{"url":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":{"name":"Image Super-Resolution","url":"/task/image-super-resolution","note":null},"dataset":{"name":"BSD100 - 4x upscaling","url":"/dataset/bsd"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Image Super-Resolution** is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.","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","MOS","LPIPS","DISTS"],"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","MOS":null,"LPIPS":null,"DISTS":null}},"counts":{"rows":71,"rows_with_code":66,"rows_with_paper_page":71,"rows_dated":71,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"DRCT-L","metrics":{"PSNR":"28.16","SSIM":"0.7577"},"uses_additional_data":false,"paper_date":"2024-03-31","paper":"/paper/drct-saving-image-super-resolution-away-from","paper_url":"https://arxiv.org/abs/2404.00722v5","paper_title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","code":"https://github.com/ming053l/drct","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"Hi-IR-L","metrics":{"PSNR":"28.13","SSIM":"0.7622"},"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":3,"model":"HMA†","metrics":{"PSNR":"28.13","SSIM":"0.7562"},"uses_additional_data":true,"paper_date":"2024-05-08","paper":"/paper/hmanet-hybrid-multi-axis-aggregation-network","paper_url":"https://arxiv.org/abs/2405.05001v1","paper_title":"HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution","code":"https://github.com/korouuuuu/hma","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"HAT-L","metrics":{"PSNR":"28.09","SSIM":"0.7551"},"uses_additional_data":false,"paper_date":"2022-05-09","paper":"/paper/activating-more-pixels-in-image-super","paper_url":"https://arxiv.org/abs/2205.04437v3","paper_title":"Activating More Pixels in Image Super-Resolution Transformer","code":"https://github.com/xpixelgroup/hat","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"HAT_FIR","metrics":{"PSNR":"28.07"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/swinfir-revisiting-the-swinir-with-fast","paper_url":"https://arxiv.org/abs/2208.11247v3","paper_title":"SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution","code":"https://github.com/Zdafeng/SwinFIR","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"DRCT","metrics":{"PSNR":"28.06","SSIM":"0.7533"},"uses_additional_data":false,"paper_date":"2024-03-31","paper":"/paper/drct-saving-image-super-resolution-away-from","paper_url":"https://arxiv.org/abs/2404.00722v5","paper_title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","code":"https://github.com/ming053l/drct","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":7,"model":"CPAT+","metrics":{"PSNR":"28.06","SSIM":"0.7532"},"uses_additional_data":false,"paper_date":"2024-07-23","paper":"/paper/channel-partitioned-windowed-attention-and","paper_url":"https://arxiv.org/abs/2407.16232v2","paper_title":"Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"HAT","metrics":{"PSNR":"28.05","SSIM":"0.7534"},"uses_additional_data":false,"paper_date":"2022-05-09","paper":"/paper/activating-more-pixels-in-image-super","paper_url":"https://arxiv.org/abs/2205.04437v3","paper_title":"Activating More Pixels in Image Super-Resolution Transformer","code":"https://github.com/xpixelgroup/hat","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"CPAT","metrics":{"PSNR":"28.04","SSIM":"0.7527"},"uses_additional_data":false,"paper_date":"2024-07-23","paper":"/paper/channel-partitioned-windowed-attention-and","paper_url":"https://arxiv.org/abs/2407.16232v2","paper_title":"Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"SwinFIR","metrics":{"PSNR":"28.03","SSIM":"0.7520"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/swinfir-revisiting-the-swinir-with-fast","paper_url":"https://arxiv.org/abs/2208.11247v3","paper_title":"SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution","code":"https://github.com/Zdafeng/SwinFIR","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"WaveMixSR-V2","metrics":{"PSNR":"27.87","SSIM":"0.764"},"uses_additional_data":false,"paper_date":"2024-09-16","paper":"/paper/wavemixsr-v2-enhancing-super-resolution-with","paper_url":"https://arxiv.org/abs/2409.10582v3","paper_title":"WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency","code":"https://github.com/pranavphoenix/WaveMixSR","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"DRLN+","metrics":{"PSNR":"27.87","SSIM":"0.7453"},"uses_additional_data":false,"paper_date":"2019-06-28","paper":"/paper/densely-residual-laplacian-super-resolution","paper_url":"https://arxiv.org/abs/1906.12021v2","paper_title":"Densely