9WVm","https://ap.wps.com/l/cbCaim14R2eC9WVm","pdf",4515257,1,18,"English","en",105,"# Introduction\n## Challenges in RefSR\n## Proposed DATSR approach\n## Experimental evaluation","[{\"question\":\"What is reference-based image super-resolution (RefSR) and how does it differ from SISR?\",\"answer\":\"RefSR reconstructs a high-resolution image by transferring details from an auxiliary reference image, while SISR attempts to recover high resolution using only a low-resolution input.\"},{\"question\":\"What are the two main challenges addressed in the paper?\",\"answer\":\"The paper focuses on correspondence matching between low-resolution and reference images under distribution differences, and on transferring relevant textures from reference images to compensate low-resolution details accurately.\"},{\"question\":\"How does DATSR improve correspondence and texture transfer?\",\"answer\":\"DATSR extracts transformation-insensitive features with the texture feature encoder, uses a reference-based deformable attention module to exploit multiple relevant textures, and then aggregates low-resolution features and relevant textures via residual feature aggregation to generate the final result.\"}]","Reference-based Image Super-Resolution with Deformable Attention Transformer - Paper | PDF",1787488403,45,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"reference-based-image-super-resolution-with-deformable-attention-transformer-paper","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/reference-based-image-super-resolution-with-deformable-attention-transformer-paper/138794/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-31","2026-08-23",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is reference-based image super-resolution (RefSR) and how does it differ from SISR?","Question",{"text":76,"@type":77},"RefSR reconstructs a high-resolution image by transferring details from an auxiliary reference image, while SISR attempts to recover high resolution using only a low-resolution input.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What are the two main challenges addressed in the paper?",{"text":81,"@type":77},"The paper focuses on correspondence matching between low-resolution and reference images under distribution differences, and on transferring relevant textures from reference images to compensate low-resolution details accurately.",{"name":83,"@type":74,"acceptedAnswer":84},"How does DATSR improve correspondence and texture transfer?",{"text":85,"@type":77},"DATSR extracts transformation-insensitive features with the texture feature encoder, uses a reference-based deformable attention module to exploit multiple relevant textures, and then aggregates low-resolution features and relevant textures via residual feature aggregation to generate the final result.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,114,119,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},8,"Research & Report",30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]