{"url":"/sota/image-deblurring-on-gopro","task":{"name":"Image Deblurring","url":"/task/image-deblurring","note":null},"dataset":{"name":"GoPro","url":"/dataset/gopro"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"file:///var/mobile/Library/SMS/Attachments/cb/11/8A26E2FC-7464-4692-8F2A-3F1B3E23BCD5/IMG_4630.jpeg","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["PSNR","SSIM","Params (M)","FID","LPIPS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"PSNR":"higher","SSIM":"higher","Params (M)":"lower","FID":"lower","LPIPS":null}},"counts":{"rows":55,"rows_with_code":46,"rows_with_paper_page":54,"rows_dated":54,"rows_using_additional_data":21},"rows":[{"rank_in_archive_order":1,"model":"AdaRevD","metrics":{"PSNR":"34.6","SSIM":"0.972"},"uses_additional_data":false,"paper_date":"2024-06-13","paper":"/paper/adarevd-adaptive-patch-exiting-reversible-1","paper_url":"https://arxiv.org/abs/2406.09135v1","paper_title":"AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring","code":"https://github.com/invokerer/deeprft","n_code_links":4,"syntology":{"n_ran":36,"n_unverified":14,"n_samples":50,"n_pointer_only_licence":50}},{"rank_in_archive_order":2,"model":"EVSSM","metrics":{"PSNR":"34.5","SSIM":"0.9712"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/efficient-visual-state-space-model-for-image","paper_url":"https://arxiv.org/abs/2405.14343v1","paper_title":"Efficient Visual State Space Model for Image Deblurring","code":"https://github.com/kkkls/evssm","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MDT","metrics":{"PSNR":"34.26"},"uses_additional_data":false,"paper_date":"2025-01-01","paper":"/paper/a-polarization-aided-transformer-for-image","paper_url":"http://openaccess.thecvf.com//content/CVPR2025/html/Chen_A_Polarization-Aided_Transformer_for_Image_Deblurring_via_Motion_Vector_Decomposition_CVPR_2025_paper.html","paper_title":"A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"fftformer","metrics":{"PSNR":"34.21","Params (M)":"16.6","SSIM":"0.969"},"uses_additional_data":true,"paper_date":"2022-11-22","paper":"/paper/efficient-frequency-domain-based-transformers","paper_url":"https://arxiv.org/abs/2211.12250v1","paper_title":"Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring","code":"https://github.com/kkkls/fftformer","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"LoFormer","metrics":{"PSNR":"34.09","SSIM":"0.969"},"uses_additional_data":false,"paper_date":"2024-07-24","paper":"/paper/loformer-local-frequency-transformer-for","paper_url":"https://arxiv.org/abs/2407.16993v1","paper_title":"LoFormer: Local Frequency Transformer for Image Deblurring","code":"https://github.com/INVOKERer/LoFormer","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"UFPDeblur","metrics":{"PSNR":"34.06","Params (M)":"80.3","SSIM":"0.968"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/self-supervised-non-uniform-kernel-estimation","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Fang_Self-Supervised_Non-Uniform_Kernel_Estimation_With_Flow-Based_Motion_Prior_for_Blind_CVPR_2023_paper.html","paper_title":"Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring","code":"https://github.com/fangzhenxuan/ufpdeblur","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"ALGNet-B","metrics":{"PSNR":"34.05","SSIM":"0.969"},"uses_additional_data":false,"paper_date":"2024-03-29","paper":"/paper/aggregating-local-and-global-features-via","paper_url":"https://arxiv.org/abs/2403.20106v2","paper_title":"Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring","code":"https://github.com/Tombs98/ALGNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MR-VNet","metrics":{"PSNR":"34.04","Params (M)":"12.3","SSIM":"0.969"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/mr-vnet-media-restoration-using-volterra","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Roheda_MR-VNet_Media_Restoration_using_Volterra_Networks_CVPR_2024_paper.html","paper_title":"MR-VNet: