{"url":"/task/image-super-resolution","name":"Image Super-Resolution","slug":"image-super-resolution","description_markdown":"**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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1589,"papers_with_code":783,"benchmarks":69,"benchmark_tables_in_archive":69,"benchmark_tables_shown":69,"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":43,"subtasks":5,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","slug":"image-super-resolution-on-set14-4x-upscaling","dataset":"Set14 - 4x upscaling","dataset_url":"/dataset/set14","rows_in_archive":104,"metrics":["PSNR","SSIM","MOS","LPIPS","DISTS"],"first_row_in_archive_order":{"model":"DRCT-L","paper_title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","paper_url":"/paper/drct-saving-image-super-resolution-away-from","paper_date":"2024-03-31","arxiv_id":"2404.00722","code_links":[{"title":"ming053l/drct","url":"https://github.com/ming053l/drct"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","slug":"image-super-resolution-on-bsd100-4x-upscaling","dataset":"BSD100 - 4x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":71,"metrics":["PSNR","SSIM","MOS","LPIPS","DISTS"],"first_row_in_archive_order":{"model":"DRCT-L","paper_title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","paper_url":"/paper/drct-saving-image-super-resolution-away-from","paper_date":"2024-03-31","arxiv_id":"2404.00722","code_links":[{"title":"ming053l/drct","url":"https://github.com/ming053l/drct"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","slug":"image-super-resolution-on-urban100-4x","dataset":"Urban100 - 4x upscaling","dataset_url":"/dataset/urban100","rows_in_archive":65,"metrics":["PSNR","SSIM","LPIPS","Perceptual Index","DISTS","LR-PSNR"],"first_row_in_archive_order":{"model":"Hi-IR-L","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","slug":"image-super-resolution-on-manga109-4x","dataset":"Manga109 - 4x upscaling","dataset_url":"/dataset/manga109","rows_in_archive":50,"metrics":["SSIM","PSNR","DISTS","LPIPS","LR-PSNR"],"first_row_in_archive_order":{"model":"Hi-IR-L","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","slug":"image-super-resolution-on-set5-2x-upscaling","dataset":"Set5 - 2x upscaling","dataset_url":"/dataset/set5","rows_in_archive":41,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DRCT-L","paper_title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","paper_url":"/paper/drct-saving-image-super-resolution-away-from","paper_date":"2024-03-31","arxiv_id":"2404.00722","code_links":[{"title":"ming053l/drct","url":"https://github.com/ming053l/drct"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","slug":"image-super-resolution-on-set14-2x-upscaling","dataset":"Set14 - 2x upscaling","dataset_url":"/dataset/set14","rows_in_archive":35,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DRCT-L","paper_title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","paper_url":"/paper/drct-saving-image-super-resolution-away-from","paper_date":"2024-03-31","arxiv_id":"2404.00722","code_links":[{"title":"ming053l/drct","url":"https://github.com/ming053l/drct"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","slug":"image-super-resolution-on-set5-3x-upscaling","dataset":"Set5 - 3x upscaling","dataset_url":"/dataset/set5","rows_in_archive":32,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HMA†","paper_title":"HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution","paper_url":"/paper/hmanet-hybrid-multi-axis-aggregation-network","paper_date":"2024-05-08","arxiv_id":"2405.05001","code_links":[{"title":"korouuuuu/hma","url":"https://github.com/korouuuuu/hma"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsd100-2x-upscaling","slug":"image-super-resolution-on-bsd100-2x-upscaling","dataset":"BSD100 - 2x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":30,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"WaveMixSR-V2","paper_title":"WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency","paper_url":"/paper/wavemixsr-v2-enhancing-super-resolution-with","paper_date":"2024-09-16","arxiv_id":"2409.10582","code_links":[{"title":"pranavphoenix/WaveMixSR","url":"https://github.com/pranavphoenix/WaveMixSR"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-urban100-2x","slug":"image-super-resolution-on-urban100-2x","dataset":"Urban100 - 2x upscaling","dataset_url":"/dataset/urban100","rows_in_archive":29,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HMA†","paper_title":"HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution","paper_url":"/paper/hmanet-hybrid-multi-axis-aggregation-network","paper_date":"2024-05-08","arxiv_id":"2405.05001","code_links":[{"title":"korouuuuu/hma","url":"https://github.com/korouuuuu/hma"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-set14-3x-upscaling","slug":"image-super-resolution-on-set14-3x-upscaling","dataset":"Set14 - 3x upscaling","dataset_url":"/dataset/set14","rows_in_archive":24,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR-L","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-urban100-3x","slug":"image-super-resolution-on-urban100-3x","dataset":"Urban100 - 3x upscaling","dataset_url":"/dataset/urban100","rows_in_archive":22,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR-L","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsd100-3x-upscaling","slug":"image-super-resolution-on-bsd100-3x-upscaling","dataset":"BSD100 - 3x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":21,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR-L","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-div2k-val-4x","slug":"image-super-resolution-on-div2k-val-4x","dataset":"DIV2K val - 4x upscaling","dataset_url":"/dataset/div2k","rows_in_archive":21,"metrics":["LPIPS","PSNR","SSIM","DISTS","LRPSNR","NIQE"],"first_row_in_archive_order":{"model":"AESOP","paper_title":"Auto-Encoded Supervision