Residual Laplacian Super-Resolution","code":"https://github.com/saeed-anwar/DRLN","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"SAN","metrics":{"PSNR":"27.86","SSIM":"0.7457"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/second-order-attention-network-for-single","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Dai_Second-Order_Attention_Network_for_Single_Image_Super-Resolution_CVPR_2019_paper.html","paper_title":"Second-Order Attention Network for Single Image Super-Resolution","code":"https://github.com/daitao/SAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"LTE","metrics":{"PSNR":"27.86"},"uses_additional_data":false,"paper_date":"2021-11-17","paper":"/paper/local-texture-estimator-for-implicit","paper_url":"https://arxiv.org/abs/2111.08918v6","paper_title":"Local Texture Estimator for Implicit Representation Function","code":"https://github.com/jaewon-lee-b/lte","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"SRGAN + Residual-in-Residual Dense Block","metrics":{"PSNR":"27.85","SSIM":"0.7455"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/esrgan-enhanced-super-resolution-generative","paper_url":"http://arxiv.org/abs/1809.00219v2","paper_title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","code":"https://github.com/eriklindernoren/PyTorch-GAN","n_code_links":46,"syntology":{"n_ran":12,"n_unverified":32,"n_samples":44,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"HAN+","metrics":{"PSNR":"27.85","SSIM":"0.7454"},"uses_additional_data":false,"paper_date":"2020-08-20","paper":"/paper/single-image-super-resolution-via-a-holistic","paper_url":"https://arxiv.org/abs/2008.08767v1","paper_title":"Single Image Super-Resolution via a Holistic Attention Network","code":"https://github.com/wwlCape/HAN","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"RFN","metrics":{"PSNR":"27.83"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/progressive-perception-oriented-network-for","paper_url":"https://arxiv.org/abs/1907.10399v2","paper_title":"Progressive Perception-Oriented Network for Single Image Super-Resolution","code":"https://github.com/Zheng222/PPON","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"ABPN","metrics":{"PSNR":"27.82","SSIM":"0.743"},"uses_additional_data":false,"paper_date":"2019-10-10","paper":"/paper/image-super-resolution-via-attention-based","paper_url":"https://arxiv.org/abs/1910.04476v1","paper_title":"Image Super-Resolution via Attention based Back Projection Networks","code":"https://github.com/Holmes-Alan/ABPN","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"CSNLN","metrics":{"PSNR":"27.8","SSIM":"0.7439"},"uses_additional_data":false,"paper_date":"2020-06-02","paper":"/paper/image-super-resolution-with-cross-scale-non","paper_url":"https://arxiv.org/abs/2006.01424v1","paper_title":"Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining","code":"https://github.com/SHI-Labs/Cross-Scale-Non-Local-Attention","n_code_links":3,"syntology":null},{"rank_in_archive_order":20,"model":"ProSR","metrics":{"PSNR":"27.79"},"uses_additional_data":false,"paper_date":"2018-04-09","paper":"/paper/a-fully-progressive-approach-to-single-image","paper_url":"http://arxiv.org/abs/1804.02900v2","paper_title":"A Fully Progressive Approach to Single-Image Super-Resolution","code":"https://github.com/fperazzi/proSR","n_code_links":6,"syntology":null},{"rank_in_archive_order":21,"model":"RCAN","metrics":{"PSNR":"27.77","SSIM":"0.7436"},"uses_additional_data":false,"paper_date":"2018-07-08","paper":"/paper/image-super-resolution-using-very-deep","paper_url":"http://arxiv.org/abs/1807.02758v2","paper_title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","code":"https://github.com/yulunzhang/RCAN","n_code_links":20,"syntology":{"n_ran":14,"n_unverified":8,"n_samples":22,"n_pointer_only_licence":3}},{"rank_in_archive_order":22,"model":"HBPN","metrics":{"PSNR":"27.77","SSIM":"0.743"},"uses_additional_data":false,"paper_date":"2019-06-17","paper":"/paper/hierarchical-back-projection-network-for","paper_url":"https://arxiv.org/abs/1906.06874v2","paper_title":"Hierarchical