Media Restoration using Volterra Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Hi-IR-L","metrics":{"PSNR":"33.99"},"uses_additional_data":false,"paper_date":"2024-11-27","paper":"/paper/hierarchical-information-flow-for-generalized","paper_url":"https://arxiv.org/abs/2411.18588v1","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"GRL","metrics":{"PSNR":"33.93","Params (M)":"19.81","SSIM":"0.968"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/efficient-and-explicit-modelling-of-image","paper_url":"https://arxiv.org/abs/2303.00748v2","paper_title":"Efficient and Explicit Modelling of Image Hierarchies for Image Restoration","code":"https://github.com/ofsoundof/grl-image-restoration","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":8,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Instruct-IPT","metrics":{"PSNR":"33.86","SSIM":"0.967"},"uses_additional_data":true,"paper_date":"2024-06-30","paper":"/paper/instruct-ipt-all-in-one-image-processing-1","paper_url":"https://arxiv.org/abs/2407.00676v2","paper_title":"Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation","code":"https://github.com/huawei-noah/Pretrained-IPT","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"MADANet","metrics":{"PSNR":"33.84","Params (M)":"16.9","SSIM":"0.964"},"uses_additional_data":true,"paper_date":"2020-06-19","paper":"/paper/motion-aware-double-attention-network-for","paper_url":"https://openaccess.thecvf.com/content/CVPR2022W/NTIRE/html/Yang_Motion_Aware_Double_Attention_Network_for_Dynamic_Scene_Deblurring_CVPRW_2022_paper.html","paper_title":"Motion Aware Double Attention Network for Dynamic Scene Deblurring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"CGNet","metrics":{"PSNR":"33.77","SSIM":"0.968"},"uses_additional_data":false,"paper_date":"2024-01-26","paper":"/paper/cascadedgaze-efficiency-in-global-context","paper_url":"https://arxiv.org/abs/2401.15235v2","paper_title":"CascadedGaze: Efficiency in Global Context Extraction for Image Restoration","code":"https://github.com/Ascend-Research/CascadedGaze","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"NAFNet-MH-C","metrics":{"PSNR":"33.75","SSIM":"0.967"},"uses_additional_data":false,"paper_date":"2022-08-27","paper":"/paper/multi-outputs-is-all-you-need-for-deblur","paper_url":"https://arxiv.org/abs/2208.13029v1","paper_title":"Multi-Outputs Is All You Need For Deblur","code":"https://github.com/liu-sd/multi-output-deblur","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"M3SNet","metrics":{"PSNR":"33.74","SSIM":"0.967"},"uses_additional_data":false,"paper_date":"2023-05-09","paper":"/paper/a-mountain-shaped-single-stage-network-for","paper_url":"https://arxiv.org/abs/2305.05146v1","paper_title":"A Mountain-Shaped Single-Stage Network for Accurate Image Restoration","code":"https://github.com/Tombs98/M3SNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"CAPTNet","metrics":{"PSNR":"33.74","SSIM":"0.967"},"uses_additional_data":false,"paper_date":"2023-09-06","paper":"/paper/prompt-based-all-in-one-image-restoration","paper_url":"https://arxiv.org/abs/2309.03063v2","paper_title":"Prompt-based Ingredient-Oriented All-in-One Image Restoration","code":"https://github.com/Tombs98/CAPTNet","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":12}},{"rank_in_archive_order":17,"model":"LAKDNet","metrics":{"PSNR":"33.72","Params (M)":"37.5","SSIM":"0.967"},"uses_additional_data":false,"paper_date":"2023-02-04","paper":"/paper/revisiting-image-deblurring-with-an-efficient","paper_url":"https://arxiv.org/abs/2302.02234v1","paper_title":"Revisiting Image Deblurring with an Efficient ConvNet","code":"https://github.com/lingyanruan/lakdnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"NAFNet - TLC","metrics":{"PSNR":"33.69","Params (M)":"67.89","SSIM":"0.967"},"uses_additional_data":false,"paper_date":"2022-04-10","paper":"/paper/simple-baselines-for-image-restoration","paper_url":"https://arxiv.org/abs/2204.04676v4","paper_title":"Simple Baselines for Image Restoration","code":"https://github.com/megvii-research/NAFNet","n_code_links":13,"syntology":{"n_ran":23,"n_unverified":7,"n_samples":30,"n_pointer_only_licence":17}},{"rank_in_archive_order":19,"model":"MaIR","metrics":{"PSNR":"33.69"},"uses_additional_data":false,"paper_date":"2024-12-28","paper":"/paper/mair-a-locality-and-continuity-preserving","paper_url":"https://arxiv.org/abs/2412.20066v1","paper_title":"MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration","code":"https://github.com/XLearning-SCU/2025-CVPR-MaIR","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"Restormer-TLC","metrics":{"PSNR":"33.57","Params (M)":"26.13","SSIM":"0.966"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/revisiting-global-statistics-aggregation-for","paper_url":"https://arxiv.org/abs/2112.04491v4","paper_title":"Improving Image Restoration by Revisiting Global Information Aggregation","code":"https://github.com/megvii-research/NAFNet","n_code_links":3,"syntology":null},{"rank_in_archive_order":21,"model":"DeepRFT+","metrics":{"PSNR":"33.52","SSIM":"0.965"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/deep-residual-fourier-transformation-for","paper_url":"https://arxiv.org/abs/2111.11745v2","paper_title":"Intriguing Findings of Frequency Selection for Image Deblurring","code":"https://github.com/invokerer/deeprft","n_code_links":5,"syntology":null},{"rank_in_archive_order":22,"model":"MPRNet-TLC","metrics":{"PSNR":"33.31","Params (M)":"20.1","SSIM":"0.964"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/revisiting-global-statistics-aggregation-for","paper_url":"https://arxiv.org/abs/2112.04491v4","paper_title":"Improving Image Restoration by Revisiting Global Information Aggregation","code":"https://github.com/megvii-research/NAFNet","n_code_links":3,"syntology":null},{"rank_in_archive_order":23,"model":"FSNet","metrics":{"PSNR":"33.29","SSIM":"0.963"},"uses_additional_data":false,"paper_date":"2023-11-06","paper":"/paper/image-restoration-via-frequency-selection","paper_url":"https://ieeexplore.ieee.org/document/10310164","paper_title":"Image Restoration via Frequency Selection","code":"https://github.com/c-yn/FSNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"MSDI-Net","metrics":{"PSNR":"33.28","SSIM":"0.964"},"uses_additional_data":false,"paper_date":"2022-08-10","paper":"/paper/learning-degradation-representations-for","paper_url":"https://arxiv.org/abs/2208.05244v1","paper_title":"Learning Degradation Representations for Image Deblurring","code":"https://github.com/dasongli1/learning_degradation","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":25,"model":"ChaIR","metrics":{"PSNR":"33.28","SSIM":"0.963"},"uses_additional_data":false,"paper_date":"2023-12-20","paper":"/paper/exploring-the-potential-of-channel","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0950705123009061","paper_title":"Exploring the potential of channel interactions for image restoration","code":"https://github.com/c-yn/ChaIR","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"ConvIR","metrics":{"PSNR":"33.28","SSIM":"0.963"},"uses_additional_data":false,"paper_date":"2024-06-25","paper":"/paper/revitalizing-convolutional-network-for-image","paper_url":"https://ieeexplore.ieee.org/abstract/document/10571568","paper_title":"Revitalizing Convolutional Network for Image Restoration","code":"https://github.com/c-yn/ConvIR","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"IRNeXt","metrics":{"PSNR":"33.16","SSIM":"0.962"},"uses_additional_data":false,"paper_date":"2023-04-24","paper":"/paper/irnext-rethinking-convolutional-network","paper_url":"https://openreview.net/forum?id=MZkbgahv4a","paper_title":"IRNeXt: