{"url":"/sota/image-super-resolution-on-ixi","task":{"name":"Image Super-Resolution","url":"/task/image-super-resolution","note":null},"dataset":{"name":"IXI","url":"/dataset/ixi-dataset"},"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 2x T2w","PSNR 4x T2w","SSIM 4x T2w","SSIM for 2x T2w"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"PSNR 2x T2w":"higher","PSNR 4x T2w":"higher","SSIM 4x T2w":"higher","SSIM for 2x T2w":"higher"}},"counts":{"rows":9,"rows_with_code":7,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"EDSR+MMHCA","metrics":{"PSNR 2x T2w":"40.43","PSNR 4x T2w":"32.70","SSIM 4x T2w":"0.9469","SSIM for 2x T2w":"0.9877"},"uses_additional_data":false,"paper_date":"2022-04-08","paper":"/paper/multimodal-multi-head-convolutional-attention","paper_url":"https://arxiv.org/abs/2204.04218v3","paper_title":"Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution","code":"https://github.com/lilygeorgescu/mhca","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SERAN","metrics":{"PSNR 2x T2w":"40.30","PSNR 4x T2w":"32.62","SSIM 4x T2w":"0.9472","SSIM for 2x T2w":"0.9874"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/mr-image-super-resolution-with-squeeze-and","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Zhang_MR_Image_Super-Resolution_With_Squeeze_and_Excitation_Reasoning_Attention_Network_CVPR_2021_paper.html","paper_title":"MR Image Super-Resolution With Squeeze and Excitation Reasoning Attention Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"CSN","metrics":{"PSNR 2x T2w":"39.71","PSNR 4x T2w":"32.05","SSIM 4x T2w":"0.9413","SSIM for 2x T2w":"0.9863"},"uses_additional_data":false,"paper_date":"2018-10-15","paper":"/paper/channel-splitting-network-for-single-mr-image","paper_url":"https://arxiv.org/abs/1810.06453v3","paper_title":"Channel Splitting Network for Single MR Image Super-Resolution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"IDN","metrics":{"PSNR 2x T2w":"39.09","PSNR 4x T2w":"31.37","SSIM 4x T2w":"0.9312","SSIM for 2x T2w":"0.9846"},"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":5,"model":"RDN","metrics":{"PSNR 2x T2w":"38.75","PSNR 4x T2w":"31.45","SSIM 4x T2w":"0.9324","SSIM for 2x T2w":"0.9838"},"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":6,"model":"CNN-IL","metrics":{"PSNR 2x T2w":"38.67","PSNR 4x T2w":"30.57","SSIM 4x T2w":"0.9210","SSIM for 2x T2w":"0.9837"},"uses_additional_data":false,"paper_date":"2020-01-05","paper":"/paper/convolutional-neural-networks-with-3","paper_url":"https://arxiv.org/abs/2001.01330v4","paper_title":"Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans","code":"https://github.com/lilygeorgescu/3d-super-res-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"VDSR","metrics":{"PSNR 2x T2w":"38.65","PSNR 4x T2w":"30.79","SSIM 4x T2w":"0.9240","SSIM for 2x T2w":"0.9836"},"uses_additional_data":false,"paper_date":"2015-11-14","paper":"/paper/accurate-image-super-resolution-using-very","paper_url":"http://arxiv.org/abs/1511.04587v2","paper_title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","code":"https://github.com/Lornatang/VDSR-PyTorch","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SRCNN","metrics":{"PSNR 2x T2w":"37.32","PSNR 4x T2w":"29.69","SSIM 4x T2w":"0.9052","SSIM for 2x T2w":"0.9796"},"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":9,"model":"T2Net","metrics":{"PSNR 2x T2w":"29.38","PSNR 4x T2w":"28.66","SSIM 4x T2w":"0.8500","SSIM for 2x T2w":"0.8720"},"uses_additional_data":false,"paper_date":"2021-06-12","paper":"/paper/task-transformer-network-for-joint-mri","paper_url":"https://arxiv.org/abs/2106.06742v3","paper_title":"Task Transformer Network for Joint MRI Reconstruction and Super-Resolution","code":"https://github.com/chunmeifeng/T2Net","n_code_links":1,"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":3,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":14,"n_unverified":43,"n_samples":57,"n_pointer_only_licence":8,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":43,"n_samples":57,"n_pointer_only_licence":8,"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"}}}