for Perceptual Image Super-Resolution","paper_url":"/paper/auto-encoded-supervision-for-perceptual-image","paper_date":"2024-11-28","arxiv_id":"2412.00124","code_links":[{"title":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}}},{"leaderboard":"/sota/image-super-resolution-on-manga109-2x","slug":"image-super-resolution-on-manga109-2x","dataset":"Manga109 - 2x upscaling","dataset_url":"/dataset/manga109","rows_in_archive":21,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR-L","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-manga109-3x","slug":"image-super-resolution-on-manga109-3x","dataset":"Manga109 - 3x upscaling","dataset_url":"/dataset/manga109","rows_in_archive":17,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR-L","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-set5-4x-upscaling","slug":"image-super-resolution-on-set5-4x-upscaling","dataset":"Set5 - 4x upscaling","dataset_url":"/dataset/set5","rows_in_archive":12,"metrics":["PSNR","SSIM","MOS"],"first_row_in_archive_order":{"model":"HMA†","paper_title":"HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution","paper_url":"/paper/hmanet-hybrid-multi-axis-aggregation-network","paper_date":"2024-05-08","arxiv_id":"2405.05001","code_links":[{"title":"korouuuuu/hma","url":"https://github.com/korouuuuu/hma"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-ffhq-256-x-256-4x","slug":"image-super-resolution-on-ffhq-256-x-256-4x","dataset":"FFHQ 256 x 256 - 4x upscaling","dataset_url":"/dataset/ffhq","rows_in_archive":11,"metrics":["FID","MS-SSIM","PSNR","SSIM"],"first_row_in_archive_order":{"model":"HiFaceGAN","paper_title":"HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment","paper_url":"/paper/hifacegan-face-renovation-via-collaborative","paper_date":"2020-05-11","arxiv_id":"2005.05005","code_links":[{"title":"Lotayou/Face-Renovation","url":"https://github.com/Lotayou/Face-Renovation"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGAN"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HiFaceGAN"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGAN"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGAN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-ffhq-1024-x-1024-4x","slug":"image-super-resolution-on-ffhq-1024-x-1024-4x","dataset":"FFHQ 1024 x 1024 - 4x upscaling","dataset_url":"/dataset/ffhq","rows_in_archive":9,"metrics":["FID","MS-SSIM","PSNR","SSIM"],"first_row_in_archive_order":{"model":"HiFaceGAN","paper_title":"HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment","paper_url":"/paper/hifacegan-face-renovation-via-collaborative","paper_date":"2020-05-11","arxiv_id":"2005.05005","code_links":[{"title":"Lotayou/Face-Renovation","url":"https://github.com/Lotayou/Face-Renovation"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGAN"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HiFaceGAN"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGAN"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGAN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-ixi","slug":"image-super-resolution-on-ixi","dataset":"IXI","dataset_url":"/dataset/ixi-dataset","rows_in_archive":9,"metrics":["PSNR 2x T2w","PSNR 4x T2w","SSIM 4x T2w","SSIM for 2x T2w"],"first_row_in_archive_order":{"model":"EDSR+MMHCA","paper_title":"Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution","paper_url":"/paper/multimodal-multi-head-convolutional-attention","paper_date":"2022-04-08","arxiv_id":"2204.04218","code_links":[{"title":"lilygeorgescu/mhca","url":"https://github.com/lilygeorgescu/mhca"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-ffhq-512-x-512-4x","slug":"image-super-resolution-on-ffhq-512-x-512-4x","dataset":"FFHQ 512 x 512 - 4x upscaling","dataset_url":"/dataset/ffhq","rows_in_archive":8,"metrics":["PSNR","SSIM","MS-SSIM","LLE","FED","FID","LPIPS","NIQE"],"first_row_in_archive_order":{"model":"HiFaceGAN","paper_title":"HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment","paper_url":"/paper/hifacegan-face-renovation-via-collaborative","paper_date":"2020-05-11","arxiv_id":"2005.05005","code_links":[{"title":"Lotayou/Face-Renovation","url":"https://github.com/Lotayou/Face-Renovation"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGAN"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HiFaceGAN"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGAN"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGAN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-set5-8x-upscaling","slug":"image-super-resolution-on-set5-8x-upscaling","dataset":"Set5 - 8x upscaling","dataset_url":"/dataset/set5","rows_in_archive":8,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"MFSRCNN","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-set14-8x-upscaling","slug":"image-super-resolution-on-set14-8x-upscaling","dataset":"Set14 - 8x upscaling","dataset_url":"/dataset/set14","rows_in_archive":7,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DBPN-RES-MR64-3","paper_title":"Deep Back-Projection Networks for Single Image Super-resolution","paper_url":"/paper/deep-back-projection-networks-for-single","paper_date":"2019-04-04","arxiv_id":"1904.05677","code_links":[{"title":"alterzero/DBPN-Pytorch","url":"https://github.com/alterzero/DBPN-Pytorch"},{"title":"shnhrtkyk/satellite-super-resolution","url":"https://github.com/shnhrtkyk/satellite-super-resolution"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/DBPN"},{"title":"2023-MindSpore-4/Code2","url":"https://github.com/2023-MindSpore-4/Code2/tree/main/DBPN"},{"title":"lyqcom/dbpn","url":"https://github.com/lyqcom/dbpn"},{"title":"lizatish/My_CNN","url":"https://github.com/lizatish/My_CNN"},{"title":"MindSpore-paper-code-3/code8","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/DBPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-vggface2-8x","slug":"image-super-resolution-on-vggface2-8x","dataset":"VggFace2 - 8x