{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T12:43:44Z","timestamp":1759409024738,"version":"build-2065373602"},"reference-count":71,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Overcoming visual degradation in challenging imaging scenarios is essential for accurate scene understanding. Although deep learning methods have integrated various perceptual capabilities and achieved remarkable progress, their high computational cost limits practical deployment under resource-constrained conditions. Moreover, when confronted with diverse degradation types, existing methods often fail to effectively model the inconsistent attenuation across color channels and spatial regions. To tackle these challenges, we propose <jats:bold>DWMamba<\/jats:bold>, a degradation-aware and weight-efficient Mamba network for image quality enhancement. Specifically, DWMamba introduces an Adaptive State Space Module (ASSM) that employs a dual-stream channel monitoring mechanism and a soft fusion strategy to capture global dependencies. With linear computational complexity, ASSM strengthens the models ability to address non-uniform degradations. In addition, by leveraging explicit edge priors and region partitioning as guidance, we design a Structure-guided Residual Fusion (SGRF) module to selectively fuse shallow and deep features, thereby restoring degraded details and enhancing low-light textures. Extensive experiments demonstrate that the proposed network delivers superior qualitative and quantitative performance, with strong generalization to diverse extreme lighting conditions. The code is available at <jats:ext-link>https:\/\/github.com\/WindySprint\/DWMamba<\/jats:ext-link>.<\/jats:p>","DOI":"10.3389\/fnbot.2025.1676787","type":"journal-article","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T12:14:00Z","timestamp":1759407240000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DWMamba: a structure-aware adaptive state space network for image quality improvement"],"prefix":"10.3389","volume":"19","author":[{"given":"Wenjun","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuncai","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixiong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"107219","DOI":"10.1016\/j.engappai.2023.107219","article-title":"HFM: a hybrid fusion method for underwater image enhancement","volume":"127","author":"An","year":"2024","journal-title":"Eng. Appl. Artif. Intell"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2653","DOI":"10.1109\/TIP.2019.2951304","article-title":"Color channel compensation (3c): A fundamental pre-processing step for image enhancement","volume":"29","author":"Ancuti","year":"2019","journal-title":"IEEE Trans. Image Proc"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00119","article-title":"\u201cO-haze: a dehazing benchmark with real hazy and haze-free outdoor images,\u201d","author":"Ancuti","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-6596-9_30","article-title":"Retinexmamba: retinex-based mamba for low-light image enhancement","author":"Bai","year":"2024","journal-title":"arXiv preprint arXiv:2405.03349"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1109\/TPAMI.2020.2977624","article-title":"Underwater single image color restoration using haze-lines and a new quantitative dataset","volume":"43","author":"Berman","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B6","first-page":"97","article-title":"\u201cLearning photographic global tonal adjustment with a database of input\/output image pairs,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Bychkovsky","year":"2011"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212","article-title":"\u201cPre-trained image processing transformer,\u201d","author":"Chen","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B8","article-title":"Mambauie&sr: unraveling the ocean's secrets with only 2.8 flops","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2404.13884"},{"key":"B9","doi-asserted-by":"publisher","first-page":"4472","DOI":"10.1109\/TIP.2023.3286263","article-title":"Pugan: Physical model-guided underwater image enhancement using gan with dual-discriminators","volume":"32","author":"Cong","year":"2023","journal-title":"IEEE Trans. Image Proc"},{"key":"B10","article-title":"O-mamba: O-shape state-space model for underwater image enhancement","author":"Dong","year":"2024","journal-title":"arXiv preprint arXiv:2408.12816"},{"key":"B11","doi-asserted-by":"publisher","first-page":"9010120","DOI":"10.26599\/TST.2025.9010120","article-title":"Coevolutionary neural dynamics considering multiple strategies for nonconvex optimization","volume":"2025","author":"Fan","year":"2025","journal-title":"Tsinghua Sci. Technol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1109\/LSP.2014.2372333","article-title":"No-reference quality assessment of contrast-distorted images based on natural scene statistics","volume":"22","author":"Fang","year":"2014","journal-title":"IEEE Signal