{"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/akdt-adaptive-kernel-dilation-transformer-for","title":"AKDT: Adaptive Kernel Dilation Transformer for Effective Image Denoising","arxiv_id":null,"date":"2025-02-26","proceeding":"VISAPP 2025 2","authors":["Alexandru Brateanu","Raul Balmez","Adrian Avram","Ciprian Orhei"],"abstract":"Image denoising is a fundamental yet challenging task, especially when dealing with high-resolution images and complex noise patterns. Most existing methods rely on standard Transformer architectures, which often suffer from high computational complexity and limited adaptability to varying noise levels. In this paper, we introduce the Adaptive Kernel Dilation Transformer (AKDT), a novel Transformer-based model that fully harnesses the power of learnable dilation rates within convolutions. AKDT consists of several layers and custom-designed blocks, including our novel Learnable Dilation Rate (LDR) module, which is utilized to construct a Noise Estimator module (NE). At the core of AKDT, the NE is seamlessly integrated within standard Transformer components to form the Noise-Guided Feed-Forward Network (NG-FFN) and Noise-Guided Multi-Headed Self-Attention (NG-MSA). These noise-modulated Transformer components enable the model to achieve unparalleled denoising performance while significantly reducing computational costs. Extensive experiments across multiple image denoising benchmarks demonstrate that AKDT sets a new state-of-the-art, effectively handling both real and synthetic noise. The source code and pre-trained models are publicly available at https://github.com/albrateanu/AKDT.","url_abs":"https://www.insticc.org/node/TechnicalProgram/VISIGRAPP/2025/presentationDetails/131577","url_pdf":"https://www.insticc.org/node/TechnicalProgram/VISIGRAPP/2025/presentationDetails/131577","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":"akdt-adaptive-kernel-dilation-transformer-for","repo_url":"https://github.com/albrateanu/AKDT","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"color-image-denoising","task_name":"Color Image Denoising"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma15","task":"Color Image Denoising","dataset":"CBSD68 sigma15","model":"AKDT","rank_in_archive_order":1,"of":10,"metrics":{"PSNR":"34.64"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma25","task":"Color Image Denoising","dataset":"CBSD68 sigma25","model":"AKDT","rank_in_archive_order":1,"of":9,"metrics":{"PSNR":"31.94"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma50","task":"Color Image Denoising","dataset":"CBSD68 sigma50","model":"AKDT","rank_in_archive_order":5,"of":18,"metrics":{"PSNR":"28.68"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-mcmaster-sigma15","task":"Color Image Denoising","dataset":"McMaster sigma15","model":"AKDT","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"36.71"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-mcmaster-sigma25","task":"Color Image Denoising","dataset":"McMaster sigma25","model":"AKDT","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"34.21"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-mcmaster-sigma50","task":"Color Image Denoising","dataset":"McMaster sigma50","model":"AKDT","rank_in_archive_order":1,"of":7,"metrics":{"PSNR":"30.95"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-urban100-sigma25","task":"Color Image Denoising","dataset":"Urban100 sigma25","model":"AKDT","rank_in_archive_order":2,"of":6,"metrics":{"PSNR":"33.14"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-urban100-sigma50","task":"Color Image Denoising","dataset":"Urban100 sigma50","model":"AKDT","rank_in_archive_order":7,"of":9,"metrics":{"PSNR":"29.82"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-urban100-sigma15-1","task":"Color Image Denoising","dataset":"urban100 sigma15","model":"AKDT","rank_in_archive_order":1,"of":8,"metrics":{"Average PSNR":"35.63","PSNR":"35.63"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sidd","task":"Image Denoising","dataset":"SIDD","model":"AKDT","rank_in_archive_order":13,"of":22,"metrics":{"PSNR (sRGB)":"39.70","SSIM (sRGB)":"0.961"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-urban100-sigma50","task":"Image Denoising","dataset":"Urban100 sigma50","model":"AKDT","rank_in_archive_order":4,"of":4,"metrics":{"PSNR":"29.82"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-urban100-sigma15","task":"Image Denoising","dataset":"urban100 sigma15","model":"AKDT","rank_in_archive_order":1,"of":4,"metrics":{"Average PSNR":"35.64"},"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":"albrateanu/AKDT","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":"996263c3c700dbb8ed83dd0a94ec53c180803c147d44765c6016003bed00518d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}