{"url":"/dataset/set5","name":"Set5","full_name":null,"description_markdown":"The **Set5** dataset is a dataset consisting of 5 images (“baby”, “bird”, “butterfly”, “head”, “woman”) commonly used for testing performance of Image Super-Resolution models.\r\nImage Source: [http://people.rennes.inria.fr/Aline.Roumy/results/SR_BMVC12.html](http://people.rennes.inria.fr/Aline.Roumy/results/SR_BMVC12.html)","description_withheld":null,"homepage":"http://people.rennes.inria.fr/Aline.Roumy/results/SR_BMVC12.html","introduced_date":"2012-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding","first_author":null,"url":"https://doi.org/10.5244/C.26.135"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Super-Resolution","url":"/task/image-super-resolution","datasets_with_task":"/datasets/task/image-super-resolution"},{"name":"Blind Super-Resolution","url":"/task/blind-super-resolution","datasets_with_task":"/datasets/task/blind-super-resolution"},{"name":"Image Rescaling","url":"/task/image-rescaling","datasets_with_task":"/datasets/task/image-rescaling"},{"name":"Compressive Sensing","url":"/task/compressive-sensing","datasets_with_task":"/datasets/task/compressive-sensing"}],"languages":[],"variants":["Set5 - 4x upscaling","Set5-2x","Set5 - 3x upscaling","Set5 - 2x upscaling","Set5 - 8x upscaling","Set5"],"data_loaders":[{"repo":"https://github.com/eugenesiow/super-image-data","url":"https://github.com/eugenesiow/super-image-data","frameworks":["pytorch"]}],"num_papers_in_archive":444,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset_variant":"Set5 - 2x upscaling","rows":41,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DRCT-L","paper":"/paper/drct-saving-image-super-resolution-away-from","metrics":{"PSNR":"39.14","SSIM":"0.9658"},"code_links":[{"title":"ming053l/drct","url":"https://github.com/ming053l/drct"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset_variant":"Set5 - 3x upscaling","rows":32,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HMA†","paper":"/paper/hmanet-hybrid-multi-axis-aggregation-network","metrics":{"PSNR":"35.35","SSIM":"0.9347"},"code_links":[{"title":"korouuuuu/hma","url":"https://github.com/korouuuuu/hma"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-super-resolution-on-set5-4x-upscaling","task":"Image Super-Resolution","dataset_variant":"Set5 - 4x upscaling","rows":12,"metrics":["PSNR","SSIM","MOS"],"first_row_in_archive_order":{"model":"HMA†","paper":"/paper/hmanet-hybrid-multi-axis-aggregation-network","metrics":{"PSNR":"33.38","SSIM":"0.9089"},"code_links":[{"title":"korouuuuu/hma","url":"https://github.com/korouuuuu/hma"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-super-resolution-on-set5-8x-upscaling","task":"Image Super-Resolution","dataset_variant":"Set5 - 8x upscaling","rows":8,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"MFSRCNN","paper":null,"metrics":{"PSNR":"29.03","SSIM":"0.8299"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/blind-super-resolution-on-set5-2x-upscaling","task":"Blind Super-Resolution","dataset_variant":"Set5 - 2x upscaling","rows":3,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DCLS","paper":"/paper/deep-constrained-least-squares-for-blind","metrics":{"PSNR":"37.63","SSIM":"0.9554"},"code_links":[{"title":"megvii-research/dcls-sr","url":"https://github.com/megvii-research/dcls-sr"},{"title":"algolzw/dcls","url":"https://github.com/algolzw/dcls"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/blind-super-resolution-on-set5-4x-upscaling","task":"Blind Super-Resolution","dataset_variant":"Set5 - 4x upscaling","rows":3,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DCLS","paper":"/paper/deep-constrained-least-squares-for-blind","metrics":{"PSNR":"32.12","SSIM":"0.889"},"code_links":[{"title":"megvii-research/dcls-sr","url":"https://github.com/megvii-research/dcls-sr"},{"title":"algolzw/dcls","url":"https://github.com/algolzw/dcls"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/blind-super-resolution-on-set5-3x-upscaling","task":"Blind Super-Resolution","dataset_variant":"Set5 - 3x upscaling","rows":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DCLS","paper":"/paper/deep-constrained-least-squares-for-blind","metrics":{"PSNR":"34.21","SSIM":"0.9218"},"code_links":[{"title":"megvii-research/dcls-sr","url":"https://github.com/megvii-research/dcls-sr"},{"title":"algolzw/dcls","url":"https://github.com/algolzw/dcls"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-rescaling-on-set5-2x","task":"Image Rescaling","dataset_variant":"Set5-2x","rows":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"T-IRN","paper":"/paper/plug-and-play-tri-branch-invertible-block-for","metrics":{"PSNR":"44.86","SSIM":"0.9883"},"code_links":[{"title":"jingwei-bao/t-invblocks","url":"https://github.com/jingwei-bao/t-invblocks"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/compressive-sensing-on-set5","task":"Compressive Sensing","dataset_variant":"Set5","rows":1,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"LapCSNet","paper":"/paper/an-efficient-deep-convolutional-laplacian","metrics":{"Average PSNR":"improving about 0.2-0.3dB"},"code_links":[{"title":"WenxueCui/LapCSNet","url":"https://github.com/WenxueCui/LapCSNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mair-a-locality-and-continuity-preserving","title":"MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration","date":"2024-12-28","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/plug-and-play-tri-branch-invertible-block-for","title":"Plug-and-Play Tri-Branch Invertible Block for Image Rescaling","date":"2024-12-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-information-flow-for-generalized","title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","date":"2024-11-27","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/ml-craist-multi-scale-low-high-frequency","title":"ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer","date":"2024-08-19","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/channel-partitioned-windowed-attention-and","title":"Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution","date":"2024-07-23","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/hmanet-hybrid-multi-axis-aggregation-network","title":"HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution","date":"2024-05-08","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/drct-saving-image-super-resolution-away-from","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","date":"2024-03-31","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-framework-for-real-time-object-detection","title":"Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy","date":"2023-03-16","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/feature-based-adaptive-contrastive","title":"Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution","date":"2022-11-29","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/swinfir-revisiting-the-swinir-with-fast","title":"SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution","date":"2022-08-24","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/one-size-fits-all-hypernetwork-for-tunable","title":"Hypernetwork-Based Adaptive Image Restoration","date":"2022-06-13","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/activating-more-pixels-in-image-super","title":"Activating More Pixels in Image