upscaling","dataset_url":"/dataset/vggface2-1","rows_in_archive":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Full-GWAInet","paper_title":"Exemplar Guided Face Image Super-Resolution without Facial Landmarks","paper_url":"/paper/exemplar-guided-face-image-super-resolution","paper_date":"2019-06-17","arxiv_id":"1906.07078","code_links":[{"title":"berkdogan2/GWAInet","url":"https://github.com/berkdogan2/GWAInet"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-webface-8x","slug":"image-super-resolution-on-webface-8x","dataset":"WebFace - 8x upscaling","dataset_url":"/dataset/casia-webface","rows_in_archive":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"GFRNet","paper_title":"Learning Warped Guidance for Blind Face Restoration","paper_url":"/paper/learning-warped-guidance-for-blind-face","paper_date":"2018-04-13","arxiv_id":"1804.04829","code_links":[{"title":"csxmli2016/GFRNet","url":"https://github.com/csxmli2016/GFRNet"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsd100-8x-upscaling","slug":"image-super-resolution-on-bsd100-8x-upscaling","dataset":"BSD100 - 8x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":6,"metrics":["PSNR","SSIM","DISTS","LPIPS","LRPSNR","NIQE"],"first_row_in_archive_order":{"model":"DRLN+","paper_title":"Densely Residual Laplacian Super-Resolution","paper_url":"/paper/densely-residual-laplacian-super-resolution","paper_date":"2019-06-28","arxiv_id":"1906.12021","code_links":[{"title":"saeed-anwar/DRLN","url":"https://github.com/saeed-anwar/DRLN"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-imagenet","slug":"image-super-resolution-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":6,"metrics":["FID","PSNR","SSIM"],"first_row_in_archive_order":{"model":"DAVI","paper_title":"Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems","paper_url":"/paper/diffusion-prior-based-amortized-variational","paper_date":"2024-07-23","arxiv_id":"2407.16125","code_links":[{"title":"mlvlab/davi","url":"https://github.com/mlvlab/davi"},{"title":"kdhRick2222/Exposure-slot","url":"https://github.com/kdhRick2222/Exposure-slot"}],"syntology":{"n":27,"n_ran":21,"n_unverified":6,"n_pointer_only":5}}},{"leaderboard":"/sota/image-super-resolution-on-celeba","slug":"image-super-resolution-on-celeba","dataset":"CelebA","dataset_url":"/dataset/celeba","rows_in_archive":5,"metrics":["FID","PSNR","SSIM"],"first_row_in_archive_order":{"model":"DDNM","paper_title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","paper_url":"/paper/zero-shot-image-restoration-using-denoising","paper_date":"2022-12-01","arxiv_id":"2212.00490","code_links":[{"title":"wyhuai/ddnm","url":"https://github.com/wyhuai/ddnm"},{"title":"xypeng9903/k-diffusion-inverse-problems","url":"https://github.com/xypeng9903/k-diffusion-inverse-problems"},{"title":"ipc-lab/deepjscc-diffusion","url":"https://github.com/ipc-lab/deepjscc-diffusion"},{"title":"andreamazzitelli/ProjectNN","url":"https://github.com/andreamazzitelli/ProjectNN"}],"syntology":{"n":23,"n_ran":12,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-manga109-8x","slug":"image-super-resolution-on-manga109-8x","dataset":"Manga109 - 8x upscaling","dataset_url":"/dataset/manga109","rows_in_archive":5,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DBPN-RES-MR64-3","paper_title":"Deep Back-Projection Networks for Single Image Super-resolution","paper_url":"/paper/deep-back-projection-networks-for-single","paper_date":"2019-04-04","arxiv_id":"1904.05677","code_links":[{"title":"alterzero/DBPN-Pytorch","url":"https://github.com/alterzero/DBPN-Pytorch"},{"title":"shnhrtkyk/satellite-super-resolution","url":"https://github.com/shnhrtkyk/satellite-super-resolution"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/DBPN"},{"title":"2023-MindSpore-4/Code2","url":"https://github.com/2023-MindSpore-4/Code2/tree/main/DBPN"},{"title":"lyqcom/dbpn","url":"https://github.com/lyqcom/dbpn"},{"title":"lizatish/My_CNN","url":"https://github.com/lizatish/My_CNN"},{"title":"MindSpore-paper-code-3/code8","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/DBPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-urban100-8x","slug":"image-super-resolution-on-urban100-8x","dataset":"Urban100 - 8x upscaling","dataset_url":"/dataset/urban100","rows_in_archive":5,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DRLN+","paper_title":"Densely Residual Laplacian Super-Resolution","paper_url":"/paper/densely-residual-laplacian-super-resolution","paper_date":"2019-06-28","arxiv_id":"1906.12021","code_links":[{"title":"saeed-anwar/DRLN","url":"https://github.com/saeed-anwar/DRLN"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-celeba-hq-128x128","slug":"image-super-resolution-on-celeba-hq-128x128","dataset":"CelebA-HQ 128x128","dataset_url":"/dataset/celeba-hq","rows_in_archive":4,"metrics":["PSNR","SSIM","Consistency"],"first_row_in_archive_order":{"model":"TSRGP","paper_title":"Trustworthy Image Super-Resolution via Generative Pseudoinverse","paper_url":"/paper/trustworthy-image-super-resolution-via","paper_date":"2025-05-18","arxiv_id":"2505.12375","code_links":[{"title":"andreasfloros/trustworthy-super-resolution","url":"https://github.com/andreasfloros/trustworthy-super-resolution"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-div8k-val-16x","slug":"image-super-resolution-on-div8k-val-16x","dataset":"DIV8K val - 16x upscaling","dataset_url":null,"rows_in_archive":3,"metrics":["LPIPS","PSNR","SSIM"],"first_row_in_archive_order":{"model":"Ours w/o cycle-loss","paper_title":"One-to-many Approach for Improving Super-Resolution","paper_url":"/paper/one-to-many-approach-for-improving-super","paper_date":"2021-06-19","arxiv_id":"2106.10437","code_links":[{"title":"krenerd/ultimate-sr","url":"https://github.com/krenerd/ultimate-sr"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-general100-4x","slug":"image-super-resolution-on-general100-4x","dataset":"General100 - 4x upscaling","dataset_url":null,"rows_in_archive":3,"metrics":["LPIPS","DISTS","LRPSNR","NIQE","PSNR","SSIM","LR-PSNR"],"first_row_in_archive_order":{"model":"SROOE","paper_title":"Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation","paper_url":"/paper/perception-oriented-single-image-super","paper_date":"2022-11-24","arxiv_id":"2211.13676","code_links":[{"title":"seungho-snu/SROOE","url":"https://github.com/seungho-snu/SROOE"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-pirm-test","slug":"image-super-resolution-on-pirm-test","dataset":"PIRM-test","dataset_url":"/dataset/pirm","rows_in_archive":3,"metrics":["NIQE"],"first_row_in_archive_order":{"model":"RankSRGAN","paper_title":"RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution","paper_url":"/paper/ranksrgan-generative-adversarial-networks","paper_date":"2019-08-18","arxiv_id":"1908.06382","code_links":[{"title":"xpixelgroup/ranksrgan","url":"https://github.com/xpixelgroup/ranksrgan"},{"title":"WenlongZhang0724/RankSRGAN","url":"https://github.com/WenlongZhang0724/RankSRGAN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-2x-upscaling","slug":"image-super-resolution-on-2x-upscaling","dataset":"2x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["#params (K)","FLOPs(G)"],"first_row_in_archive_order":{"model":"ML-CrAIST","paper_title":"ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer","paper_url":"/paper/ml-craist-multi-scale-low-high-frequency","paper_date":"2024-08-19","arxiv_id":"2408.09940","code_links":[{"title":"alik033/ml-craist","url":"https://github.com/alik033/ml-craist"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-3x-upscaling","slug":"image-super-resolution-on-3x-upscaling","dataset":"3x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["#params (K)","FLOPs(G)"],"first_row_in_archive_order":{"model":"ML-CrAIST","paper_title":"ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer","paper_url":"/paper/ml-craist-multi-scale-low-high-frequency","paper_date":"2024-08-19","arxiv_id":"2408.09940","code_links":[{"title":"alik033/ml-craist","url":"https://github.com/alik033/ml-craist"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-4x-upscaling","slug":"image-super-resolution-on-4x-upscaling","dataset":"4x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["#params (K)","FLOPs(G)"],"first_row_in_archive_order":{"model":"ML-CrAIST","paper_title":"ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer","paper_url":"/paper/ml-craist-multi-scale-low-high-frequency","paper_date":"2024-08-19","arxiv_id":"2408.09940","code_links":[{"title":"alik033/ml-craist","url":"https://github.com/alik033/ml-craist"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-b100-2x-upscaling","slug":"image-super-resolution-on-b100-2x-upscaling","dataset":"B100 - 2x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["SSIM","PSNR"],"first_row_in_archive_order":{"model":"ML-CrAIST","paper_title":"ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer","paper_url":"/paper/ml-craist-multi-scale-low-high-frequency","paper_date":"2024-08-19","arxiv_id":"2408.09940","code_links":[{"title":"alik033/ml-craist","url":"https://github.com/alik033/ml-craist"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-b100-3x-upscaling","slug":"image-super-resolution-on-b100-3x-upscaling","dataset":"B100 - 3x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["SSIM","PSNR"],"first_row_in_archive_order":{"model":"ML-CrAIST","paper_title":"ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer","paper_url":"/paper/ml-craist-multi-scale-low-high-frequency","paper_date":"2024-08-19","arxiv_id":"2408.09940","code_links":[{"title":"alik033/ml-craist","url":"https://github.com/alik033/ml-craist"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-b100-4x-upscaling","slug":"image-super-resolution-on-b100-4x-upscaling","dataset":"B100 - 4x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ML-CrAIST","paper_title":"ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer","paper_url":"/paper/ml-craist-multi-scale-low-high-frequency","paper_date":"2024-08-19","arxiv_id":"2408.09940","code_links":[{"title":"alik033/ml-craist","url":"https://github.com/alik033/ml-craist"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsds100-2x","slug":"image-super-resolution-on-bsds100-2x","dataset":"BSDS100 - 2x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DBPN-RES-MR64-3","paper_title":"Deep Back-Projection Networks for Single Image Super-resolution","paper_url":"/paper/deep-back-projection-networks-for-single","paper_date":"2019-04-04","arxiv_id":"1904.05677","code_links":[{"title":"alterzero/DBPN-Pytorch","url":"https://github.com/alterzero/DBPN-Pytorch"},{"title":"shnhrtkyk/satellite-super-resolution","url":"https://github.com/shnhrtkyk/satellite-super-resolution"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/DBPN"},{"title":"2023-MindSpore-4/Code2","url":"https://github.com/2023-MindSpore-4/Code2/tree/main/DBPN"},{"title":"lyqcom/dbpn","url":"https://github.com/lyqcom/dbpn"},{"title":"lizatish/My_CNN","url":"https://github.com/lizatish/My_CNN"},{"title":"MindSpore-paper-code-3/code8","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/DBPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-cufed5-4x-upscaling","slug":"image-super-resolution-on-cufed5-4x-upscaling","dataset":"CUFED5 - 4x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Extracter-rec","paper_title":"EXTRACTER: Efficient Texture Matching with Attention and Gradient Enhancing for Large Scale Image Super Resolution","paper_url":"/paper/extracter-efficient-texture-matching-with","paper_date":"2023-10-02","arxiv_id":"2310.01379","code_links":[{"title":"esteban-rs/extracter","url":"https://github.com/esteban-rs/extracter"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-div2k-val-8x","slug":"image-super-resolution-on-div2k-val-8x","dataset":"DIV2K val - 