{"url":"/task/super-resolution","name":"Super-Resolution","slug":"super-resolution","description_markdown":"**Super-Resolution** is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Credit: [MemNet](https://github.com/tyshiwo/MemNet) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3874,"papers_with_code":1627,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":22,"subtasks":7,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/super-resolution-on-hradis-et-al-dataset","slug":"super-resolution-on-hradis-et-al-dataset","dataset":"hradis et al dataset","dataset_url":null,"rows_in_archive":1,"metrics":["Average PSNR","SSIM"],"first_row_in_archive_order":{"model":"super-resolution","paper_title":"SDT-DCSCN for Simultaneous Super-Resolution and Deblurring of Text Images","paper_url":"/paper/sdt-dcscn-for-simultaneous-super-resolution","paper_date":"2022-01-15","arxiv_id":"2201.05865","code_links":[{"title":"halaneji/SDT-DCSCN","url":"https://github.com/halaneji/SDT-DCSCN"}],"syntology":null}}],"datasets":[{"url":"/dataset/drealsr","name":"DRealSR","full_name":"Diverse Real-world image Super-Resolution","num_papers_in_archive":36},{"url":"/dataset/textzoom","name":"TextZoom","full_name":null,"num_papers_in_archive":28},{"url":"/dataset/msu-sr-qa-dataset","name":"MSU SR-QA Dataset","full_name":"MSU Super-Resolution Quality Assessment Dataset","num_papers_in_archive":26},{"url":"/dataset/realsrset","name":"RealSRSet","full_name":"","num_papers_in_archive":20},{"url":"/dataset/holopix50k","name":"Holopix50k","full_name":"","num_papers_in_archive":12},{"url":"/dataset/cats","name":"CATS","full_name":"Color and Thermal Stereo Benchmark","num_papers_in_archive":11},{"url":"/dataset/qmul-survface","name":"QMUL-SurvFace","full_name":"","num_papers_in_archive":10},{"url":"/dataset/ost300","name":"OST300","full_name":"OST300","num_papers_in_archive":7},{"url":"/dataset/proba-v","name":"PROBA-V","full_name":"PROBA-V Super-Resolution dataset","num_papers_in_archive":7},{"url":"/dataset/stanford-light-field","name":"Stanford Light Field","full_name":"","num_papers_in_archive":7},{"url":"/dataset/alsat-2b","name":"Alsat-2B","full_name":"","num_papers_in_archive":2},{"url":"/dataset/davanet","name":"DAVANet","full_name":"","num_papers_in_archive":2},{"url":"/dataset/stereomsi","name":"StereoMSI","full_name":"","num_papers_in_archive":2},{"url":"/dataset/digital","name":"DIGITal","full_name":"Digitally Generated Numerals","num_papers_in_archive":1},{"url":"/dataset/inria-dlfd","name":"INRIA DLFD","full_name":"INRIA Dense Light Field","num_papers_in_archive":1},{"url":"/dataset/pixelshift200","name":"PixelShift200","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sickle","name":"SICKLE","full_name":"Satellite Imagery for Cropping annotated with Keyparameter LabEls","num_papers_in_archive":1},{"url":"/dataset/sr-caco-2","name":"SR-CACO-2","full_name":"SR-CACO-2","num_papers_in_archive":1},{"url":"/dataset/testimages","name":"TESTIMAGES","full_name":"","num_papers_in_archive":1},{"url":"/dataset/kid-f","name":"KID-F","full_name":"K-pop Idol Dataset - Female","num_papers_in_archive":0},{"url":"/dataset/mus2","name":"MuS2","full_name":"A Real-World Benchmark for Sentinel-2 Multi-Image Super-Resolution","num_papers_in_archive":0},{"url":"/dataset/pinet","name":"PINet","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-object-super-resolution","name":"3D Object Super-Resolution"},{"url":"/task/depth-map-super-resolution","name":"Depth Map Super-Resolution"},{"url":"/task/image-rescaling","name":"Image Rescaling"},{"url":"/task/image-super-resolution","name":"Image Super-Resolution"},{"url":"/task/reference-based-super-resolution","name":"Reference-based Super-Resolution"},{"url":"/task/reference-based-video-super-resolution","name":"Reference-based Video Super-Resolution"},{"url":"/task/video-super-resolution","name":"Video Super-Resolution"}],"parent_tasks":[{"url":"/task/3d-object-super-resolution","name":"3D Object Super-Resolution"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":1627,"tagged_in_all":3874,"items":[{"url":"/paper/generative-adversarial-networks","title":"Generative Adversarial Networks","date":"2014-06-10","arxiv_id":"1406.2661","repositories_listed":189,"syntology":{"n":55,"n_ran":23,"n_unverified":32,"n_pointer_only":18}},{"url":"/paper/photo-realistic-single-image-super-resolution","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","date":"2016-09-15","arxiv_id":"1609.04802","repositories_listed":140,"syntology":{"n":72,"n_ran":16,"n_unverified":56,"n_pointer_only":11}},{"url":"/paper/perceptual-losses-for-real-time-style","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","date":"2016-03-27","arxiv_id":"1603.08155","repositories_listed":80,"syntology":{"n":46,"n_ran":13,"n_unverified":33,"n_pointer_only":5}},{"url":"/paper/image-super-resolution-using-deep","title":"Image Super-Resolution Using Deep Convolutional Networks","date":"2014-12-31","arxiv_id":"1501.00092","repositories_listed":60,"syntology":{"n":27,"n_ran":7,"n_unverified":20,"n_pointer_only":7}},{"url":"/paper/singan-learning-a-generative-model-from-a","title":"SinGAN: Learning a Generative Model from a Single Natural