{"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/deblurgan-v2-deblurring-orders-of-magnitude","title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","arxiv_id":"1908.03826","date":"2019-08-10","proceeding":"ICCV 2019 10","authors":["Orest Kupyn","Tetiana Martyniuk","Junru Wu","Zhangyang Wang"],"abstract":"We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility. DeblurGAN-v2 is based on a relativistic conditional GAN with a double-scale discriminator. For the first time, we introduce the Feature Pyramid Network into deblurring, as a core building block in the generator of DeblurGAN-v2. It can flexibly work with a wide range of backbones, to navigate the balance between performance and efficiency. The plug-in of sophisticated backbones (e.g., Inception-ResNet-v2) can lead to solid state-of-the-art deblurring. Meanwhile, with light-weight backbones (e.g., MobileNet and its variants), DeblurGAN-v2 reaches 10-100 times faster than the nearest competitors, while maintaining close to state-of-the-art results, implying the option of real-time video deblurring. We demonstrate that DeblurGAN-v2 obtains very competitive performance on several popular benchmarks, in terms of deblurring quality (both objective and subjective), as well as efficiency. Besides, we show the architecture to be effective for general image restoration tasks too. Our codes, models and data are available at: https://github.com/KupynOrest/DeblurGANv2","url_abs":"https://arxiv.org/abs/1908.03826v1","url_pdf":"https://arxiv.org/pdf/1908.03826v1.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":"deblurgan-v2-deblurring-orders-of-magnitude","repo_url":"https://github.com/KupynOrest/DeblurGANv2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deblurgan-v2-deblurring-orders-of-magnitude","repo_url":"https://github.com/HDCVLab/MC-Blur-Dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deblurgan-v2-deblurring-orders-of-magnitude","repo_url":"https://github.com/TAMU-VITA/DeblurGANv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deblurgan-v2-deblurring-orders-of-magnitude","repo_url":"https://github.com/kritiksoman/GIMP-ML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deblurgan-v2-deblurring-orders-of-magnitude","repo_url":"https://github.com/vcarehuman/YoloPose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deblurgan-v2-deblurring-orders-of-magnitude","repo_url":"https://github.com/vita-group/deblurganv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"blind-face-restoration","task_name":"Blind Face Restoration"},{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"single-image-blind-deblurring","task_name":"Single-Image Blind Deblurring"},{"task_slug":"video-deblurring","task_name":"Video Deblurring"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"DeblurGANv2*","rank_in_archive_order":3,"of":15,"metrics":{"Deg.":"39.64","FID":"52.69","LPIPS":"40.01","NIQE":"4.917","PSNR":"25.91","SSIM":"0.6952"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-based-1","task":"Deblurring","dataset":"BASED","model":"DeblurGAN Inception","rank_in_archive_order":2,"of":4,"metrics":{"ERQAv2.0":"0.74297","LPIPS":"0.08867","PSNR":"31.17171","SSIM":"0.94301","VMAF":"66.91781"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"DeblurGAN-v2","rank_in_archive_order":50,"of":56,"metrics":{"PSNR":"29.55","SSIM":"0.934"},"uses_additional_data":true},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"DeblurGANv2-MobileNet","rank_in_archive_order":54,"of":56,"metrics":{"PSNR":"28.17","SSIM":"0.925"},"uses_additional_data":true},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"DeblurGANv2-MobileNet-DSC","rank_in_archive_order":55,"of":56,"metrics":{"PSNR":"28.03","SSIM":"0.922"},"uses_additional_data":true},{"leaderboard":"/sota/deblurring-on-based","task":"Deblurring","dataset":"MSU BASED","model":"DeblurGAN Inception","rank_in_archive_order":4,"of":11,"metrics":{"Subjective":"1.0375"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset":"RealBlur-J","model":"DeblurGAN-v2","rank_in_archive_order":17,"of":17,"metrics":{"PSNR (sRGB)":"29.69","Params(M)":"5.08","SSIM (sRGB)":"0.870"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-trained-on-gopro","task":"Deblurring","dataset":"RealBlur-J (trained on GoPro)","model":"DeblurGAN-v2","rank_in_archive_order":11,"of":15,"metrics":{"PSNR (sRGB)":"28.70","SSIM (sRGB)":"0.866"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset":"RealBlur-R","model":"DeblurGAN-v2","rank_in_archive_order":16,"of":17,"metrics":{"PSNR (sRGB)":"36.44","SSIM (sRGB)":"0.935"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r-trained-on-gopro","task":"Deblurring","dataset":"RealBlur-R (trained on GoPro)","model":"DeblurGAN-v2","rank_in_archive_order":16,"of":19,"metrics":{"SSIM (sRGB)":"0.944"},"uses_additional_data":false},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"DeblurGAN-v2","rank_in_archive_order":49,"of":55,"metrics":{"PSNR":"29.55","Params (M)":"5.08","SSIM":"0.925"},"uses_additional_data":true},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"DeblurGANv2-MobileNet","rank_in_archive_order":52,"of":55,"metrics":{"PSNR":"28.17"},"uses_additional_data":true},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"DeblurGANv2-MobileNet-DSC","rank_in_archive_order":53,"of":55,"metrics":{"PSNR":"28.03","SSIM":"0.922"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.03826","atlas_url":"https://app.syntology.ai/?focus=1908.03826","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":"1908.03826"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1908.03826\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1908.03826"},"call":"get_concepts_for_paper(arxiv_id=\"1908.03826\")"}],"by_repo":[{"repo":"KupynOrest/DeblurGANv2","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"HDCVLab/MC-Blur-Dataset","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"TAMU-VITA/DeblurGANv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kritiksoman/GIMP-ML","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2011.06294","2103.13413"],"harvested_for_calls":[{"arxiv_id":"2011.06294","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2011.06294"},"call":"get_harvested_code_for_paper(arxiv_id=\"2011.06294\")"},{"arxiv_id":"2103.13413","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.13413"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.13413\")"}]},{"repo":"vcarehuman/YoloPose","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vita-group/deblurganv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.16749"],"harvested_for_calls":[{"arxiv_id":"2405.16749","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.16749"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.16749\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"f1242f01d05c98e82981ca0df1d31ce554944630c55dc35b7dcd91a04c169431","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}