8x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["LPIPS","PSNR","SSIM","DISTS","LRPSNR","NIQE"],"first_row_in_archive_order":{"model":"FxSR-PD t=0.8","paper_title":"Flexible Style Image Super-Resolution using Conditional Objective","paper_url":"/paper/flexible-style-image-super-resolution-using","paper_date":"2022-01-13","arxiv_id":"2201.04898","code_links":[{"title":"seungho-snu/fxsr","url":"https://github.com/seungho-snu/fxsr"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-general100-8x","slug":"image-super-resolution-on-general100-8x","dataset":"General100 - 8x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["LPIPS","DISTS","LRPSNR","NIQE","PSNR","SSIM"],"first_row_in_archive_order":{"model":"FxSR-PD t=0.8","paper_title":"Flexible Style Image Super-Resolution using Conditional Objective","paper_url":"/paper/flexible-style-image-super-resolution-using","paper_date":"2022-01-13","arxiv_id":"2201.04898","code_links":[{"title":"seungho-snu/fxsr","url":"https://github.com/seungho-snu/fxsr"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-sun80-4x-upscaling","slug":"image-super-resolution-on-sun80-4x-upscaling","dataset":"Sun80 - 4x upscaling","dataset_url":null,"rows_in_archive":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Extracter-rec","paper_title":"EXTRACTER: Efficient Texture Matching with Attention and Gradient Enhancing for Large Scale Image Super Resolution","paper_url":"/paper/extracter-efficient-texture-matching-with","paper_date":"2023-10-02","arxiv_id":"2310.01379","code_links":[{"title":"esteban-rs/extracter","url":"https://github.com/esteban-rs/extracter"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsd100-16x","slug":"image-super-resolution-on-bsd100-16x","dataset":"BSD100 - 16x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ABPN","paper_title":"Image Super-Resolution via Attention based Back Projection Networks","paper_url":"/paper/image-super-resolution-via-attention-based","paper_date":"2019-10-10","arxiv_id":"1910.04476","code_links":[{"title":"Holmes-Alan/ABPN","url":"https://github.com/Holmes-Alan/ABPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsd200-2x-upscaling","slug":"image-super-resolution-on-bsd200-2x-upscaling","dataset":"BSD200 - 2x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"CSRCNN","paper_title":"Cascade Convolutional Neural Network for Image Super-Resolution","paper_url":"/paper/cascade-convolutional-neural-network-for","paper_date":"2020-08-24","arxiv_id":"2008.10329","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsds100-4x","slug":"image-super-resolution-on-bsds100-4x","dataset":"BSDS100 - 4x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DBPN-RES-MR64-3","paper_title":"Deep Back-Projection Networks for Single Image Super-resolution","paper_url":"/paper/deep-back-projection-networks-for-single","paper_date":"2019-04-04","arxiv_id":"1904.05677","code_links":[{"title":"alterzero/DBPN-Pytorch","url":"https://github.com/alterzero/DBPN-Pytorch"},{"title":"shnhrtkyk/satellite-super-resolution","url":"https://github.com/shnhrtkyk/satellite-super-resolution"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/DBPN"},{"title":"2023-MindSpore-4/Code2","url":"https://github.com/2023-MindSpore-4/Code2/tree/main/DBPN"},{"title":"lyqcom/dbpn","url":"https://github.com/lyqcom/dbpn"},{"title":"lizatish/My_CNN","url":"https://github.com/lizatish/My_CNN"},{"title":"MindSpore-paper-code-3/code8","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/DBPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-bsds100-8x","slug":"image-super-resolution-on-bsds100-8x","dataset":"BSDS100 - 8x upscaling","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"DBPN-RES-MR64-3","paper_title":"Deep Back-Projection Networks for Single Image Super-resolution","paper_url":"/paper/deep-back-projection-networks-for-single","paper_date":"2019-04-04","arxiv_id":"1904.05677","code_links":[{"title":"alterzero/DBPN-Pytorch","url":"https://github.com/alterzero/DBPN-Pytorch"},{"title":"shnhrtkyk/satellite-super-resolution","url":"https://github.com/shnhrtkyk/satellite-super-resolution"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/DBPN"},{"title":"2023-MindSpore-4/Code2","url":"https://github.com/2023-MindSpore-4/Code2/tree/main/DBPN"},{"title":"lyqcom/dbpn","url":"https://github.com/lyqcom/dbpn"},{"title":"lizatish/My_CNN","url":"https://github.com/lizatish/My_CNN"},{"title":"MindSpore-paper-code-3/code8","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/DBPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-celeb-hq-4x","slug":"image-super-resolution-on-celeb-hq-4x","dataset":"Celeb-HQ 4x upscaling","dataset_url":"/dataset/celeba-hq","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Edge-informed SR","paper_title":"Edge-Informed Single Image Super-Resolution","paper_url":"/paper/edge-informed-single-image-super-resolution","paper_date":"2019-09-11","arxiv_id":"1909.05305","code_links":[{"title":"knazeri/edge-informed-sisr","url":"https://github.com/knazeri/edge-informed-sisr"},{"title":"AntonioAlgaida/Edge.SRGAN","url":"https://github.com/AntonioAlgaida/Edge.SRGAN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-chikusei-dataset","slug":"image-super-resolution-on-chikusei-dataset","dataset":"Chikusei Dataset","dataset_url":"/dataset/chikusei-dataset","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"DIP-HyperKite (ours)","paper_title":"Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction","paper_url":"/paper/hyperspectral-pansharpening-based-on-improved","paper_date":"2021-07-06","arxiv_id":"2107.02630","code_links":[{"title":"wgcban/DIP-HyperKite","url":"https://github.com/wgcban/DIP-HyperKite"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-div2k-val-16x","slug":"image-super-resolution-on-div2k-val-16x","dataset":"DIV2K val - 16x upscaling","dataset_url":"/dataset/div2k","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ABPN","paper_title":"Image