Process. Lett"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19944","article-title":"\u201cUnsupervised underwater image restoration: from a homology perspective,\u201d","author":"Fu","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B14","doi-asserted-by":"publisher","first-page":"111977","DOI":"10.1016\/j.knosys.2024.111977","article-title":"Ddformer: Dimension decomposition transformer with semi-supervised learning for underwater image enhancement","volume":"297","author":"Gao","year":"2024","journal-title":"Knowl. Based Syst"},{"key":"B15","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"B16","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv:2111.00396"},{"key":"B17","article-title":"Watermamba: visual state space model for underwater image enhancement","author":"Guan","year":"2024","journal-title":"arXiv preprint arXiv:2405.08419"},{"key":"B18","first-page":"222","article-title":"\u201cMambair: a simple baseline for image restoration with state-space model,\u201d","volume-title":"European Conference on Computer Vision","author":"Guo","year":"2025"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1109\/TPAMI.2010.168","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B20","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1109\/TCSVT.2023.3290363","article-title":"Non-uniform illumination underwater image restoration via illumination channel sparsity prior","volume":"34","author":"Hou","year":"2024","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIE.2025.3566731","article-title":"A momentum recurrent neural network for sparse motion planning of redundant manipulators with majorization-minimization","volume":"2025","author":"Huang","year":"2025","journal-title":"IEEE Trans. Ind. Electr"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3189630","article-title":"Underwater image enhancement via adaptive group attention-based multiscale cascade transformer","volume":"71","author":"Huang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B23","doi-asserted-by":"publisher","first-page":"125350","DOI":"10.1016\/j.eswa.2024.125350","article-title":"Underwater variable zoom: depth-guided perception network for underwater image enhancement","volume":"259","author":"Huang","year":"2025","journal-title":"Expert Syst. Appl"},{"key":"B24","article-title":"Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception","author":"Islam","year":"","journal-title":"arXiv preprint arXiv:2002.01155"},{"key":"B25","doi-asserted-by":"publisher","first-page":"3227","DOI":"10.1109\/LRA.2020.2974710","article-title":"Fast underwater image enhancement for improved visual perception","volume":"5","author":"Islam","year":"","journal-title":"IEEE Robot. Autom. Lett"},{"key":"B26","doi-asserted-by":"publisher","first-page":"4301","DOI":"10.1109\/TMM.2021.3115442","article-title":"Underwater image enhancement with lightweight cascaded network","volume":"24","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Multim"},{"key":"B27","doi-asserted-by":"publisher","first-page":"108324","DOI":"10.1016\/j.patcog.2021.108324","article-title":"Two-step domain adaptation for underwater image enhancement","volume":"122","author":"Jiang","year":"2022","journal-title":"Pattern Recognit"},{"key":"B28","doi-asserted-by":"publisher","first-page":"6584","DOI":"10.1109\/TCSVT.2022.3174817","article-title":"Target oriented perceptual adversarial fusion network for underwater image enhancement","volume":"32","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1109\/TAC.2022.3144135","article-title":"Gradient-based differential neural-solution to time-dependent nonlinear optimization","volume":"68","author":"Jin","year":"2022","journal-title":"IEEE Trans. Automat. Contr"},{"key":"B30","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1109\/TCSVT.2022.3208100","article-title":"A perception-aware decomposition and fusion framework for underwater image enhancement","volume":"33","author":"Kang","year":"2023","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00148","article-title":"\u201cSpectroformer: multi-domain query cascaded transformer network for underwater image enhancement,\u201d","author":"Khan","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"B32","doi-asserted-by":"publisher","first-page":"4985","DOI":"10.1109\/TIP.2021.3076367","article-title":"Underwater image enhancement via medium transmission-guided multi-color space embedding","volume":"30","author":"Li","year":"2021","journal-title":"IEEE Trans. Image Proc"},{"key":"B33","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/TIP.2019.2955241","article-title":"An underwater image enhancement benchmark dataset and beyond","volume":"29","author":"Li","year":"2019","journal-title":"IEEE Trans. Image Proc"},{"key":"B34","doi-asserted-by":"publisher","first-page":"4879","DOI":"10.1109\/TCSVT.2021.3114230","article-title":"Gudcp: generalization of underwater dark channel prior for underwater image