Back Projection Network for Image Super-Resolution","code":"https://github.com/Holmes-Alan/HBPN","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"SwinOIR","metrics":{"PSNR":"27.76","SSIM":"0.7441"},"uses_additional_data":false,"paper_date":"2023-03-16","paper":"/paper/a-framework-for-real-time-object-detection","paper_url":"https://arxiv.org/abs/2303.09190v2","paper_title":"Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy","code":"https://github.com/rubbbbbbbbby/swinoir","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"GMFN","metrics":{"PSNR":"27.74","SSIM":"0.7421"},"uses_additional_data":false,"paper_date":"2019-07-09","paper":"/paper/gated-multiple-feedback-network-for-image","paper_url":"https://arxiv.org/abs/1907.04253v2","paper_title":"Gated Multiple Feedback Network for Image Super-Resolution","code":"https://github.com/liqilei/GMFN","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"RDN","metrics":{"PSNR":"27.72","SSIM":"0.7419"},"uses_additional_data":false,"paper_date":"2018-02-24","paper":"/paper/residual-dense-network-for-image-super","paper_url":"http://arxiv.org/abs/1802.08797v2","paper_title":"Residual Dense Network for Image Super-Resolution","code":"https://github.com/idealo/image-super-resolution","n_code_links":16,"syntology":{"n_ran":7,"n_unverified":17,"n_samples":24,"n_pointer_only_licence":1}},{"rank_in_archive_order":26,"model":"SRFBN","metrics":{"PSNR":"27.72","SSIM":"0.7409"},"uses_additional_data":false,"paper_date":"2019-03-23","paper":"/paper/feedback-network-for-image-super-resolution","paper_url":"https://arxiv.org/abs/1903.09814v2","paper_title":"Feedback Network for Image Super-Resolution","code":"https://github.com/Paper99/SRFBN_CVPR19","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"D-DBPN","metrics":{"PSNR":"27.72","SSIM":"0.740"},"uses_additional_data":false,"paper_date":"2018-03-07","paper":"/paper/deep-back-projection-networks-for-super","paper_url":"http://arxiv.org/abs/1803.02735v1","paper_title":"Deep Back-Projection Networks For Super-Resolution","code":"https://github.com/sanghyun-son/EDSR-PyTorch","n_code_links":16,"syntology":{"n_ran":8,"n_unverified":6,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"EDSR","metrics":{"PSNR":"27.71","SSIM":"0.7420"},"uses_additional_data":false,"paper_date":"2017-07-10","paper":"/paper/enhanced-deep-residual-networks-for-single","paper_url":"http://arxiv.org/abs/1707.02921v1","paper_title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","code":"https://github.com/sanghyun-son/EDSR-PyTorch","n_code_links":45,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":2}},{"rank_in_archive_order":29,"model":"Manifold Simplification","metrics":{"PSNR":"27.66","SSIM":"0.7380"},"uses_additional_data":false,"paper_date":"2016-11-19","paper":"/paper/beyond-deep-residual-learning-for-image","paper_url":"http://arxiv.org/abs/1611.06345v4","paper_title":"Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification","code":"https://github.com/iorism/CNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"MWCNN","metrics":{"PSNR":"27.62","SSIM":"0.7355"},"uses_additional_data":false,"paper_date":"2018-05-18","paper":"/paper/multi-level-wavelet-cnn-for-image-restoration","paper_url":"http://arxiv.org/abs/1805.07071v2","paper_title":"Multi-level Wavelet-CNN for Image