Rethinking Convolutional Network Design for Image Restoration","code":"https://github.com/c-yn/IRNeXt","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"HINet-TLC","metrics":{"PSNR":"33.08","SSIM":"0.962"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/revisiting-global-statistics-aggregation-for","paper_url":"https://arxiv.org/abs/2112.04491v4","paper_title":"Improving Image Restoration by Revisiting Global Information Aggregation","code":"https://github.com/megvii-research/NAFNet","n_code_links":3,"syntology":null},{"rank_in_archive_order":29,"model":"MHNet","metrics":{"PSNR":"33.04","Params (M)":"17"},"uses_additional_data":false,"paper_date":"2023-02-19","paper":"/paper/mixed-hierarchy-network-for-image-restoration","paper_url":"https://arxiv.org/abs/2302.09554v4","paper_title":"Mixed Hierarchy Network for Image Restoration","code":"https://github.com/tombs98/mhnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"Uformer-B","metrics":{"PSNR":"32.97","Params (M)":"50.88","SSIM":"0.967"},"uses_additional_data":false,"paper_date":"2021-06-06","paper":"/paper/uformer-a-general-u-shaped-transformer-for","paper_url":"https://arxiv.org/abs/2106.03106v2","paper_title":"Uformer: A General U-Shaped Transformer for Image Restoration","code":"https://github.com/ZhendongWang6/Uformer","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":2}},{"rank_in_archive_order":31,"model":"Restormer","metrics":{"PSNR":"32.92","Params (M)":"26.13","SSIM":"0.961"},"uses_additional_data":false,"paper_date":"2021-11-18","paper":"/paper/restormer-efficient-transformer-for-high","paper_url":"https://arxiv.org/abs/2111.09881v2","paper_title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","code":"https://github.com/swz30/restormer","n_code_links":13,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":32,"model":"MAXIM-3S","metrics":{"PSNR":"32.86"},"uses_additional_data":false,"paper_date":"2022-01-09","paper":"/paper/maxim-multi-axis-mlp-for-image-processing","paper_url":"https://arxiv.org/abs/2201.02973v2","paper_title":"MAXIM: Multi-Axis MLP for Image Processing","code":"https://github.com/google-research/maxim","n_code_links":3,"syntology":{"n_ran":27,"n_unverified":19,"n_samples":46,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"MIMO-UNet++","metrics":{"PSNR":"32.68","Params (M)":"16.1","SSIM":"0.959"},"uses_additional_data":false,"paper_date":"2021-08-11","paper":"/paper/rethinking-coarse-to-fine-approach-in-single","paper_url":"https://arxiv.org/abs/2108.05054v2","paper_title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","code":"https://github.com/chosj95/mimo-unet","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":6}},{"rank_in_archive_order":34,"model":"MPRNet","metrics":{"PSNR":"32.66","Params (M)":"20.1","SSIM":"0.959"},"uses_additional_data":false,"paper_date":"2021-02-04","paper":"/paper/multi-stage-progressive-image-restoration","paper_url":"https://arxiv.org/abs/2102.02808v2","paper_title":"Multi-Stage Progressive Image Restoration","code":"https://github.com/swz30/restormer","n_code_links":8,"syntology":{"n_ran":18,"n_unverified":8,"n_samples":26,"n_pointer_only_licence":25}},{"rank_in_archive_order":35,"model":"MB2D","metrics":{"PSNR":"32.16","SSIM":"0.953"},"uses_additional_data":true,"paper_date":"2020-12-23","paper":"/paper/blur-more-to-deblur-better-multi-blur2deblur","paper_url":"https://arxiv.org/abs/2012.12507v1","paper_title":"Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":36,"model":"RADNet","metrics":{"PSNR":"32.15","SSIM":"0.9560"},"uses_additional_data":true,"paper_date":"2019-03-25","paper":"/paper/spatially-adaptive-residual-networks-for","paper_url":"https://arxiv.org/abs/1903.11394v4","paper_title":"Motion Deblurring