{"url":"/task/image-reconstruction","name":"Image Reconstruction","slug":"image-reconstruction","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2143,"papers_with_code":712,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":12,"subtasks":5,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-reconstruction-on-imagenet","slug":"image-reconstruction-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":15,"metrics":["FID","LPIPS","PSNR","SSIM"],"first_row_in_archive_order":{"model":"MGVQ (16x16x8)","paper_title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization","paper_url":"/paper/mgvq-could-vq-vae-beat-vae-a-generalizable","paper_date":"2025-07-14","arxiv_id":"2507.07997","code_links":[{"title":"MKJia/MGVQ","url":"https://github.com/MKJia/MGVQ"}],"syntology":null}},{"leaderboard":"/sota/image-reconstruction-on-ultra-high-resolution","slug":"image-reconstruction-on-ultra-high-resolution","dataset":"Ultra-High Resolution Image Reconstruction Benchmark","dataset_url":"/dataset/uhdbench","rows_in_archive":6,"metrics":["rFID","PSNR","SSIM","LPIPS"],"first_row_in_archive_order":{"model":"SD-VAE (16x16)","paper_title":"High-Resolution Image Synthesis with Latent Diffusion Models","paper_url":"/paper/high-resolution-image-synthesis-with-latent","paper_date":"2021-12-20","arxiv_id":"2112.10752","code_links":[{"title":"compvis/stable-diffusion","url":"https://github.com/compvis/stable-diffusion"},{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"stability-ai/stablediffusion","url":"https://github.com/stability-ai/stablediffusion"},{"title":"microsoft/visual-chatgpt","url":"https://github.com/microsoft/visual-chatgpt"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/ppdiffusers"},{"title":"geekyutao/inpaint-anything","url":"https://github.com/geekyutao/inpaint-anything"},{"title":"showlab/Tune-A-Video","url":"https://github.com/showlab/Tune-A-Video"},{"title":"divamgupta/stable-diffusion-tensorflow","url":"https://github.com/divamgupta/stable-diffusion-tensorflow"},{"title":"mayuelala/followyourpose","url":"https://github.com/mayuelala/followyourpose"},{"title":"glouppe/info8010-deep-learning","url":"https://github.com/glouppe/info8010-deep-learning"},{"title":"keras-team/keras-cv","url":"https://github.com/keras-team/keras-cv"},{"title":"deforum/stable-diffusion","url":"https://github.com/deforum/stable-diffusion"},{"title":"mindspore-lab/mindone","url":"https://github.com/mindspore-lab/mindone"},{"title":"baaivision/vid2vid-zero","url":"https://github.com/baaivision/vid2vid-zero"},{"title":"zgctroy/layoutdiffusion","url":"https://github.com/zgctroy/layoutdiffusion"},{"title":"compvis/fm-boosting","url":"https://github.com/compvis/fm-boosting"},{"title":"Francis-Rings/MotionFollower","url":"https://github.com/Francis-Rings/MotionFollower"},{"title":"explainingai-code/StableDiffusion-PyTorch","url":"https://github.com/explainingai-code/StableDiffusion-PyTorch"},{"title":"ankanbhunia/Handwriting-Transformers","url":"https://github.com/ankanbhunia/Handwriting-Transformers"},{"title":"lorenzo-stacchio/Stable-Diffusion-Inpaint","url":"https://github.com/lorenzo-stacchio/Stable-Diffusion-Inpaint"},{"title":"vainf/diff-pruning","url":"https://github.com/vainf/diff-pruning"},{"title":"Francis-Rings/MotionEditor","url":"https://github.com/Francis-Rings/MotionEditor"},{"title":"olaviinha/NeuralImageSuperResolution","url":"https://github.com/olaviinha/NeuralImageSuperResolution"},{"title":"joanrod/ocr-vqgan","url":"https://github.com/joanrod/ocr-vqgan"},{"title":"showlab/loveu-tgve-2023","url":"https://github.com/showlab/loveu-tgve-2023"},{"title":"yangling0818/contextdiff","url":"https://github.com/yangling0818/contextdiff"},{"title":"SnailDev/github-hot-hub","url":"https://github.com/SnailDev/github-hot-hub"},{"title":"lonnyzhang423/github-hot-hub","url":"https://github.com/lonnyzhang423/github-hot-hub"},{"title":"lilijiangg/autodiffusion","url":"https://github.com/lilijiangg/autodiffusion"},{"title":"will-wang19/Image-Edit-with-Mask-generated-by-Stable-Diffusion","url":"https://github.com/will-wang19/Image-Edit-with-