Restoration","code":"https://github.com/lpj0/MWCNN","n_code_links":5,"syntology":null},{"rank_in_archive_order":31,"model":"SRResNet","metrics":{"MOS":"2.29","PSNR":"27.58","SSIM":"0.762"},"uses_additional_data":false,"paper_date":"2016-09-15","paper":"/paper/photo-realistic-single-image-super-resolution","paper_url":"http://arxiv.org/abs/1609.04802v5","paper_title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","code":"https://github.com/tensorflow/models/tree/master/research/gan","n_code_links":140,"syntology":{"n_ran":21,"n_unverified":51,"n_samples":72,"n_pointer_only_licence":11}},{"rank_in_archive_order":32,"model":"CARN","metrics":{"PSNR":"27.58","SSIM":"0.7349"},"uses_additional_data":false,"paper_date":"2018-03-23","paper":"/paper/fast-accurate-and-lightweight-super-1","paper_url":"http://arxiv.org/abs/1803.08664v5","paper_title":"Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network","code":"https://github.com/nmhkahn/CARN-pytorch","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"BSRN","metrics":{"PSNR":"27.57","SSIM":"0.7353"},"uses_additional_data":false,"paper_date":"2018-11-30","paper":"/paper/lightweight-and-efficient-image-super","paper_url":"http://arxiv.org/abs/1811.12546v1","paper_title":"Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network","code":"https://github.com/idearibosome/tf-bsrn-sr","n_code_links":2,"syntology":null},{"rank_in_archive_order":34,"model":"SRRAM","metrics":{"PSNR":"27.56","SSIM":"0.7350"},"uses_additional_data":false,"paper_date":"2018-11-29","paper":"/paper/ram-residual-attention-module-for-single","paper_url":"https://arxiv.org/abs/1811.12043v2","paper_title":"MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution","code":"https://github.com/S-aiueo32/SRRAM","n_code_links":3,"syntology":null},{"rank_in_archive_order":35,"model":"IMDN","metrics":{"PSNR":"27.56"},"uses_additional_data":false,"paper_date":"2019-09-26","paper":"/paper/lightweight-image-super-resolution-with-1","paper_url":"https://arxiv.org/abs/1909.11856v1","paper_title":"Lightweight Image Super-Resolution with Information Multi-distillation Network","code":"https://github.com/Zheng222/IMDN","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"ENet-E","metrics":{"PSNR":"27.50","SSIM":"0.7326"},"uses_additional_data":false,"paper_date":"2016-12-23","paper":"/paper/enhancenet-single-image-super-resolution","paper_url":"http://arxiv.org/abs/1612.07919v2","paper_title":"EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis","code":"https://github.com/msmsajjadi/EnhanceNet-Code","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":3}},{"rank_in_archive_order":37,"model":"SRMDNF","metrics":{"PSNR":"27.49","SSIM":"0.734"},"uses_additional_data":false,"paper_date":"2017-12-17","paper":"/paper/learning-a-single-convolutional-super","paper_url":"http://arxiv.org/abs/1712.06116v2","paper_title":"Learning a Single Convolutional Super-Resolution Network for Multiple Degradations","code":"https://github.com/cszn/SRMD","n_code_links":1,"syntology":null},{"rank_in_archive_order":38,"model":"NLRN","metrics":{"PSNR":"27.48","SSIM":"0.7306"},"uses_additional_data":false,"paper_date":"2018-06-07","paper":"/paper/non-local-recurrent-network-for-image","paper_url":"http://arxiv.org/abs/1806.02919v2","paper_title":"Non-Local Recurrent Network for Image Restoration","code":"https://github.com/Ding-Liu/NLRN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"RL-CSC","metrics":{"PSNR":"27.44","SSIM":"0.7302"},"uses_additional_data":false,"paper_date":"2018-12-31","paper":"/paper/image-super-resolution-via-rl-csc-when","paper_url":"http://arxiv.org/abs/1812.11950v1","paper_title":"Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":40,"model":"SESR","metrics":{"PSNR":"27.42","SSIM":"0.737"},"uses_additional_data":false,"paper_date":"2018-01-31","paper":"/paper/sesr-single-image-super-resolution-with","paper_url":"http://arxiv.org/abs/1801.10319v1","paper_title":"SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks","code":"https://github.com/opteroncx/SESR","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"LFFN-S","metrics":{"PSNR":"27.42"},"uses_additional_data":false,"paper_date":"2019-02-15","paper":"/paper/lightweight-feature-fusion-network-for-single","paper_url":"http://arxiv.org/abs/1902.05694v2","paper_title":"Lightweight Feature Fusion Network for Single Image Super-Resolution","code":"https://github.com/qibao77/LFFN-master","n_code_links":2,"syntology":null},{"rank_in_archive_order":42,"model":"IDN","metrics":{"PSNR":"27.41","SSIM":"0.7297"},"uses_additional_data":false,"paper_date":"2018-03-26","paper":"/paper/fast-and-accurate-single-image-super","paper_url":"http://arxiv.org/abs/1803.09454v1","paper_title":"Fast and Accurate Single Image Super-Resolution