with an Adaptive Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"SAPHNet","metrics":{"PSNR":"32.02","SSIM":"0.953"},"uses_additional_data":true,"paper_date":"2020-04-11","paper":"/paper/spatially-attentive-patch-hierarchical","paper_url":"https://arxiv.org/abs/2004.05343v1","paper_title":"Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"Learning Event-Based Motion Deblurring","metrics":{"PSNR":"31.79","SSIM":"0.949"},"uses_additional_data":true,"paper_date":"2020-04-13","paper":"/paper/learning-event-based-motion-deblurring","paper_url":"https://arxiv.org/abs/2004.05794v1","paper_title":"Learning Event-Based Motion Deblurring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"SRN+PSS+NSC","metrics":{"PSNR":"31.58","SSIM":"0.9478"},"uses_additional_data":true,"paper_date":"2019-06-01","paper":"/paper/dynamic-scene-deblurring-with-parameter","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Gao_Dynamic_Scene_Deblurring_With_Parameter_Selective_Sharing_and_Nested_Skip_CVPR_2019_paper.html","paper_title":"Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections","code":"https://github.com/firenxygao/deblur","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"DMPHN","metrics":{"PSNR":"31.50","SSIM":"0.9483"},"uses_additional_data":true,"paper_date":"2019-04-06","paper":"/paper/deep-stacked-hierarchical-multi-patch-network","paper_url":"http://arxiv.org/abs/1904.03468v1","paper_title":"Deep Stacked Hierarchical Multi-patch Network for Image Deblurring","code":"https://github.com/HongguangZhang/DMPHN-cvpr19-master","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"SDWNet","metrics":{"PSNR":"31.36"},"uses_additional_data":false,"paper_date":"2021-10-12","paper":"/paper/sdwnet-a-straight-dilated-network-with","paper_url":"https://arxiv.org/abs/2110.05803v1","paper_title":"SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring","code":"https://github.com/flyegle/sdwnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"MT-RNN","metrics":{"PSNR":"31.15","SSIM":"0.945"},"uses_additional_data":true,"paper_date":"2019-11-18","paper":"/paper/multi-temporal-recurrent-neural-networks-for","paper_url":"https://arxiv.org/abs/1911.07410v1","paper_title":"Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training","code":"https://github.com/Dong1P/MTRNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"DBCPeNet","metrics":{"PSNR":"31.10","SSIM":"0.945"},"uses_additional_data":true,"paper_date":"2020-05-21","paper":"/paper/dark-and-bright-channel-prior-embedded","paper_url":"https://ieeexplore.ieee.org/document/9097949","paper_title":"Dark and Bright Channel Prior Embedded Network for Dynamic Scene Deblurring","code":"https://github.com/csjcai/DBCPeNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"DBGAN","metrics":{"PSNR":"31.10","SSIM":"0.9424"},"uses_additional_data":true,"paper_date":"2020-04-04","paper":"/paper/deblurring-by-realistic-blurring","paper_url":"https://arxiv.org/abs/2004.01860v2","paper_title":"Deblurring by Realistic Blurring","code":"https://github.com/HDCVLab/Deblurring-by-Realistic-Blurring","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"ESTRNN","metrics":{"PSNR":"31.07","SSIM":"0.9023"},"uses_additional_data":true,"paper_date":"2021-06-30","paper":"/paper/efficient-spatio-temporal-recurrent-neural-1","paper_url":"https://arxiv.org/abs/2106.16028v2","paper_title":"Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network","code":"https://github.com/zzh-tech/ESTRNN","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"IR-SDE","metrics":{"FID":"6.32","LPIPS":"0.064","PSNR":"30.7","SSIM":"0.901"},"uses_additional_data":false,"paper_date":"2023-01-27","paper":"/paper/image-restoration-with-mean-reverting","paper_url":"https://arxiv.org/abs/2301.11699v3","paper_title":"Image Restoration with Mean-Reverting Stochastic Differential