{"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/deep-stacked-hierarchical-multi-patch-network","title":"Deep Stacked Hierarchical Multi-patch Network for Image Deblurring","arxiv_id":"1904.03468","date":"2019-04-06","proceeding":"CVPR 2019 6","authors":["Hongguang Zhang","Yuchao Dai","Hongdong Li","Piotr Koniusz"],"abstract":"Despite deep end-to-end learning methods have shown their superiority in\nremoving non-uniform motion blur, there still exist major challenges with the\ncurrent multi-scale and scale-recurrent models: 1) Deconvolution/upsampling\noperations in the coarse-to-fine scheme result in expensive runtime; 2) Simply\nincreasing the model depth with finer-scale levels cannot improve the quality\nof deblurring. To tackle the above problems, we present a deep hierarchical\nmulti-patch network inspired by Spatial Pyramid Matching to deal with blurry\nimages via a fine-to-coarse hierarchical representation. To deal with the\nperformance saturation w.r.t. depth, we propose a stacked version of our\nmulti-patch model. Our proposed basic multi-patch model achieves the\nstate-of-the-art performance on the GoPro dataset while enjoying a 40x faster\nruntime compared to current multi-scale methods. With 30ms to process an image\nat 1280x720 resolution, it is the first real-time deep motion deblurring model\nfor 720p images at 30fps. For stacked networks, significant improvements (over\n1.2dB) are achieved on the GoPro dataset by increasing the network depth.\nMoreover, by varying the depth of the stacked model, one can adapt the\nperformance and runtime of the same network for different application\nscenarios.","url_abs":"http://arxiv.org/abs/1904.03468v1","url_pdf":"http://arxiv.org/pdf/1904.03468v1.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":[{"paper_slug":"deep-stacked-hierarchical-multi-patch-network","repo_url":"https://github.com/HongguangZhang/DMPHN-cvpr19-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"DMPHN","rank_in_archive_order":44,"of":56,"metrics":{"PSNR":"31.50","SSIM":" 0.9483"},"uses_additional_data":true},{"leaderboard":"/sota/deblurring-on-hide-trained-on-gopro","task":"Deblurring","dataset":"HIDE (trained on GOPRO)","model":"DMPHN","rank_in_archive_order":23,"of":26,"metrics":{"PSNR (sRGB)":"29.09","Params (M)":"7.23","SSIM (sRGB)":"0.924"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r-trained-on-gopro","task":"Deblurring","dataset":"RealBlur-R (trained on GoPro)","model":"DMPHN","rank_in_archive_order":13,"of":19,"metrics":{"SSIM (sRGB)":"0.948"},"uses_additional_data":false},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"DMPHN","rank_in_archive_order":40,"of":55,"metrics":{"PSNR":"31.50","SSIM":"0.9483"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.03468","atlas_url":"https://app.syntology.ai/?focus=1904.03468","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":"1904.03468"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.03468\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.03468"},"call":"get_concepts_for_paper(arxiv_id=\"1904.03468\")"}],"by_repo":[{"repo":"HongguangZhang/DMPHN-cvpr19-master","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b1968f7d8e3382c3bfb03e40d13e47f4918d879ef73b7b55df630197d3be61ab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}