{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/hierarchical-information-flow-for-generalized","title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","arxiv_id":"2411.18588","date":"2024-11-27","proceeding":null,"authors":["Yawei Li","Bin Ren","Jingyun Liang","Rakesh Ranjan","Mengyuan Liu","Nicu Sebe","Ming-Hsuan Yang","Luca Benini"],"abstract":"While vision transformers show promise in numerous image restoration (IR) tasks, the challenge remains in efficiently generalizing and scaling up a model for multiple IR tasks. To strike a balance between efficiency and model capacity for a generalized transformer-based IR method, we propose a hierarchical information flow mechanism for image restoration, dubbed Hi-IR, which progressively propagates information among pixels in a bottom-up manner. Hi-IR constructs a hierarchical information tree representing the degraded image across three levels. Each level encapsulates different types of information, with higher levels encompassing broader objects and concepts and lower levels focusing on local details. Moreover, the hierarchical tree architecture removes long-range self-attention, improves the computational efficiency and memory utilization, thus preparing it for effective model scaling. Based on that, we explore model scaling to improve our method's capabilities, which is expected to positively impact IR in large-scale training settings. Extensive experimental results show that Hi-IR achieves state-of-the-art performance in seven common image restoration tasks, affirming its effectiveness and generalizability.","url_abs":"https://arxiv.org/abs/2411.18588v1","url_pdf":"https://arxiv.org/pdf/2411.18588v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"color-image-denoising","task_name":"Color Image Denoising"},{"task_slug":"grayscale-image-denoising","task_name":"Grayscale Image Denoising"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"jpeg-artifact-correction","task_name":"JPEG Artifact Correction"},{"task_slug":"jpeg-artifact-removal","task_name":"JPEG Artifact Removal"},{"task_slug":"jpeg-compression-artifact-reduction","task_name":"Jpeg Compression Artifact Reduction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/color-image-denoising-on-kodak24-sigma15","task":"Color Image Denoising","dataset":"Kodak24 sigma15","model":"Hi-IR","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"35.42"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-kodak24-sigma25","task":"Color Image Denoising","dataset":"Kodak24 sigma25","model":"Hi-IR","rank_in_archive_order":2,"of":3,"metrics":{"PSNR":"33.01"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-kodak24-sigma50","task":"Color Image Denoising","dataset":"Kodak24 sigma50","model":"Hi-IR","rank_in_archive_order":5,"of":9,"metrics":{"PSNR":"29.98"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-mcmaster-sigma15","task":"Color Image Denoising","dataset":"McMaster sigma15","model":"Hi-IR","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"35.69"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-mcmaster-sigma25","task":"Color Image Denoising","dataset":"McMaster sigma25","model":"Hi-IR","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"33.44"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-mcmaster-sigma50","task":"Color Image Denoising","dataset":"McMaster sigma50","model":"Hi-IR","rank_in_archive_order":3,"of":7,"metrics":{"PSNR":"30.42"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-urban100-sigma25","task":"Color Image Denoising","dataset":"Urban100 sigma25","model":"Hi-IR","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"33.34"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-urban100-sigma50","task":"Color Image Denoising","dataset":"Urban100 sigma50","model":"Hi-IR","rank_in_archive_order":1,"of":9,"metrics":{"PSNR":"30.59"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-urban100-sigma15-1","task":"Color Image Denoising","dataset":"urban100 sigma15","model":"Hi-IR","rank_in_archive_order":8,"of":8,"metrics":{"PSNR":"35.46"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma15","task":"Grayscale Image Denoising","dataset":"Set12 sigma15","model":"Hi-IR","rank_in_archive_order":1,"of":8,"metrics":{"PSNR":"33.48"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma25","task":"Grayscale Image Denoising","dataset":"Set12 sigma25","model":"Hi-IR","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"31.19"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma50","task":"Grayscale Image Denoising","dataset":"Set12 sigma50","model":"Hi-IR","rank_in_archive_order":1,"of":8,"metrics":{"PSNR":"28.15"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma25","task":"Grayscale Image Denoising","dataset":"Urban100 sigma25","model":"Hi-IR","rank_in_archive_order":1,"of":10,"metrics":{"PSNR":"31.92"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma50","task":"Grayscale Image Denoising","dataset":"Urban100 sigma50","model":"Hi-IR","rank_in_archive_order":1,"of":10,"metrics":{"PSNR":"28.91"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma15-1","task":"Grayscale Image Denoising","dataset":"urban100 sigma15","model":"Hi-IR","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"34.11"},"uses_additional_data":false},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"Hi-IR-L","rank_in_archive_order":9,"of":55,"metrics":{"PSNR":"33.99"},"uses_additional_data":false},{"leaderboard":"/sota/image-deblurring-on-hide-trained-on-gopro","task":"Image Deblurring","dataset":"HIDE (trained on GOPRO)","model":"Hi-IR-L","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"31.64"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-2x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 2x upscaling","model":"Hi-IR-L","rank_in_archive_order":5,"of":30,"metrics":{"PSNR":"32.77","SSIM":"0.9092"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-3x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 3x upscaling","model":"Hi-IR-L","rank_in_archive_order":1,"of":21,"metrics":{"PSNR":"29.67","SSIM":"0.8256"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"Hi-IR-L","rank_in_archive_order":2,"of":71,"metrics":{"PSNR":"28.13","SSIM":"0.7622"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-2x","task":"Image Super-Resolution","dataset":"Manga109 - 2x upscaling","model":"Hi-IR-L","rank_in_archive_order":1,"of":21,"metrics":{"PSNR":"41.22","SSIM":"0.9846"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-3x","task":"Image Super-Resolution","dataset":"Manga109 - 3x upscaling","model":"Hi-IR-L","rank_in_archive_order":1,"of":17,"metrics":{"PSNR":"36.12","SSIM":"0.9588"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","task":"Image Super-Resolution","dataset":"Manga109 - 4x