Equations","code":"https://github.com/algolzw/image-restoration-sde","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"Blurred-Image-to-Video","metrics":{"PSNR":"30.58","SSIM":"0.941"},"uses_additional_data":true,"paper_date":"2018-04-09","paper":"/paper/bringing-alive-blurred-moments","paper_url":"http://arxiv.org/abs/1804.02913v2","paper_title":"Bringing Alive Blurred Moments","code":"https://github.com/anshulbshah/Blurred-Image-to-Video","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"DeepDeblur-PyTorch","metrics":{"PSNR":"30.12","Params (M)":"11.72","SSIM":"0.9021"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":49,"model":"DeblurGAN-v2","metrics":{"PSNR":"29.55","Params (M)":"5.08","SSIM":"0.925"},"uses_additional_data":true,"paper_date":"2019-08-10","paper":"/paper/deblurgan-v2-deblurring-orders-of-magnitude","paper_url":"https://arxiv.org/abs/1908.03826v1","paper_title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","code":"https://github.com/kritiksoman/GIMP-ML","n_code_links":6,"syntology":null},{"rank_in_archive_order":50,"model":"Nah et al","metrics":{"PSNR":"29.08","SSIM":"0.9135"},"uses_additional_data":true,"paper_date":"2016-12-07","paper":"/paper/deep-multi-scale-convolutional-neural-network","paper_url":"http://arxiv.org/abs/1612.02177v2","paper_title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","code":"https://github.com/SeungjunNah/DeepDeblur-PyTorch","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":51,"model":"STFAN","metrics":{"PSNR":"28.59","SSIM":"0.861"},"uses_additional_data":true,"paper_date":"2019-04-28","paper":"/paper/spatio-temporal-filter-adaptive-network-for","paper_url":"https://arxiv.org/abs/1904.12257v2","paper_title":"Spatio-Temporal Filter Adaptive Network for Video Deblurring","code":"https://github.com/sczhou/STFAN","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":52,"model":"DeblurGANv2-MobileNet","metrics":{"PSNR":"28.17"},"uses_additional_data":true,"paper_date":"2019-08-10","paper":"/paper/deblurgan-v2-deblurring-orders-of-magnitude","paper_url":"https://arxiv.org/abs/1908.03826v1","paper_title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","code":"https://github.com/kritiksoman/GIMP-ML","n_code_links":6,"syntology":null},{"rank_in_archive_order":53,"model":"DeblurGANv2-MobileNet-DSC","metrics":{"PSNR":"28.03","SSIM":"0.922"},"uses_additional_data":true,"paper_date":"2019-08-10","paper":"/paper/deblurgan-v2-deblurring-orders-of-magnitude","paper_url":"https://arxiv.org/abs/1908.03826v1","paper_title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","code":"https://github.com/kritiksoman/GIMP-ML","n_code_links":6,"syntology":null},{"rank_in_archive_order":54,"model":"BANet","metrics":{"SSIM":"0.957"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/banet-blur-aware-attention-networks-for","paper_url":"https://arxiv.org/abs/2101.07518v4","paper_title":"BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring","code":"https://github.com/pp00704831/banet","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"SRN","metrics":{"Params (M)":"8.06","SSIM":"0.9342"},"uses_additional_data":true,"paper_date":"2018-02-06","paper":"/paper/scale-recurrent-network-for-deep-image","paper_url":"http://arxiv.org/abs/1802.01770v1","paper_title":"Scale-recurrent Network for Deep Image Deblurring","code":"https://github.com/jiangsutx/SRN-Deblur","n_code_links":4,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":17,"rows_with_any_sample_ran":16,"distinct_papers_with_graph_line":17,"distinct_papers_with_any_sample_ran":16,"samples_over_distinct_papers":{"n_ran":163,"n_unverified":86,"n_samples":249,"n_pointer_only_licence":129,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":163,"n_unverified":86,"n_samples":249,"n_pointer_only_licence":129,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}