restoration","volume":"32","author":"Liang","year":"2021","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"107462","DOI":"10.1016\/j.engappai.2023.107462","article-title":"Gccf: a lightweight and scalable network for underwater image enhancement","volume":"128","author":"Liu","year":"","journal-title":"Eng. Appl. Artif. Intell"},{"key":"B36","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1109\/TNNLS.2021.3106044","article-title":"Activated gradients for deep neural networks","volume":"34","author":"Liu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B37","doi-asserted-by":"publisher","first-page":"6602","DOI":"10.1109\/TCSVT.2025.3541429","article-title":"Liednet: a lightweight network for low-light enhancement and deblurring","volume":"35","author":"Liu","year":"2025","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B38","doi-asserted-by":"publisher","first-page":"11436","DOI":"10.1109\/TMC.2024.3397242","article-title":"A distributed competitive and collaborative coordination for multirobot systems","volume":"23","author":"Liu","year":"2024","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B39","doi-asserted-by":"publisher","first-page":"4922","DOI":"10.1109\/TIP.2022.3190209","article-title":"Twin adversarial contrastive learning for underwater image enhancement and beyond","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Trans. Image Proc"},{"key":"B40","article-title":"Hsidmamba: exploring bidirectional state-space models for hyperspectral denoising","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2404.09697"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00277","article-title":"\u201cL2uwe: a framework for the efficient enhancement of low-light underwater images using local contrast and multi-scale fusion,\u201d","author":"Marques","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops"},{"key":"B42","doi-asserted-by":"publisher","first-page":"108154","DOI":"10.1016\/j.optlaseng.2024.108154","article-title":"Fusion of multiscale gradient domain enhancement and gamma correction for underwater image\/video enhancement and restoration","volume":"178","author":"Mishra","year":"2024","journal-title":"Opt. Lasers Eng"},{"key":"B43","first-page":"302","article-title":"\u201cOsmosis: RGBD diffusion prior for underwater image restoration,\u201d","volume-title":"European Conference on Computer Vision","author":"Nathan","year":"2025"},{"key":"B44","doi-asserted-by":"publisher","first-page":"107445","DOI":"10.1016\/j.engappai.2023.107445","article-title":"Underwater image enhancement using adaptive standardization and normalization networks","volume":"127","author":"Park","year":"2024","journal-title":"Eng. Appl. Artif. Intell"},{"key":"B45","doi-asserted-by":"publisher","first-page":"3066","DOI":"10.1109\/TIP.2023.3276332","article-title":"U-shape transformer for underwater image enhancement","volume":"32","author":"Peng","year":"2023","journal-title":"IEEE Trans. Image Proc"},{"key":"B46","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1109\/TIP.2018.2813092","article-title":"Generalization of the dark channel prior for single image restoration","volume":"27","author":"Peng","year":"2018","journal-title":"IEEE Trans. Image Proc"},{"key":"B47","doi-asserted-by":"publisher","first-page":"5560","DOI":"10.1109\/TCSVT.2025.3530090","article-title":"Vmambair: visual state space model for image restoration","volume":"35","author":"Shi","year":"2025","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507","article-title":"\u201cPixel difference networks for efficient edge detection,\u201d","author":"Su","year":"2021","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B49","doi-asserted-by":"publisher","first-page":"108411","DOI":"10.1016\/j.engappai.2024.108411","article-title":"Inspiration: a reinforcement learning-based human visual perception-driven image enhancement paradigm for underwater scenes","volume":"133","author":"Wang","year":"2024","journal-title":"Eng. Appl. Artif. Intell"},{"key":"B50","doi-asserted-by":"publisher","first-page":"3538","DOI":"10.1109\/TIP.2013.2261309","article-title":"Naturalness preserved enhancement algorithm for non-uniform illumination images","volume":"22","author":"Wang","year":"2013","journal-title":"IEEE Trans. Image Proc"},{"key":"B51","doi-asserted-by":"publisher","first-page":"122710","DOI":"10.1016\/j.eswa.2023.122710","article-title":"A multi-level wavelet-based underwater image enhancement network with color compensation prior","volume":"242","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1109\/TIP.2023.3244647","article-title":"Domain adaptation for underwater image enhancement","volume":"32","author":"Wang","year":"2023","journal-title":"IEEE Trans. Image Proc"},{"key":"B53","doi-asserted-by":"publisher","first-page":"e2020E","DOI":"10.1029\/2020EA001604","article-title":"Classification of weather phenomenon from images by using deep convolutional neural network","volume":"8","author":"Xiao","year":"2021","journal-title":"Earth Space Sci"},{"key":"B54","doi-asserted-by":"publisher","first-page":"6062","DOI":"10.1109\/TIP.2015.2491020","article-title":"An