Mask-generated-by-Stable-Diffusion"},{"title":"quereste/implicit-deepfake","url":"https://github.com/quereste/implicit-deepfake"},{"title":"joanrod/figure-diffusion","url":"https://github.com/joanrod/figure-diffusion"},{"title":"spengliang/smoothvideo","url":"https://github.com/spengliang/smoothvideo"},{"title":"joh-fischer/PlantLDM","url":"https://github.com/joh-fischer/PlantLDM"},{"title":"milmor/latent-diffusion-transformer","url":"https://github.com/milmor/latent-diffusion-transformer"},{"title":"artem-gorodetskii/wikiart-latent-diffusion","url":"https://github.com/artem-gorodetskii/wikiart-latent-diffusion"},{"title":"fhshen2022/prunerepaint","url":"https://github.com/fhshen2022/prunerepaint"},{"title":"benearnthof/fm_boosting","url":"https://github.com/benearnthof/fm_boosting"},{"title":"clarken92/vfm","url":"https://github.com/clarken92/vfm"},{"title":"camilocarvajalreyes/sfws-stable-diffusion","url":"https://github.com/camilocarvajalreyes/sfws-stable-diffusion"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/Super-Resolution-for-Root-Imaging"}],"syntology":{"n":28,"n_ran":19,"n_unverified":9,"n_pointer_only":5}}},{"leaderboard":"/sota/image-reconstruction-on-edge-to-handbags","slug":"image-reconstruction-on-edge-to-handbags","dataset":"Edge-to-Handbags","dataset_url":null,"rows_in_archive":4,"metrics":["FID","LPIPS","HP","MMD"],"first_row_in_archive_order":{"model":"PI-REC","paper_title":"PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain","paper_url":"/paper/pi-rec-progressive-image-reconstruction-1","paper_date":"2019-03-25","arxiv_id":"1903.10146","code_links":[{"title":"youyuge34/PI-REC","url":"https://github.com/youyuge34/PI-REC"}],"syntology":null}},{"leaderboard":"/sota/image-reconstruction-on-edge-to-shoes","slug":"image-reconstruction-on-edge-to-shoes","dataset":"Edge-to-Shoes","dataset_url":null,"rows_in_archive":4,"metrics":["FID","LPIPS","HP","MMD"],"first_row_in_archive_order":{"model":"PI-REC","paper_title":"PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain","paper_url":"/paper/pi-rec-progressive-image-reconstruction-1","paper_date":"2019-03-25","arxiv_id":"1903.10146","code_links":[{"title":"youyuge34/PI-REC","url":"https://github.com/youyuge34/PI-REC"}],"syntology":null}},{"leaderboard":"/sota/image-reconstruction-on-audio-set","slug":"image-reconstruction-on-audio-set","dataset":"Audio Set","dataset_url":null,"rows_in_archive":2,"metrics":["SSIM"],"first_row_in_archive_order":{"model":"Ours (STFT: magnitude, L1l=1) W-Replicate","paper_title":"Towards Robust Image-in-Audio Deep Steganography","paper_url":"/paper/towards-robust-image-in-audio-deep","paper_date":"2023-03-09","arxiv_id":"2303.05007","code_links":[{"title":"migamic/pixinwav2","url":"https://github.com/migamic/pixinwav2"}],"syntology":null}},{"leaderboard":"/sota/image-reconstruction-on-imagenet-256x256","slug":"image-reconstruction-on-imagenet-256x256","dataset":"ImageNet 256x256","dataset_url":null,"rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"AugVAE-ML","paper_title":"L-Verse: Bidirectional Generation Between Image and Text","paper_url":"/paper/l-verse-bidirectional-generation-between","paper_date":"2021-11-22","arxiv_id":"2111.11133","code_links":[{"title":"tgisaturday/L-Verse","url":"https://github.com/tgisaturday/L-Verse"}],"syntology":null}},{"leaderboard":"/sota/image-reconstruction-on-edge-to-clothes","slug":"image-reconstruction-on-edge-to-clothes","dataset":"Edge-to-Clothes","dataset_url":null,"rows_in_archive":1,"metrics":["FID","LPIPS"],"first_row_in_archive_order":{"model":"bFT","paper_title":"Guided Image-to-Image Translation with Bi-Directional Feature Transformation","paper_url":"/paper/guided-image-to-image-translation-with-bi-1","paper_date":"2019-10-24","arxiv_id":"1910.11328","code_links":[{"title":"vt-vl-lab/Guided-pix2pix","url":"https://github.com/vt-vl-lab/Guided-pix2pix"}],"syntology":null}},{"leaderboard":"/sota/image-reconstruction-on-spike-x4k","slug":"image-reconstruction-on-spike-x4k","dataset":"Spike-X4K","dataset_url":"/dataset/spike-x4k","rows_in_archive":1,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"SwinSF","paper_title":"SwinSF: Image Reconstruction from Spatial-Temporal Spike Streams","paper_url":"/paper/swinsf-image-reconstruction-from-spatial","paper_date":"2024-07-22","arxiv_id":"2407.15708","code_links":[{"title":"bupt-ai-cz/SwinSF","url":"https://github.com/bupt-ai-cz/SwinSF"}],"syntology":null}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/general-100","name":"General-100","full_name":"General-100","num_papers_in_archive":30},{"url":"/dataset/ced","name":"CED","full_name":"Color Event Camera Dataset","num_papers_in_archive":15},{"url":"/dataset/sen12ms-cr","name":"SEN12MS-CR","full_name":"","num_papers_in_archive":13},{"url":"/dataset/sen12ms-cr-ts","name":"SEN12MS-CR-TS","full_name":"SEN12MS-CR-TS","num_papers_in_archive":7},{"url":"/dataset/uhdbench","name":"Ultra-High Resolution Image Reconstruction Benchmark","full_name":"","num_papers_in_archive":6},{"url":"/dataset/2detect","name":"2DeteCT","full_name":"2DeteCT - A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning","num_papers_in_archive":5},{"url":"/dataset/oadat","name":"OADAT","full_name":"OADAT: Experimental and Synthetic Clinical Optoacoustic Data for Standardized Image Processing","num_papers_in_archive":2},{"url":"/dataset/rgb-davis-dataset","name":"RGB-DAVIS Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/spike-x4k","name":"Spike-X4K","full_name":"Spike-X4K Dataset","num_papers_in_archive":1},{"url":"/dataset/wificam","name":"WiFiCam","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cbct-walnut","name":"CBCT Walnut","full_name":"Cone-Beam X-Ray CT Data Collection Designed for Machine Learning","num_papers_in_archive":0}],"subtasks":[{"url":"/task/blind-super-resolution","name":"Blind Super-Resolution"},{"url":"/task/ct-reconstruction","name":"CT Reconstruction"},{"url":"/task/film-removal","name":"Film Removal"},{"url":"/task/mri-reconstruction","name":"MRI Reconstruction"},{"url":"/task/wifi-csi-based-image-reconstruction","name":"WiFi CSI-based Image Reconstruction"}],"parent_tasks":[],"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":712,"tagged_in_all":2143,"items":[{"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/unsupervised-monocular-depth-estimation-with","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","date":"2016-09-13","arxiv_id":"1609.03677","repositories_listed":16,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":5}},{"url":"/paper/digging-into-self-supervised-monocular-depth","title":"Digging Into Self-Supervised Monocular Depth Estimation","date":"2018-06-04","arxiv_id":"1806.01260","repositories_listed":15,"syntology":{"n":24,"n_ran":17,"n_unverified":7,"n_pointer_only":6}},{"url":"/paper/universal-style-transfer-via-feature","title":"Universal Style Transfer via Feature Transforms","date":"2017-05-23","arxiv_id":"1705.08086","repositories_listed":15,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","arxiv_id":"2012.09841","repositories_listed":13,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/fastmri-an-open-dataset-and-benchmarks-for","title":"fastMRI: An Open Dataset and Benchmarks for Accelerated MRI","date":"2018-11-21","arxiv_id":"1811.08839","repositories_listed":13,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/maskgit-masked-generative-image-transformer","title":"MaskGIT: Masked Generative Image Transformer","date":"2022-02-08","arxiv_id":"2202.04200","repositories_listed":9,"syntology":{"n":21,"n_ran":14,"n_unverified":7,"n_pointer_only":4}},{"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/assessment-of-data-consistency-through","title":"Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction","date":"2021-11-30","arxiv_id":"2111.15498","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/unifying-vision-text-and-layout-for-universal","title":"Unifying Vision, Text, and Layout for Universal Document Processing","date":"2022-12-05","arxiv_id":"2212.02623","repositories_listed":5,"syntology":{"n":17,"n_ran":4,"n_unverified":13,"n_pointer_only":3}},{"url":"/paper/vector-quantized-image-modeling-with-improved-1","title":"Vector-quantized