IEEE Journal of Selected Topics in Signal Processing最新文献_第7页

Reprojection-Guided Non-Line-of-Sight Imaging Under Irregular Undersampling 不规则欠采样下的重投影制导非视线成像

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-10-10 DOI: 10.1109/JSTSP.2025.3620710

Xingyu Cui;Huanjing Yue;Jingyu Yang

{"title":"Reprojection-Guided Non-Line-of-Sight Imaging Under Irregular Undersampling","authors":"Xingyu Cui;Huanjing Yue;Jingyu Yang","doi":"10.1109/JSTSP.2025.3620710","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3620710","url":null,"abstract":"Non-line-of-sight (NLOS) imaging enables the visualization of scenes outside the direct line of sight, with broad potential applications in robotic vision, autonomous navigation, disaster relief, and medical diagnostics. However, most existing NLOS methods depend on densely sampled transients collected from large and continuous relay surfaces, which restricts their applicability in real-world scenarios where the available relay surfaces are typically sparse, irregular, or fragmented. To overcome the challenges posed by irregular undersampling in NLOS imaging, we propose a reprojection-guided framework designed for robust performance in such scenarios. At its core is a transient recovery network that reconstructs denoised, fully-sampled transients from noisy, undersampled inputs, thereby mitigating the inherent ill-posedness of the problem. To further enhance recovery quality and improve generalization, we develop a range-space reprojection (RSRP) module that extracts intrinsic information from the measurements and generates explicit guidance. This guidance is leveraged by the spatio-temporal modulation (STM) blocks, which adaptively control its influence to enhance transient denoising and recovery. Extensive experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches, showing strong generalization across diverse relay surfaces and marking a substantial step toward practical and robust NLOS imaging.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1739-1751"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148513690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

F$^mathbf {2}$Mamba: Frequency-Aware and Flexibly-Unfolded Mamba for Compressed Sensing Mamba：用于压缩感知的频率感知和灵活展开的Mamba

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-09-10 DOI: 10.1109/JSTSP.2025.3608600

Hongping Gan;Feiyang Shen

{"title":"F$^mathbf {2}$Mamba: Frequency-Aware and Flexibly-Unfolded Mamba for Compressed Sensing","authors":"Hongping Gan;Feiyang Shen","doi":"10.1109/JSTSP.2025.3608600","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3608600","url":null,"abstract":"Existing Deep Unfolding Networks (DUNs) typically employ a series of repeated network modules to unfold traditional algorithms for compressed sensing (CS), resulting in redundant feature information extracted at different iterative stages. Additionally, the neglect of frequency-domain information limits the feature extraction efficiency of DUNs. To address these issues, we propose a Flexibly-Unfolded and Frequency-Aware Mamba network for CS, called F<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>Mamba. Specifically, the proposed F<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>Mamba integrates a sequence of Flexible Unfolding Mamba Satge (FUMSs) for iterative image recovery. Each FUMS flexibly unfolds one iterative step of the homotopy algorithm through a tunable architecture comprising two L-Mamba and a Frequency Prior Extraction Block (FPEB), enabling the perception of image features at different scale space. The L-Mamba, primarily composed of cross Mamba blocks, establishes global receptive fields at multiple scales while enhancing local information perception through a cross mechanism. Meanwhile, the FPEB enhances the extraction of frequency-domain priors within the mathematical framework of homotopy algorithms. Finally, we introduce a hierarchical feature complementarity module to integrate shallow image patterns and deep semantic abstractions across the FUMSs, thereby obtaining the reconstructed image. Experimental results demonstrate that, compared to other state-of-the-art methods, our proposed F<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>Mamba achieves superior performance in image quality metrics, such as SSIM and PSNR, as well as in visual perception.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1668-1681"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Waveformer: A Frequency-Aware Transformer-CNN Hybrid for Hyperspectral Image Demosaicing 波形发生器：用于高光谱图像去马赛克的频率感知变压器- cnn混合

