{"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/gradient-magnitude-similarity-deviation-a","title":"Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index","arxiv_id":"1308.3052","date":"2013-08-14","proceeding":null,"authors":["Wufeng Xue","Lei Zhang","Xuanqin Mou","Alan C. Bovik"],"abstract":"It is an important task to faithfully evaluate the perceptual quality of\noutput images in many applications such as image compression, image restoration\nand multimedia streaming. A good image quality assessment (IQA) model should\nnot only deliver high quality prediction accuracy but also be computationally\nefficient. The efficiency of IQA metrics is becoming particularly important due\nto the increasing proliferation of high-volume visual data in high-speed\nnetworks. We present a new effective and efficient IQA model, called gradient\nmagnitude similarity deviation (GMSD). The image gradients are sensitive to\nimage distortions, while different local structures in a distorted image suffer\ndifferent degrees of degradations. This motivates us to explore the use of\nglobal variation of gradient based local quality map for overall image quality\nprediction. We find that the pixel-wise gradient magnitude similarity (GMS)\nbetween the reference and distorted images combined with a novel pooling\nstrategy the standard deviation of the GMS map can predict accurately\nperceptual image quality. The resulting GMSD algorithm is much faster than most\nstate-of-the-art IQA methods, and delivers highly competitive prediction\naccuracy.","url_abs":"http://arxiv.org/abs/1308.3052v2","url_pdf":"http://arxiv.org/pdf/1308.3052v2.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":"full-reference-image-quality-assessment","task_name":"Full reference image quality assessment"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/full-reference-image-quality-assessment-on-4","task":"Full reference image quality assessment","dataset":"DRIQ","model":"GMSD","rank_in_archive_order":5,"of":10,"metrics":{"PLCC":"0.8001","SRCC":"0.7762"},"uses_additional_data":false},{"leaderboard":"/sota/full-reference-image-quality-assessment-on-3","task":"Full reference image quality assessment","dataset":"ESPL","model":"GMSD","rank_in_archive_order":8,"of":11,"metrics":{"PLCC":"0.8234","SRCC":"0.8209"},"uses_additional_data":false},{"leaderboard":"/sota/full-reference-image-quality-assessment-on-2","task":"Full reference image quality assessment","dataset":"KADID10K","model":"GMSD","rank_in_archive_order":6,"of":11,"metrics":{"SRCC":"0.8474"},"uses_additional_data":false},{"leaderboard":"/sota/full-reference-image-quality-assessment-on","task":"Full reference image quality assessment","dataset":"TID2008","model":"GMSD","rank_in_archive_order":6,"of":13,"metrics":{"PLCC":"0.8788","SRCC":"0.8907"},"uses_additional_data":false},{"leaderboard":"/sota/image-quality-assessment-on-msu-fr-vqa","task":"Image Quality Assessment","dataset":"MSU FR VQA Database","model":"GMSD","rank_in_archive_order":6,"of":6,"metrics":{"SRCC":"0.8937"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1308.3052","atlas_url":"https://app.syntology.ai/?focus=1308.3052","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1308.3052"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1308.3052\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1308.3052"},"call":"get_concepts_for_paper(arxiv_id=\"1308.3052\")"}],"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":"85a09b7d5bd5e8a25b57be2e6ef87583b540d04f5bf0fc9a37c5688f4ee8dbfa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}