Image Modeling with Improved VQGAN","date":"2021-10-09","arxiv_id":"2110.04627","repositories_listed":5,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/homotopic-gradients-of-generative-density","title":"Homotopic Gradients of Generative Density Priors for MR Image Reconstruction","date":"2020-08-14","arxiv_id":"2008.06284","repositories_listed":5,"syntology":null},{"url":"/paper/autoregressive-image-generation-using","title":"Autoregressive Image Generation using Residual Quantization","date":"2022-03-03","arxiv_id":"2203.01941","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/mask-guided-spectral-wise-transformer-for","title":"Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction","date":"2021-11-15","arxiv_id":"2111.07910","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/adaptable-gan-encoders-for-image","title":"Improving generative adversarial network inversion via fine-tuning GAN encoders","date":"2021-08-23","arxiv_id":"2108.10201","repositories_listed":4,"syntology":null},{"url":"/paper/reconresnet-regularised-residual-learning-for","title":"ReconResNet: Regularised Residual Learning for MR Image Reconstruction of Undersampled Cartesian and Radial Data","date":"2021-03-16","arxiv_id":"2103.09203","repositories_listed":4,"syntology":null},{"url":"/paper/can-un-trained-neural-networks-compete-with","title":"Accelerated MRI with Un-trained Neural Networks","date":"2020-07-06","arxiv_id":"2007.02471","repositories_listed":4,"syntology":null},{"url":"/paper/gradient-origin-networks","title":"Gradient Origin Networks","date":"2020-07-06","arxiv_id":"2007.02798","repositories_listed":4,"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/probabilistic-auto-encoder","title":"Probabilistic Autoencoder","date":"2020-06-09","arxiv_id":"2006.05479","repositories_listed":4,"syntology":{"n":13,"n_ran":1,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/improving-sample-efficiency-in-model-free-1","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","date":"2019-10-02","arxiv_id":"1910.01741","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/implicit-generation-and-generalization-in","title":"Implicit Generation and Generalization in Energy-Based Models","date":"2019-03-20","arxiv_id":"1903.08689","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/towards-real-time-unsupervised-monocular","title":"Towards real-time unsupervised monocular depth estimation on CPU","date":"2018-06-29","arxiv_id":"1806.11430","repositories_listed":4,"syntology":null},{"url":"/paper/efficient-and-accurate-inversion-of-multiple","title":"Efficient and accurate inversion of multiple scattering with deep learning","date":"2018-03-18","arxiv_id":"1803.06594","repositories_listed":4,"syntology":null},{"url":"/paper/convolutional-recurrent-neural-networks-for-7","title":"Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction","date":"2017-12-05","arxiv_id":"1712.01751","repositories_listed":4,"syntology":null},{"url":"/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","arxiv_id":"1707.05425","repositories_listed":4,"syntology":null},{"url":"/paper/a-deep-cascade-of-convolutional-neural","title":"A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction","date":"2017-04-08","arxiv_id":"1704.02422","repositories_listed":4,"syntology":null},{"url":"/paper/a-deep-cascade-of-convolutional-neural-1","title":"A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction","date":"2017-03-01","arxiv_id":"1703.00555","repositories_listed":4,"syntology":null},{"url":"/paper/visual-autoregressive-modeling-scalable-image","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","date":"2024-04-03","arxiv_id":"2404.02905","repositories_listed":3,"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/modality-cycles-with-masked-conditional","title":"Modality Cycles with Masked Conditional Diffusion for Unsupervised Anomaly Segmentation in MRI","date":"2023-08-30","arxiv_id":"2308.16150","repositories_listed":3,"syntology":null}],"syntology_records":18,"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"}}