via Information Distillation Network","code":"https://github.com/Zheng222/IDN-Caffe","n_code_links":2,"syntology":null},{"rank_in_archive_order":43,"model":"RED30","metrics":{"PSNR":"27.40","SSIM":"0.7290"},"uses_additional_data":false,"paper_date":"2016-03-30","paper":"/paper/image-restoration-using-very-deep","paper_url":"http://arxiv.org/abs/1603.09056v2","paper_title":"Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections","code":"https://github.com/yjn870/REDNet-pytorch","n_code_links":3,"syntology":null},{"rank_in_archive_order":44,"model":"RED30","metrics":{"PSNR":"27.4","SSIM":"0.729"},"uses_additional_data":false,"paper_date":"2016-06-29","paper":"/paper/image-restoration-using-convolutional-auto","paper_url":"http://arxiv.org/abs/1606.08921v3","paper_title":"Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections","code":"https://github.com/titu1994/Image-Super-Resolution","n_code_links":17,"syntology":null},{"rank_in_archive_order":45,"model":"MemNet","metrics":{"PSNR":"27.40","SSIM":"0.7281"},"uses_additional_data":false,"paper_date":"2017-08-07","paper":"/paper/memnet-a-persistent-memory-network-for-image","paper_url":"http://arxiv.org/abs/1708.02209v1","paper_title":"MemNet: A Persistent Memory Network for Image Restoration","code":"https://github.com/tyshiwo/MemNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":46,"model":"LapSRN","metrics":{"PSNR":"27.32","SSIM":"0.728"},"uses_additional_data":false,"paper_date":"2017-04-12","paper":"/paper/deep-laplacian-pyramid-networks-for-fast-and","paper_url":"http://arxiv.org/abs/1704.03915v2","paper_title":"Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution","code":"https://github.com/nhatsmrt/superres","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"DnCNN-3","metrics":{"PSNR":"27.29","SSIM":"0.7253"},"uses_additional_data":false,"paper_date":"2016-08-13","paper":"/paper/beyond-a-gaussian-denoiser-residual-learning","paper_url":"http://arxiv.org/abs/1608.03981v1","paper_title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","code":"https://github.com/cszn/DnCNN","n_code_links":22,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":48,"model":"DSRN","metrics":{"PSNR":"27.25","SSIM":"0.724"},"uses_additional_data":false,"paper_date":"2018-05-07","paper":"/paper/image-super-resolution-via-dual-state","paper_url":"http://arxiv.org/abs/1805.02704v1","paper_title":"Image Super-Resolution via Dual-State Recurrent Networks","code":"https://github.com/WeiHan3/dsrn","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"DRCN","metrics":{"MOS":"2.12","PSNR":"27.21","SSIM":"0.7493"},"uses_additional_data":false,"paper_date":"2015-11-14","paper":"/paper/deeply-recursive-convolutional-network-for","paper_url":"http://arxiv.org/abs/1511.04491v2","paper_title":"Deeply-Recursive Convolutional Network for Image Super-Resolution","code":"https://github.com/jiny2001/deeply-recursive-cnn-tf","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"RC-Net","metrics":{"PSNR":"27.21"},"uses_additional_data":false,"paper_date":"2019-10-19","paper":"/paper/image-restoration-using-deep-regulated","paper_url":"https://arxiv.org/abs/1910.08853v1","paper_title":"Image Restoration Using Deep Regulated Convolutional Networks","code":"https://github.com/cswin/RC-Nets","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"IA","metrics":{"PSNR":"27.16"},"uses_additional_data":false,"paper_date":"2015-11-06","paper":"/paper/seven-ways-to-improve-example-based-single","paper_url":"http://arxiv.org/abs/1511.02228v1","paper_title":"Seven ways to improve example-based single image super resolution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":52,"model":"ZSSR","metrics":{"PSNR":"27.12","SSIM":"0.7211"},"uses_additional_data":false,"paper_date":"2017-12-17","paper":"/paper/zero-shot-super-resolution-using-deep","paper_url":"http://arxiv.org/abs/1712.06087v1","paper_title":"\"Zero-Shot\" Super-Resolution using Deep Internal