Super-Resolution via Attention based Back Projection Networks","paper_url":"/paper/image-super-resolution-via-attention-based","paper_date":"2019-10-10","arxiv_id":"1910.04476","code_links":[{"title":"Holmes-Alan/ABPN","url":"https://github.com/Holmes-Alan/ABPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-div8k-test-16x","slug":"image-super-resolution-on-div8k-test-16x","dataset":"DIV8K test - 16x upscaling","dataset_url":null,"rows_in_archive":1,"metrics":["LPIPS","PSNR"],"first_row_in_archive_order":{"model":"RFB-ESRGAN","paper_title":"Perceptual Extreme Super Resolution Network with Receptive Field Block","paper_url":"/paper/perceptual-extreme-super-resolution-network","paper_date":"2020-05-26","arxiv_id":"2005.12597","code_links":[{"title":"Lornatang/RFB_ESRGAN-PyTorch","url":"https://github.com/Lornatang/RFB_ESRGAN-PyTorch"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-epfl-nir-vis","slug":"image-super-resolution-on-epfl-nir-vis","dataset":"EPFL NIR-VIS","dataset_url":null,"rows_in_archive":1,"metrics":["SSIM"],"first_row_in_archive_order":{"model":"RAMS (ours)","paper_title":"Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural Networks","paper_url":"/paper/multi-image-super-resolution-of-remotely","paper_date":"2020-07-06","arxiv_id":"2007.03107","code_links":[{"title":"isaaccorley/torchrs","url":"https://github.com/isaaccorley/torchrs"},{"title":"EscVM/RAMS","url":"https://github.com/EscVM/RAMS"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-general-100-4x","slug":"image-super-resolution-on-general-100-4x","dataset":"General-100 - 4x upscaling","dataset_url":null,"rows_in_archive":1,"metrics":["DISTS","LPIPS","PSNR","SSIM"],"first_row_in_archive_order":{"model":"AESOP","paper_title":"Auto-Encoded Supervision for Perceptual Image Super-Resolution","paper_url":"/paper/auto-encoded-supervision-for-perceptual-image","paper_date":"2024-11-28","arxiv_id":"2412.00124","code_links":[{"title":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}}},{"leaderboard":"/sota/image-super-resolution-on-kitti-2012-2x","slug":"image-super-resolution-on-kitti-2012-2x","dataset":"KITTI 2012 - 2x upscaling","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"PASSRnet","paper_title":"Learning Parallax Attention for Stereo Image Super-Resolution","paper_url":"/paper/learning-parallax-attention-for-stereo-image","paper_date":"2019-03-14","arxiv_id":"1903.05784","code_links":[{"title":"LongguangWang/PASSRnet","url":"https://github.com/LongguangWang/PASSRnet"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-kitti-2012-4x","slug":"image-super-resolution-on-kitti-2012-4x","dataset":"KITTI 2012 - 4x upscaling","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"PASSRnet","paper_title":"Learning Parallax Attention for Stereo Image Super-Resolution","paper_url":"/paper/learning-parallax-attention-for-stereo-image","paper_date":"2019-03-14","arxiv_id":"1903.05784","code_links":[{"title":"LongguangWang/PASSRnet","url":"https://github.com/LongguangWang/PASSRnet"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-kitti-2015-2x","slug":"image-super-resolution-on-kitti-2015-2x","dataset":"KITTI 2015 - 2x upscaling","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"PASSRnet","paper_title":"Learning Parallax Attention for Stereo Image Super-Resolution","paper_url":"/paper/learning-parallax-attention-for-stereo-image","paper_date":"2019-03-14","arxiv_id":"1903.05784","code_links":[{"title":"LongguangWang/PASSRnet","url":"https://github.com/LongguangWang/PASSRnet"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-kitti-2015-4x","slug":"image-super-resolution-on-kitti-2015-4x","dataset":"KITTI 2015 - 4x upscaling","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"PASSRnet","paper_title":"Learning Parallax Attention for Stereo Image Super-Resolution","paper_url":"/paper/learning-parallax-attention-for-stereo-image","paper_date":"2019-03-14","arxiv_id":"1903.05784","code_links":[{"title":"LongguangWang/PASSRnet","url":"https://github.com/LongguangWang/PASSRnet"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-manga109-16x","slug":"image-super-resolution-on-manga109-16x","dataset":"Manga109 - 16x upscaling","dataset_url":"/dataset/manga109","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ABPN","paper_title":"Image Super-Resolution via Attention based Back Projection Networks","paper_url":"/paper/image-super-resolution-via-attention-based","paper_date":"2019-10-10","arxiv_id":"1910.04476","code_links":[{"title":"Holmes-Alan/ABPN","url":"https://github.com/Holmes-Alan/ABPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-middlebury-2x","slug":"image-super-resolution-on-middlebury-2x","dataset":"Middlebury - 2x upscaling","dataset_url":"/dataset/middlebury","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"PASSRnet","paper_title":"Learning Parallax Attention for Stereo Image Super-Resolution","paper_url":"/paper/learning-parallax-attention-for-stereo-image","paper_date":"2019-03-14","arxiv_id":"1903.05784","code_links":[{"title":"LongguangWang/PASSRnet","url":"https://github.com/LongguangWang/PASSRnet"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-middlebury-4x","slug":"image-super-resolution-on-middlebury-4x","dataset":"Middlebury - 4x upscaling","dataset_url":"/dataset/middlebury","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"PASSRnet","paper_title":"Learning Parallax Attention for Stereo Image