{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/loformer-local-frequency-transformer-for","title":"LoFormer: Local Frequency Transformer for Image Deblurring","arxiv_id":"2407.16993","date":"2024-07-24","proceeding":null,"authors":["Xintian Mao","Jiansheng Wang","Xingran Xie","Qingli Li","Yan Wang"],"abstract":"Due to the computational complexity of self-attention (SA), prevalent techniques for image deblurring often resort to either adopting localized SA or employing coarse-grained global SA methods, both of which exhibit drawbacks such as compromising global modeling or lacking fine-grained correlation. In order to address this issue by effectively modeling long-range dependencies without sacrificing fine-grained details, we introduce a novel approach termed Local Frequency Transformer (LoFormer). Within each unit of LoFormer, we incorporate a Local Channel-wise SA in the frequency domain (Freq-LC) to simultaneously capture cross-covariance within low- and high-frequency local windows. These operations offer the advantage of (1) ensuring equitable learning opportunities for both coarse-grained structures and fine-grained details, and (2) exploring a broader range of representational properties compared to coarse-grained global SA methods. Additionally, we introduce an MLP Gating mechanism complementary to Freq-LC, which serves to filter out irrelevant features while enhancing global learning capabilities. Our experiments demonstrate that LoFormer significantly improves performance in the image deblurring task, achieving a PSNR of 34.09 dB on the GoPro dataset with 126G FLOPs. https://github.com/DeepMed-Lab-ECNU/Single-Image-Deblur","url_abs":"https://arxiv.org/abs/2407.16993v1","url_pdf":"https://arxiv.org/pdf/2407.16993v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"loformer-local-frequency-transformer-for","repo_url":"https://github.com/deepmed-lab-ecnu/single-image-deblur","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"loformer-local-frequency-transformer-for","repo_url":"https://github.com/INVOKERer/LoFormer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-hide-trained-on-gopro","task":"Deblurring","dataset":"HIDE (trained on GOPRO)","model":"LoFormer","rank_in_archive_order":5,"of":26,"metrics":{"PSNR (sRGB)":"31.86","SSIM (sRGB)":"0.949"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset":"RealBlur-J","model":"LoFormer","rank_in_archive_order":6,"of":17,"metrics":{"PSNR (sRGB)":"32.90","SSIM (sRGB)":"0.933"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset":"RealBlur-R","model":"LoFormer","rank_in_archive_order":7,"of":17,"metrics":{"PSNR (sRGB)":"40.23","SSIM (sRGB)":"0.974"},"uses_additional_data":false},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"LoFormer","rank_in_archive_order":5,"of":55,"metrics":{"PSNR":"34.09","SSIM":"0.969"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.16993","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}