Learning","code":"https://github.com/assafshocher/ZSSR","n_code_links":7,"syntology":null},{"rank_in_archive_order":53,"model":"ESPCN","metrics":{"MOS":"2.01","PSNR":"27.02","SSIM":"0.7442"},"uses_additional_data":false,"paper_date":"2016-09-16","paper":"/paper/real-time-single-image-and-video-super","paper_url":"http://arxiv.org/abs/1609.05158v2","paper_title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","code":"https://github.com/alexjc/neural-enhance","n_code_links":47,"syntology":{"n_ran":4,"n_unverified":16,"n_samples":20,"n_pointer_only_licence":1}},{"rank_in_archive_order":54,"model":"FAFR*","metrics":{"PSNR":"26.91"},"uses_additional_data":false,"paper_date":"2017-12-14","paper":"/paper/image-super-resolution-via-feature-augmented","paper_url":"http://arxiv.org/abs/1712.05248v1","paper_title":"Image Super-resolution via Feature-augmented Random Forest","code":"https://github.com/HarleyHK/FARF","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"SRCNN","metrics":{"PSNR":"26.9","SSIM":"0.7101"},"uses_additional_data":false,"paper_date":"2014-12-31","paper":"/paper/image-super-resolution-using-deep","paper_url":"http://arxiv.org/abs/1501.00092v3","paper_title":"Image Super-Resolution Using Deep Convolutional Networks","code":"https://github.com/nagadomi/waifu2x","n_code_links":60,"syntology":{"n_ran":7,"n_unverified":20,"n_samples":27,"n_pointer_only_licence":7}},{"rank_in_archive_order":56,"model":"JMPF+","metrics":{"PSNR":"26.87"},"uses_additional_data":false,"paper_date":"2017-08-30","paper":"/paper/joint-maximum-purity-forest-with-application","paper_url":"http://arxiv.org/abs/1708.09200v1","paper_title":"Joint Maximum Purity Forest with Application to Image Super-Resolution","code":"https://github.com/HarleyHK/JMPF","n_code_links":1,"syntology":null},{"rank_in_archive_order":57,"model":"4PP-EUSR","metrics":{"PSNR":"26.5707","SSIM":"0.6900"},"uses_additional_data":false,"paper_date":"2018-09-13","paper":"/paper/deep-learning-based-image-super-resolution","paper_url":"http://arxiv.org/abs/1809.04789v2","paper_title":"Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality","code":"https://github.com/idearibosome/tf-perceptual-eusr","n_code_links":1,"syntology":null},{"rank_in_archive_order":58,"model":"FxSR-PD t=0.0","metrics":{"LPIPS":"0.3433","PSNR":"26.38","SSIM":"0.738"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/flexible-style-image-super-resolution-using","paper_url":"https://arxiv.org/abs/2201.04898v3","paper_title":"Flexible Style Image Super-Resolution using Conditional Objective","code":"https://github.com/seungho-snu/fxsr","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"bicubic","metrics":{"MOS":"1.47","PSNR":"25.94","SSIM":"0.6935"},"uses_additional_data":false,"paper_date":"2016-09-15","paper":"/paper/photo-realistic-single-image-super-resolution","paper_url":"http://arxiv.org/abs/1609.04802v5","paper_title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","code":"https://github.com/tensorflow/models/tree/master/research/gan","n_code_links":140,"syntology":{"n_ran":21,"n_unverified":51,"n_samples":72,"n_pointer_only_licence":11}},{"rank_in_archive_order":60,"model":"AESOP","metrics":{"DISTS":"0.1072","LPIPS":"0.1385","PSNR":"25.93","SSIM":"0.6813"},"uses_additional_data":false,"paper_date":"2024-11-28","paper":"/paper/auto-encoded-supervision-for-perceptual-image","paper_url":"https://arxiv.org/abs/2412.00124v2","paper_title":"Auto-Encoded Supervision for Perceptual Image Super-Resolution","code":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":61,"model":"SPSR","metrics":{"LPIPS":"0.1611","PSNR":"25.505","SSIM":"0.6576"},"uses_additional_data":false,"paper_date":"2020-03-29","paper":"/paper/structure-preserving-super-resolution-with","paper_url":"https://arxiv.org/abs/2003.13081v1","paper_title":"Structure-Preserving Super Resolution with Gradient Guidance","code":"https://github.com/Maclory/SPSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":62,"model":"SFT-GAN","metrics":{"PSNR":"25.33","SSIM":"0.651"},"uses_additional_data":false,"paper_date":"2018-04-09","paper":"/paper/recovering-realistic-texture-in-image-super","paper_url":"http://arxiv.org/abs/1804.02815v1","paper_title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","code":"https://github.com/xinntao/BasicSR","n_code_links":4,"syntology":null},{"rank_in_archive_order":63,"model":"SRGAN","metrics":{"MOS":"3.56","PSNR":"25.16","SSIM":"0.6688"},"uses_additional_data":false,"paper_date":"2016-09-15","paper":"/paper/photo-realistic-single-image-super-resolution","paper_url":"http://arxiv.org/abs/1609.04802v5","paper_title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","code":"https://github.com/tensorflow/models/tree/master/research/gan","n_code_links":140,"syntology":{"n_ran":21,"n_unverified":51,"n_samples":72,"n_pointer_only_licence":11}},{"rank_in_archive_order":64,"model":"nearest