Super-Resolution","paper_url":"/paper/learning-parallax-attention-for-stereo-image","paper_date":"2019-03-14","arxiv_id":"1903.05784","code_links":[{"title":"LongguangWang/PASSRnet","url":"https://github.com/LongguangWang/PASSRnet"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-set14","slug":"image-super-resolution-on-set14","dataset":"Set14","dataset_url":"/dataset/set14","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ATD","paper_title":"Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary","paper_url":"/paper/transcending-the-limit-of-local-window","paper_date":"2024-01-16","arxiv_id":"2401.08209","code_links":[{"title":"labshuhanggu/adaptive-token-dictionary","url":"https://github.com/labshuhanggu/adaptive-token-dictionary"}],"syntology":{"n":15,"n_ran":11,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-super-resolution-on-set5-5x-upscaling","slug":"image-super-resolution-on-set5-5x-upscaling","dataset":"Set5 - 5x upscaling","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HyperRes","paper_title":"Hypernetwork-Based Adaptive Image Restoration","paper_url":"/paper/one-size-fits-all-hypernetwork-for-tunable","paper_date":"2022-06-13","arxiv_id":"2206.05970","code_links":[{"title":"ifryed/HyperRes","url":"https://github.com/ifryed/HyperRes"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/image-super-resolution-on-set5-6x-upscaling","slug":"image-super-resolution-on-set5-6x-upscaling","dataset":"Set5 - 6x upscaling","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HyperRes","paper_title":"Hypernetwork-Based Adaptive Image Restoration","paper_url":"/paper/one-size-fits-all-hypernetwork-for-tunable","paper_date":"2022-06-13","arxiv_id":"2206.05970","code_links":[{"title":"ifryed/HyperRes","url":"https://github.com/ifryed/HyperRes"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/image-super-resolution-on-shipspotting","slug":"image-super-resolution-on-shipspotting","dataset":"ShipSpotting","dataset_url":"/dataset/shipspotting","rows_in_archive":1,"metrics":["Frechet Inception Distance"],"first_row_in_archive_order":{"model":"StableShip","paper_title":"Ship in Sight: Diffusion Models for Ship-Image Super Resolution","paper_url":"/paper/ship-in-sight-diffusion-models-for-ship-image","paper_date":"2024-03-27","arxiv_id":"2403.18370","code_links":[{"title":"luigisigillo/shipinsight","url":"https://github.com/luigisigillo/shipinsight"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":9}}},{"leaderboard":"/sota/image-super-resolution-on-textzoom","slug":"image-super-resolution-on-textzoom","dataset":"TextZoom","dataset_url":"/dataset/textzoom","rows_in_archive":1,"metrics":["Average Accuracy","ASTER Overall Accuracy","MORAN Overall Accuracy","CRNN Overall Accuracy"],"first_row_in_archive_order":{"model":"NCAP","paper_title":"NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior","paper_url":"/paper/ncap-scene-text-image-super-resolution-with","paper_date":"2025-04-01","arxiv_id":"2504.00410","code_links":[{"title":"THINKWARE-AI/NCAP","url":"https://github.com/THINKWARE-AI/NCAP"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-urban100-16x","slug":"image-super-resolution-on-urban100-16x","dataset":"Urban100 - 16x upscaling","dataset_url":"/dataset/urban100","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ABPN","paper_title":"Image Super-Resolution via Attention based Back Projection Networks","paper_url":"/paper/image-super-resolution-via-attention-based","paper_date":"2019-10-10","arxiv_id":"1910.04476","code_links":[{"title":"Holmes-Alan/ABPN","url":"https://github.com/Holmes-Alan/ABPN"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-usr-248-4x","slug":"image-super-resolution-on-usr-248-4x","dataset":"USR-248 - 4x upscaling","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR","SSIM","UIQM"],"first_row_in_archive_order":{"model":"SRDRM-GAN","paper_title":"Underwater Image Super-Resolution using Deep Residual Multipliers","paper_url":"/paper/underwater-image-super-resolution-using-deep","paper_date":"2019-09-20","arxiv_id":"1909.09437","code_links":[{"title":"TingdiRen/URSCT-SESR","url":"https://github.com/TingdiRen/URSCT-SESR"},{"title":"xahidbuffon/srdrm","url":"https://github.com/xahidbuffon/srdrm"},{"title":"IRVLab/srdrm","url":"https://github.com/IRVLab/srdrm"}],"syntology":null}},{"leaderboard":"/sota/image-super-resolution-on-wlfw","slug":"image-super-resolution-on-wlfw","dataset":"WLFW","dataset_url":null,"rows_in_archive":1,"metrics":["Loss"],"first_row_in_archive_order":{"model":"ArcFace (0.4)","paper_title":"EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset","paper_url":"/paper/edface-celeb-1m-benchmarking-face","paper_date":"2021-10-11","arxiv_id":"2110.05031","code_links":[{"title":"HDCVLab/EDFace-Celeb-1M","url":"https://github.com/HDCVLab/EDFace-Celeb-1M"}],"syntology":null}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/celeba","name":"CelebA","full_name":"CelebFaces Attributes Dataset","num_papers_in_archive":3477},{"url":"/dataset/ffhq","name":"FFHQ","full_name":"Flickr-Faces-HQ","num_papers_in_archive":1468},{"url":"/dataset/celeba-hq","name":"CelebA-HQ","full_name":"CelebA-HQ","num_papers_in_archive":954},{"url":"/dataset/bsd","name":"BSD","full_name":"Berkeley Segmentation Dataset","num_papers_in_archive":718},{"url":"/dataset/div2k","name":"DIV2K","full_name":"","num_papers_in_archive":654},{"url":"/dataset/urban100","name":"Urban100","full_name":"","num_papers_in_archive":591},{"url":"/dataset/vggface2-1","name":"VGGFace2","full_name":"Vggface2: A dataset for recognising faces  across pose and age","num_papers_in_archive":539},{"url":"/dataset/set14","name":"Set14","full_name":"","num_papers_in_archive":532},{"url":"/dataset/perceptual-similarity","name":"Perceptual Similarity","full_name":"","num_papers_in_archive":452},{"url":"/dataset/set5","name":"Set5","full_name":"","num_papers_in_archive":444},{"url":"/dataset/casia-webface","name":"CASIA-WebFace","full_name":"","num_papers_in_archive":415},{"url":"/dataset/manga109","name":"Manga109","full_name":"Manga109","num_papers_in_archive":300},{"url":"/dataset/middlebury","name":"Middlebury","full_name":"Middlebury Stereo","num_papers_in_archive":223},{"url":"/dataset/vimeo90k-1","name":"Vimeo90K","full_name":"","num_papers_in_archive":220},{"url":"/dataset/fmow","name":"fMoW","full_name":"Functional Map of