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-10-14 DOI: 10.1109/JSTSP.2025.3620712

Junwei Xu;Mengzu Liu;Shilong Zhang;Fangfang Wu;Tao Huang;Weisheng Dong

{"title":"Waveformer: A Frequency-Aware Transformer-CNN Hybrid for Hyperspectral Image Demosaicing","authors":"Junwei Xu;Mengzu Liu;Shilong Zhang;Fangfang Wu;Tao Huang;Weisheng Dong","doi":"10.1109/JSTSP.2025.3620712","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3620712","url":null,"abstract":"Hyperspectral image (HSI) demosaicing plays a critical role in reconstructing full-resolution HSIs from multispectral filter array (MSFA) acquisitions. Although recent deep-learning approaches based on CNNs and Transformers have achieved significant improvements, a systematic understanding of how these architectures behave across different frequency components remains limited. To address this limitation, we perform a comprehensive frequency-aware analysis with wavelet decomposition, systematically revealing that Transformers excel at modeling low-frequency global structures, whereas CNNs are superior for reconstructing high-frequency details within the unique context of HSI demosaicing. Motivated by this principled insight, we propose <bold>Waveformer</b>, a novel frequency-aware hybrid framework that explicitly decomposes the HSI into low- and high-frequency components using wavelet transform and assigns their reconstruction tasks to optimally suited architectures: Transformers for low-frequency modeling and CNNs for high-frequency enhancement. Furthermore, to counteract ambiguity in traditional attention mechanisms caused by softmax normalization, we introduce a <bold>Self-Calibration Attention</b> mechanism that adaptively calibrates each token’s self-identity across spatial and spectral dimensions, thereby enhancing the model’s discriminative power and suppressing interactions from irrelevant tokens. Extensive experiments conducted on multiple benchmark datasets validate the effectiveness of our design. Our method consistently outperforms state-of-the-art baselines, demonstrating strong generalization ability and enhanced reconstruction quality across diverse scenes and spectral configurations.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1752-1766"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rehazing for Dehazing: A Physics-Guided Parametric Augmentation Net 用于除雾的复原：物理导向的参数增强网络

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-10-27 DOI: 10.1109/JSTSP.2025.3626262

Chih-Ling Chang;Fu-Jen Tsai;Ziling Huang;Lin Gu;Chia-Wen Lin

{"title":"Rehazing for Dehazing: A Physics-Guided Parametric Augmentation Net","authors":"Chih-Ling Chang;Fu-Jen Tsai;Ziling Huang;Lin Gu;Chia-Wen Lin","doi":"10.1109/JSTSP.2025.3626262","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3626262","url":null,"abstract":"Image dehazing in real-world scenarios remains challenging due to the significant domain gap between synthetic and real hazy images, which often degrades the performance of dehazing models. Constructing real-world hazy-clean image pairs is particularly difficult, as it requires capturing scenes under identical conditions with and without haze. To address this limitation, we propose a Physics-guided Parametric Augmentation Network (PANet) that synthesizes realistic hazy-clean training pairs to boost dehazing performance in real-world applications. PANet comprises two key components: (1) a Haze-to-Parameter Mapper (HPM) that projects input hazy images into a physics-based parametric space encoding haze characteristics, and (2) a Parameter-to-Haze Mapper (PHM) that reconstructs hazy images from resampled haze parameter maps. By independently resampling pixel-level parameter maps in the physics space, PANet can generate diverse hazy images with physically interpretable haze properties not seen in the original training data. Experimental results demonstrate that PANet significantly enhances existing hazy image benchmarks and improves the generalization performance of state-of-the-art dehazing models.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1782-1795"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148513688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Robust Frequency Domain-Generalized Network for Multispectral Pansharpening 多谱泛锐化的鲁棒频域广义网络

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-10-14 DOI: 10.1109/JSTSP.2025.3620709