Image","date":"2019-05-02","arxiv_id":"1905.01164","repositories_listed":47,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/real-time-single-image-and-video-super","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","date":"2016-09-16","arxiv_id":"1609.05158","repositories_listed":47,"syntology":{"n":20,"n_ran":4,"n_unverified":16,"n_pointer_only":1}},{"url":"/paper/esrgan-enhanced-super-resolution-generative","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","date":"2018-09-01","arxiv_id":"1809.00219","repositories_listed":46,"syntology":{"n":44,"n_ran":8,"n_unverified":36,"n_pointer_only":0}},{"url":"/paper/enhanced-deep-residual-networks-for-single","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","date":"2017-07-10","arxiv_id":"1707.02921","repositories_listed":45,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/high-resolution-image-synthesis-with-latent","title":"High-Resolution Image Synthesis with Latent Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10752","repositories_listed":41,"syntology":{"n":28,"n_ran":19,"n_unverified":9,"n_pointer_only":5}},{"url":"/paper/beyond-a-gaussian-denoiser-residual-learning","title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","date":"2016-08-13","arxiv_id":"1608.03981","repositories_listed":22,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/image-super-resolution-using-very-deep","title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","date":"2018-07-08","arxiv_id":"1807.02758","repositories_listed":20,"syntology":{"n":22,"n_ran":10,"n_unverified":12,"n_pointer_only":3}},{"url":"/paper/fourier-neural-operator-for-parametric-1","title":"Fourier Neural Operator for Parametric Partial Differential Equations","date":"2020-10-18","arxiv_id":"2010.08895","repositories_listed":19,"syntology":{"n":33,"n_ran":18,"n_unverified":15,"n_pointer_only":9}},{"url":"/paper/image-restoration-using-convolutional-auto","title":"Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections","date":"2016-06-29","arxiv_id":"1606.08921","repositories_listed":17,"syntology":null},{"url":"/paper/pulse-self-supervised-photo-upsampling-via","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","date":"2020-03-08","arxiv_id":"2003.03808","repositories_listed":16,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/deep-back-projection-networks-for-super","title":"Deep Back-Projection Networks For Super-Resolution","date":"2018-03-07","arxiv_id":"1803.02735","repositories_listed":16,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/residual-dense-network-for-image-super","title":"Residual Dense Network for Image Super-Resolution","date":"2018-02-24","arxiv_id":"1802.08797","repositories_listed":16,"syntology":{"n":24,"n_ran":7,"n_unverified":17,"n_pointer_only":1}},{"url":"/paper/accelerating-the-super-resolution","title":"Accelerating the Super-Resolution Convolutional Neural Network","date":"2016-08-01","arxiv_id":"1608.00367","repositories_listed":16,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/consistency-models","title":"Consistency Models","date":"2023-03-02","arxiv_id":"2303.01469","repositories_listed":15,"syntology":{"n":57,"n_ran":28,"n_unverified":29,"n_pointer_only":8}},{"url":"/paper/deep-image-prior","title":"Deep Image Prior","date":"2017-11-29","arxiv_id":"1711.10925","repositories_listed":14,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/temporally-coherent-gans-for-video-super","title":"Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation","date":"2018-11-23","arxiv_id":"1811.09393","repositories_listed":13,"syntology":{"n":25,"n_ran":2,"n_unverified":23,"n_pointer_only":0}},{"url":"/paper/sampling-generative-networks","title":"Sampling Generative Networks","date":"2016-09-14","arxiv_id":"1609.04468","repositories_listed":13,"syntology":{"n":15,"n_ran":1,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/learning-enriched-features-for-real-image","title":"Learning Enriched Features for Real Image Restoration and Enhancement","date":"2020-03-15","arxiv_id":"2003.06792","repositories_listed":12,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":3}},{"url":"/paper/wide-activation-for-efficient-and-accurate","title":"Wide Activation for Efficient and Accurate Image Super-Resolution","date":"2018-08-27","arxiv_id":"1808.08718","repositories_listed":12,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":2}},{"url":"/paper/cgans-with-projection-discriminator","title":"cGANs with Projection Discriminator","date":"2018-02-15","arxiv_id":"1802.05637","repositories_listed":12,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/invertible-image-rescaling","title":"Invertible Image Rescaling","date":"2020-05-12","arxiv_id":"2005.05650","repositories_listed":11,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/edvr-video-restoration-with-enhanced","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","date":"2019-05-07","arxiv_id":"1905.02716","repositories_listed":11,"syntology":{"n":19,"n_ran":5,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/swinir-image-restoration-using-swin","title":"SwinIR: Image Restoration Using Swin Transformer","date":"2021-08-23","arxiv_id":"2108.10257","repositories_listed":9,"syntology":{"n":45,"n_ran":30,"n_unverified":15,"n_pointer_only":5}},{"url":"/paper/towards-compact-single-image-super-resolution","title":"Towards Compact Single Image Super-Resolution via Contrastive Self-distillation","date":"2021-05-25","arxiv_id":"2105.11683","repositories_listed":9,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/real-esrgan-training-real-world-blind-super","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","date":"2021-07-22","arxiv_id":"2107.10833","repositories_listed":8,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/srflow-learning-the-super-resolution-space","title":"SRFlow: Learning the Super-Resolution Space with Normalizing Flow","date":"2020-06-25","arxiv_id":"2006.14200","repositories_listed":8,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}}],"syntology_records":29,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}