{"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/sad-net-a-full-spectral-self-attention-detail","title":"SAD-Net: a full spectral self-attention detail enhancement network for single image dehazing","arxiv_id":null,"date":"2025-04-07","proceeding":"Scientific Reports 2025 4","authors":["Qingjun Niu， Kun Wu， Jialu Zhang， Zhenqi Han， Lizhuang Liu"],"abstract":"Single-image dehazing technology plays a significant role in video surveillance and intelligent \r\ntransportation. However, existing dehazing methods using vanilla convolution only extract features \r\nin the temporal domain and lack the ability to capture multi-directional information. To address the \r\naforementioned issues, we design a new full spectral attention-based detail enhancement dehazing \r\nnetwork, named SAD-Net. SAD-Net adopts a U-Net-like structure and integrates Spectral Detail \r\nEnhancement Convolution (SDEC) and Frequency-Guided Attention (FGA). SDEC combines wavelet \r\ntransform and difference convolution(DC) to enhance high-frequency features while preserving low\r\nfrequency information. FGA detects haze-induced discrepancies and fine-tunes feature modulation. \r\nExperimental results show that SAD-Net outperforms six other dehazing networks on the Dense-Haze, \r\nNH-Haze, RESIDE and I-Haze datasets. Specifically, it increases the peak signal-to-noise ratio (PSNR) \r\nto 17.16 dB on the Dense-Haze dataset, surpassing the current state-of-the-art (SOTA) methods. \r\nAdditionally, SAD-Net achieves excellent dehazing performance on an external dataset without any \r\nprior training.","url_abs":"https://www.nature.com/articles/s41598-025-92061-1","url_pdf":"https://www.nature.com/articles/s41598-025-92061-1.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":"sad-net-a-full-spectral-self-attention-detail","repo_url":"https://github.com/niuqj/SAD-Net","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"single-image-dehazing","task_name":"Single Image Dehazing"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fga","method_name":"FGA"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-dehazing-on-dense-haze","task":"Image Dehazing","dataset":"Dense-Haze","model":"SAD-Net","rank_in_archive_order":2,"of":5,"metrics":{"PSNR":"17.16","SSIM":"0.55"},"uses_additional_data":false},{"leaderboard":"/sota/image-dehazing-on-i-haze","task":"Image Dehazing","dataset":"I-Haze","model":"SAD-Net","rank_in_archive_order":4,"of":4,"metrics":{"PSNR":"21.65","SSIM":"0.84"},"uses_additional_data":false},{"leaderboard":"/sota/image-dehazing-on-nh-haze","task":"Image Dehazing","dataset":"NH-HAZE","model":"SAD-Net","rank_in_archive_order":4,"of":4,"metrics":{"PSNR":"20.48"},"uses_additional_data":false},{"leaderboard":"/sota/image-dehazing-on-sots-indoor","task":"Image Dehazing","dataset":"SOTS Indoor","model":"SAD-Net","rank_in_archive_order":6,"of":34,"metrics":{"PSNR":"41.71","SSIM":"0.993"},"uses_additional_data":false},{"leaderboard":"/sota/image-dehazing-on-sots-outdoor","task":"Image Dehazing","dataset":"SOTS Outdoor","model":"SAD-Net","rank_in_archive_order":10,"of":31,"metrics":{"PSNR":"37.78","SSIM":"0.990"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"niuqj/SAD-Net","kind":"named_in_paper","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":"91af9dda36c138c9b88d27ce822577f657bc18efcda75101809b145d64000ce6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}