Super-Resolution Transformer","date":"2022-05-09","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/deep-constrained-least-squares-for-blind","title":"Deep Constrained Least Squares for Blind Image Super-Resolution","date":"2022-02-15","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/on-efficient-transformer-and-image-pre","title":"On Efficient Transformer-Based Image Pre-training for Low-Level Vision","date":"2021-12-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/local-texture-estimator-for-implicit","title":"Local Texture Estimator for Implicit Representation Function","date":"2021-11-17","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unfolding-the-alternating-optimization-for","title":"Unfolding the Alternating Optimization for Blind Super Resolution","date":"2020-10-06","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":5,"samples_unverified":0,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cascade-convolutional-neural-network-for","title":"Cascade Convolutional Neural Network for Image Super-Resolution","date":"2020-08-24","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/single-image-super-resolution-via-a-holistic","title":"Single Image Super-Resolution via a Holistic Attention Network","date":"2020-08-20","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/sub-pixel-back-projection-network-for","title":"Sub-Pixel Back-Projection Network For Lightweight Single Image Super-Resolution","date":"2020-08-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/progressive-multi-scale-residual-network-for","title":"Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution","date":"2020-07-19","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/image-super-resolution-with-cross-scale-non","title":"Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining","date":"2020-06-02","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/invertible-image-rescaling","title":"Invertible Image Rescaling","date":"2020-05-12","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":3,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-restoration-using-deep-regulated","title":"Image Restoration Using Deep Regulated Convolutional Networks","date":"2019-10-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/image-super-resolution-via-attention-based","title":"Image Super-Resolution via Attention based Back Projection Networks","date":"2019-10-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lightweight-image-super-resolution-with-1","title":"Lightweight Image Super-Resolution with Information Multi-distillation Network","date":"2019-09-26","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lcscnet-linear-compressing-based-skip","title":"LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution","date":"2019-09-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/densely-residual-laplacian-super-resolution","title":"Densely Residual Laplacian Super-Resolution","date":"2019-06-28","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hierarchical-back-projection-network-for","title":"Hierarchical Back Projection Network for Image Super-Resolution","date":"2019-06-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/modulating-image-restoration-with-continual","title":"Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers","date":"2019-04-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/blind-super-resolution-with-iterative-kernel","title":"Blind Super-Resolution With Iterative Kernel Correction","date":"2019-04-06","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-back-projection-networks-for-single","title":"Deep Back-Projection Networks for Single Image Super-resolution","date":"2019-04-04","rows_on_this_dataset":2,"code_links":7,"syntology":null},{"paper":"/paper/deepred-deep-image-prior-powered-by-red","title":"DeepRED: Deep Image Prior Powered by RED","date":"2019-03-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/feedback-network-for-image-super-resolution","title":"Feedback Network for Image Super-Resolution","date":"2019-03-23","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lightweight-feature-fusion-network-for-single","title":"Lightweight Feature Fusion Network for Single Image Super-Resolution","date":"2019-02-15","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/fast-accurate-and-lightweight-super","title":"Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search","date":"2019-01-22","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-nearest-neighbors-networks","title":"Neural Nearest Neighbors Networks","date":"2018-10-30","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/multi-level-wavelet-cnn-for-image-restoration","title":"Multi-level Wavelet-CNN for Image Restoration","date":"2018-05-18","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/an-efficient-deep-convolutional-laplacian","title":"An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios","date":"2018-04-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fast-accurate-and-lightweight-super-1","title":"Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network","date":"2018-03-23","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-and-accurate-image-super-resolution-by","title":"Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network","date":"2017-07-18","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/enhanced-deep-residual-networks-for-single","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","date":"2017-07-10","rows_on_this_dataset":1,"code_links":45,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-deep-cnn-denoiser-prior-for-image","title":"Learning Deep CNN Denoiser Prior for Image Restoration","date":"2017-04-11","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/photo-realistic-single-image-super-resolution","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","date":"2016-09-15","rows_on_this_dataset":1,"code_links":140,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":72,"samples_ran":16,"samples_unverified":56,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/beyond-a-gaussian-denoiser-residual-learning","title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","date":"2016-08-13","rows_on_this_dataset":2,"code_links":22,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-restoration-using-convolutional-auto","title":"Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections","date":"2016-06-29","rows_on_this_dataset":2,"code_links":17,"syntology":null},{"paper":"/paper/deeply-recursive-convolutional-network-for","title":"Deeply-Recursive Convolutional Network for Image Super-Resolution","date":"2015-11-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/accurate-image-super-resolution-using-very","title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","date":"2015-11-14","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-super-resolution-using-deep","title":"Image Super-Resolution Using Deep Convolutional Networks","date":"2014-12-31","rows_on_this_dataset":1,"code_links":60,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":27,"samples_ran":7,"samples_unverified":20,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":18,"samples_harvested":185,"samples_ran":56,"samples_unverified":129,"pointer_only_for_licence":31,"papers_with_no_sample_that_ran":4,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}