neighbors","metrics":{"MOS":"1.11","PSNR":"25.02","SSIM":"0.6606"},"uses_additional_data":false,"paper_date":"2016-09-15","paper":"/paper/photo-realistic-single-image-super-resolution","paper_url":"http://arxiv.org/abs/1609.04802v5","paper_title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","code":"https://github.com/tensorflow/models/tree/master/research/gan","n_code_links":140,"syntology":{"n_ran":21,"n_unverified":51,"n_samples":72,"n_pointer_only_licence":11}},{"rank_in_archive_order":65,"model":"Perceptual Loss","metrics":{"PSNR":"24.95","SSIM":"0.6317"},"uses_additional_data":false,"paper_date":"2016-03-27","paper":"/paper/perceptual-losses-for-real-time-style","paper_url":"http://arxiv.org/abs/1603.08155v1","paper_title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","code":"https://github.com/alexjc/neural-enhance","n_code_links":80,"syntology":{"n_ran":15,"n_unverified":31,"n_samples":46,"n_pointer_only_licence":5}},{"rank_in_archive_order":66,"model":"SROOE","metrics":{"LPIPS":"0.1500","PSNR":"24.87","SSIM":"0.6869"},"uses_additional_data":false,"paper_date":"2022-11-24","paper":"/paper/perception-oriented-single-image-super","paper_url":"https://arxiv.org/abs/2211.13676v3","paper_title":"Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation","code":"https://github.com/seungho-snu/SROOE","n_code_links":1,"syntology":null},{"rank_in_archive_order":67,"model":"FxSR-PD t=0.8","metrics":{"LPIPS":"0.1572","PSNR":"24.77","SSIM":"0.6817"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/flexible-style-image-super-resolution-using","paper_url":"https://arxiv.org/abs/2201.04898v3","paper_title":"Flexible Style Image Super-Resolution using Conditional Objective","code":"https://github.com/seungho-snu/fxsr","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"Edge-informed SR","metrics":{"PSNR":"24.25","SSIM":"0.851"},"uses_additional_data":false,"paper_date":"2019-09-11","paper":"/paper/edge-informed-single-image-super-resolution","paper_url":"https://arxiv.org/abs/1909.05305v1","paper_title":"Edge-Informed Single Image Super-Resolution","code":"https://github.com/knazeri/edge-informed-sisr","n_code_links":2,"syntology":null},{"rank_in_archive_order":69,"model":"WaveMixSR","metrics":{"SSIM":"0.7605"},"uses_additional_data":false,"paper_date":"2023-07-01","paper":"/paper/wavemixsr-a-resource-efficient-neural-network","paper_url":"https://arxiv.org/abs/2307.00430v1","paper_title":"WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution","code":"https://github.com/pranavphoenix/WaveMixSR","n_code_links":1,"syntology":null},{"rank_in_archive_order":70,"model":"S-RFN","metrics":{"SSIM":"0.7515"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/progressive-perception-oriented-network-for","paper_url":"https://arxiv.org/abs/1907.10399v2","paper_title":"Progressive Perception-Oriented Network for Single Image Super-Resolution","code":"https://github.com/Zheng222/PPON","n_code_links":1,"syntology":null},{"rank_in_archive_order":71,"model":"Config (e)","metrics":{"LPIPS":"0.1209"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/one-to-many-approach-for-improving-super","paper_url":"https://arxiv.org/abs/2106.10437v4","paper_title":"One-to-many Approach for Improving Super-Resolution","code":"https://github.com/krenerd/ultimate-sr","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":24,"rows_with_any_sample_ran":20,"distinct_papers_with_graph_line":20,"distinct_papers_with_any_sample_ran":16,"samples_over_distinct_papers":{"n_ran":112,"n_unverified":212,"n_samples":324,"n_pointer_only_licence":42,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":179,"n_unverified":365,"n_samples":544,"n_pointer_only_licence":78,"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"}}}