the World","num_papers_in_archive":144},{"url":"/dataset/hide","name":"HIDE","full_name":"","num_papers_in_archive":95},{"url":"/dataset/xview","name":"xView","full_name":"","num_papers_in_archive":93},{"url":"/dataset/bsd100","name":"BSD100","full_name":null,"num_papers_in_archive":80},{"url":"/dataset/drealsr","name":"DRealSR","full_name":"Diverse Real-world image Super-Resolution","num_papers_in_archive":36},{"url":"/dataset/pirm","name":"PIRM","full_name":"Perceptual Image Restoration and Manipulation","num_papers_in_archive":32},{"url":"/dataset/general-100","name":"General-100","full_name":"General-100","num_papers_in_archive":30},{"url":"/dataset/textzoom","name":"TextZoom","full_name":null,"num_papers_in_archive":28},{"url":"/dataset/flickr1024","name":"Flickr1024","full_name":"","num_papers_in_archive":26},{"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/ixi-dataset","name":"IXI","full_name":"IXI Brain Development Dataset","num_papers_in_archive":23},{"url":"/dataset/ls3d-w","name":"LS3D-W","full_name":"","num_papers_in_archive":18},{"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/camerafusion","name":"CameraFusion","full_name":"","num_papers_in_archive":5},{"url":"/dataset/aerorit","name":"AeroRIT","full_name":"","num_papers_in_archive":4},{"url":"/dataset/qst","name":"QST","full_name":"Quick Sky Time","num_papers_in_archive":3},{"url":"/dataset/chikusei-dataset","name":"Chikusei Dataset","full_name":"Airborne hyperspectral data taken over Chikusei","num_papers_in_archive":2},{"url":"/dataset/davanet","name":"DAVANet","full_name":"","num_papers_in_archive":2},{"url":"/dataset/edface-celeb-1m","name":"EDFace-Celeb-1M","full_name":"","num_papers_in_archive":2},{"url":"/dataset/real-ce","name":"Real-CE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/stereomsi","name":"StereoMSI","full_name":"","num_papers_in_archive":2},{"url":"/dataset/l1bsr","name":"L1BSR","full_name":"L1BSR dataset","num_papers_in_archive":1},{"url":"/dataset/oli2msi","name":"OLI2MSI","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sen2venus","name":"Sen2venus","full_name":"SEN2VENµS","num_papers_in_archive":1},{"url":"/dataset/shipspotting","name":"ShipSpotting","full_name":"","num_papers_in_archive":1},{"url":"/dataset/testimages","name":"TESTIMAGES","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/burst-image-super-resolution","name":"Burst Image Super-Resolution"},{"url":"/task/multi-frame-super-resolution","name":"Multi-Frame Super-Resolution"},{"url":"/task/multispectral-image-super-resolution","name":"Multispectral Image Super-resolution"},{"url":"/task/satellite-image-super-resolution","name":"satellite image super-resolution"},{"url":"/task/stereo-image-super-resolution","name":"Stereo Image Super-Resolution"}],"parent_tasks":[{"url":"/task/16k","name":"16k"},{"url":"/task/super-resolution","name":"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":783,"tagged_in_all":1589,"items":[{"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/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/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/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/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/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/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/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}},{"url":"/paper/the-2018-pirm-challenge-on-perceptual-image","title":"The 2018 PIRM Challenge on Perceptual Image Super-resolution","date":"2018-09-20","arxiv_id":"1809.07517","repositories_listed":8,"syntology":null},{"url":"/paper/accurate-image-super-resolution-using-very","title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","date":"2015-11-14","arxiv_id":"1511.04587","repositories_listed":8,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/deep-back-projection-networks-for-single","title":"Deep Back-Projection Networks for Single Image Super-resolution","date":"2019-04-04","arxiv_id":"1904.05677","repositories_listed":7,"syntology":null},{"url":"/paper/recurrent-back-projection-network-for-video","title":"Recurrent Back-Projection Network for Video Super-Resolution","date":"2019-03-25","arxiv_id":"1903.10128","repositories_listed":7,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/zero-shot-super-resolution-using-deep","title":"\"Zero-Shot\" Super-Resolution using Deep Internal Learning","date":"2017-12-17","arxiv_id":"1712.06087","repositories_listed":7,"syntology":null},{"url":"/paper/fast-and-accurate-image-super-resolution-with","title":"Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks","date":"2017-10-04","arxiv_id":"1710.01992","repositories_listed":7,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/revisiting-rcan-improved-training-for-image","title":"Revisiting RCAN: Improved Training for Image Super-Resolution","date":"2022-01-27","arxiv_id":"2201.11279","repositories_listed":6,"syntology":null},{"url":"/paper/pre-trained-image-processing-transformer","title":"Pre-Trained Image Processing Transformer","date":"2020-12-01","arxiv_id":"2012.00364","repositories_listed":6,"syntology":null},{"url":"/paper/a-comprehensive-guide-to-bayesian","title":"A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference","date":"2019-01-08","arxiv_id":"1901.02731","repositories_listed":6,"syntology":{"n":14,"n_ran":4,"n_unverified":10,"n_pointer_only":1}},{"url":"/paper/a-fully-progressive-approach-to-single-image","title":"A Fully Progressive Approach to Single-Image Super-Resolution","date":"2018-04-09","arxiv_id":"1804.02900","repositories_listed":6,"syntology":null},{"url":"/paper/swin2sr-swinv2-transformer-for-compressed","title":"Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration","date":"2022-09-22","arxiv_id":"2209.11345","repositories_listed":5,"syntology":null}],"syntology_records":23,"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"}}