upscaling","model":"Hi-IR-L","rank_in_archive_order":1,"of":50,"metrics":{"PSNR":"33.13","SSIM":"0.9366"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 2x upscaling","model":"Hi-IR-L","rank_in_archive_order":4,"of":35,"metrics":{"PSNR":"35.27","SSIM":"0.9311"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-3x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 3x upscaling","model":"Hi-IR-L","rank_in_archive_order":1,"of":24,"metrics":{"PSNR":"31.55","SSIM":"0.8616"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"Hi-IR-L","rank_in_archive_order":3,"of":104,"metrics":{"PSNR":"29.49","SSIM":"0.8041"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"Hi-IR-L","rank_in_archive_order":4,"of":41,"metrics":{"PSNR":"38.87","SSIM":"0.9663"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"Hi-IR-L","rank_in_archive_order":5,"of":32,"metrics":{"PSNR":"35.2","SSIM":"0.938"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-4x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 4x upscaling","model":"Hi-IR-L","rank_in_archive_order":4,"of":12,"metrics":{"PSNR":"33.22","SSIM":"0.9103"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-2x","task":"Image Super-Resolution","dataset":"Urban100 - 2x upscaling","model":"Hi-IR-L","rank_in_archive_order":3,"of":29,"metrics":{"PSNR":"35.16","SSIM":"0.9505"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-3x","task":"Image Super-Resolution","dataset":"Urban100 - 3x upscaling","model":"Hi-IR-L","rank_in_archive_order":1,"of":22,"metrics":{"PSNR":"31.07","SSIM":"0.902"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"Hi-IR-L","rank_in_archive_order":1,"of":65,"metrics":{"PSNR":"28.72","SSIM":"0.8514"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-bsd500-quality-10","task":"JPEG Artifact Correction","dataset":"BSD500 (Quality 10 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"28.35","SSIM":"0.8092"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-bsd500-quality-20","task":"JPEG Artifact Correction","dataset":"BSD500 (Quality 20 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"30.61","SSIM":"0.874"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-bsd500-quality-30","task":"JPEG Artifact Correction","dataset":"BSD500 (Quality 30 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"31.99","SSIM":"0.9035"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-bsd500-quality-40","task":"JPEG Artifact Correction","dataset":"BSD500 (Quality 40 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"32.92","SSIM":"0.9195"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-classic5-quality","task":"JPEG Artifact Correction","dataset":"Classic5 (Quality 10 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":7,"metrics":{"PSNR":"30.38","SSIM":"0.8266"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-classic5-quality-1","task":"JPEG Artifact Correction","dataset":"Classic5 (Quality 20 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"32.62","SSIM":"0.8751"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-classic5-quality-2","task":"JPEG Artifact Correction","dataset":"Classic5 (Quality 30 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"33.8","SSIM":"0.8962"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-classic5-quality-3","task":"JPEG Artifact Correction","dataset":"Classic5 (Quality 40 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":5,"metrics":{"PSNR":"34.61","SSIM":"0.9082"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 10 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":9,"metrics":{"PSNR":"28.36","SSIM":"0.818"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-20","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 20 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":9,"metrics":{"PSNR":"30.66","SSIM":"0.8797"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-20-1","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 20 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":12,"metrics":{"PSNR":"32.31","SSIM":"0.8938"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-30","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 30 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"32.02","SSIM":"0.9063"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-30-1","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 30 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":7,"metrics":{"PSNR":"33.73","SSIM":"0.9223"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-40-1","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 40 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"32.94","SSIM":"0.921"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-40","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 40 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":5,"metrics":{"PSNR":"34.71","SSIM":"0.9347"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10-1","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 10 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":13,"metrics":{"PSNR":"29.94","SSIM":"0.8359"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality-4","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 10 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"29.11","SSIM":"0.8727"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 10 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"31.07","SSIM":"0.895"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality-5","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 20 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"31.36","SSIM":"0.9115"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality-1","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 20 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"33.51","SSIM":"0.925"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality-6","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 30 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"32.57","SSIM":"0.9279"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality-2","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 30 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"34.86","SSIM":"0.9459"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality-7","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 40 Color)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"33.37","SSIM":"0.9373"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-urban100-quality-3","task":"JPEG Artifact Correction","dataset":"Urban100 (Quality 40 Grayscale)","model":"Hi-IR","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"35.77","SSIM":"0.9561"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c6d804f18ff746130793629d1b16f5c3dc7e3dc14b5c5d63960a853887f4f474","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}