underwater color image quality evaluation metric","volume":"24","author":"Yang","year":"2015","journal-title":"IEEE Trans. Image Proc"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00064","article-title":"\u201cUnderwater light field retention: neural rendering for underwater imaging,\u201d","author":"Ye","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3110575","article-title":"TEBCF: real-world underwater image texture enhancement model based on blurriness and color fusion","volume":"60","author":"Yuan","year":"2021","journal-title":"IEEE Trans. Geosci. Rem. Sens"},{"key":"B57","article-title":"Vmamba: visual state space model","author":"Yue","year":"2024","journal-title":"arXiv preprint arXiv:2401.10166"},{"key":"B58","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/j.neunet.2023.11.008","article-title":"Robust underwater image enhancement with cascaded multi-level sub-networks and triple attention mechanism","volume":"169","author":"Zhang","year":"","journal-title":"Neural Netw"},{"key":"B59","article-title":"Mamba-uie: Enhancing underwater images with physical model constraint","author":"Zhang","year":"","journal-title":"arXiv preprint arXiv:2407.19248"},{"key":"B60","doi-asserted-by":"publisher","first-page":"122546","DOI":"10.1016\/j.eswa.2023.122546","article-title":"Liteenhancenet: A lightweight network for real-time single underwater image enhancement","volume":"240","author":"Zhang","year":"","journal-title":"Expert Syst. Appl"},{"key":"B61","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1109\/TCSVT.2023.3299314","article-title":"Underwater image enhancement via weighted wavelet visual perception fusion","volume":"34","author":"Zhang","year":"","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"B62","doi-asserted-by":"publisher","first-page":"3997","DOI":"10.1109\/TIP.2022.3177129","article-title":"Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement","volume":"31","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Image Proc"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00791","article-title":"\u201cWavelet-based fourier information interaction with frequency diffusion adjustment for underwater image restoration,\u201d","author":"Zhao","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B64","article-title":"Rsdehamba: Lightweight vision mamba for remote sensing satellite image dehazing","author":"Zhou","year":"","journal-title":"arXiv preprint arXiv:2405.10030"},{"key":"B65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3346384","article-title":"Iacc: cross-illumination awareness and color correction for underwater images under mixed natural and artificial lighting","volume":"62","author":"Zhou","year":"","journal-title":"IEEE Trans. Geosci. Rem. Sens"},{"key":"B66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-023-01853-3","article-title":"Underwater camera: Improving visual perception via adaptive dark pixel prior and color correction","volume":"2023","author":"Zhou","year":"","journal-title":"Int. J. Comput. Vision"},{"key":"B67","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1109\/JOE.2022.3223733","article-title":"Underwater image enhancement method via multi-interval subhistogram perspective equalization","volume":"48","author":"Zhou","year":"","journal-title":"IEEE J. Oceanic Eng"},{"key":"B68","doi-asserted-by":"publisher","first-page":"4132","DOI":"10.1007\/s11263-024-01987-y","article-title":"Hclr-net: Hybrid contrastive learning regularization with locally randomized perturbation for underwater image enhancement","volume":"132","author":"Zhou","year":"","journal-title":"Int. J. Comput. Vision"},{"key":"B69","doi-asserted-by":"publisher","first-page":"7838","DOI":"10.1109\/TMM.2024.3372400","article-title":"A pixel distribution remapping and multi-prior retinex variational model for underwater image enhancement","volume":"26","author":"Zhou","year":"","journal-title":"IEEE Trans. Multim"},{"key":"B70","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1109\/JOE.2023.3275615","article-title":"Multicolor light attenuation modeling for underwater image restoration. IEEE J","volume":"48","author":"Zhou","year":"","journal-title":"Oceanic Eng"},{"key":"B71","doi-asserted-by":"publisher","first-page":"5442","DOI":"10.1109\/TIP.2022.3196546","article-title":"Underwater image enhancement with hyper-laplacian reflectance priors","volume":"31","author":"Zhuang","year":"2022","journal-title":"IEEE Trans. Image Proc"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1676787\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T12:14:02Z","timestamp":1759407242000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1676787\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,2]]},"references-count":71,"alternative-id":["10.3389\/fnbot.2025.1676787"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2025.1676787","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,2]]},"article-number":"1676787"}}