Shen Xu;Shengwei Zhong;Chen Gong

{"title":"A Robust Frequency Domain-Generalized Network for Multispectral Pansharpening","authors":"Shen Xu;Shengwei Zhong;Chen Gong","doi":"10.1109/JSTSP.2025.3620709","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3620709","url":null,"abstract":"Multispectral pansharpening combines high-resolution panchromatic images and low-resolution multispectral images to generate high-resolution multispectral images. Existing deep learning-based pansharpening methods have been shown to outperform traditional ones by better preserving spatial and spectral details. However, most existing deep learning-based methods rely heavily on large amounts of training data from a single satellite, and their performance deteriorates significantly when applied to testing data from different satellites. The generalization problem of pansharpening methods is a challenge due to the shift of data distribution from training to testing data. A domain-generalized approach capable of handling cross-satellite scenarios would greatly reduce training costs and enhance practical applicability. Thus, we proposed a novel robust frequency domain-generalized pansharpening network (RFDGNet). RFDGNet incorporates frequency decomposition to better capture domain invariant characteristics, along with an adversarial training strategy. Specifically, RFDGNet consists of three specialized modules: the global dynamic spectral extractor, which dynamically learns satellite-specific styles based on low-frequency global information; the gradient-adaptive high-frequency enhancer, which refines spatial details through gradient analysis and wavelet decomposition; and the spectral enhancement module for spectral information preservation. Furthermore, we design a novel domain generalization strategy, which includes a new adversarial loss to improve the network and employ misleading domain labels to guide the network in learning domain-invariant representations. Experiments on both in-domain and cross-domain pansharpening scenarios show significant advantages in both accuracy and generalization.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1724-1738"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148513692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IEEE Signal Processing Society Publication Information IEEE信号处理学会出版物信息

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2026-02-06 DOI: 10.1109/JSTSP.2026.3658788

引用次数: 0

Enhancing Underwater Imaging With 4-D Light Fields: Dataset and Method 利用四维光场增强水下成像：数据集与方法

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-07-16 DOI: 10.1109/JSTSP.2025.3589758

Yuji Lin;Junhui Hou;Xianqiang Lyu;Qian Zhao;Deyu Meng

{"title":"Enhancing Underwater Imaging With 4-D Light Fields: Dataset and Method","authors":"Yuji Lin;Junhui Hou;Xianqiang Lyu;Qian Zhao;Deyu Meng","doi":"10.1109/JSTSP.2025.3589758","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3589758","url":null,"abstract":"In this paper, we delve into the realm of 4-D light fields (LFs) to enhance underwater imaging plagued by light absorption, scattering, and other challenges. Contrasting with conventional 2-D RGB imaging, 4-D LF imaging excels in capturing scenes from multiple perspectives, thereby indirectly embedding geometric information. This intrinsic property is anticipated to effectively address the challenges associated with underwater imaging. By leveraging both explicit and implicit depth cues present in 4-D LF images, we propose a progressive, mutually reinforcing framework for underwater 4-D LF image enhancement and depth estimation. The entire framework decomposes this complex task, iteratively optimizing the enhanced image and depth information to progressively achieve optimal enhancement results. More importantly, we construct the first 4-D LF-based underwater image dataset for quantitative evaluation and supervised training of learning-based methods, comprising 75 underwater scenes with multiple views and 3675 high-resolution 2 K pairs. To craft vibrant and varied underwater scenes, we build underwater environments with various objects and adopt several types of degradation. Through extensive experimentation, we showcase the potential and superiority of 4-D LF-based underwater imaging vis-a-vis traditional 2-D RGB-based approaches. Moreover, our method effectively corrects color bias and achieves state-of-the-art performance.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1617-1631"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Editorial: High-Dimensional Imaging: Emerging Challenges and Advances in Reconstruction and Restoration 社论：高维成像：重建和恢复的新挑战和进展

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2026-02-06 DOI: 10.1109/JSTSP.2026.3657475

Zhiyuan Zha;Saiprasad Ravishankar;Chen Zhao;Hassan Mansour;Giuseppe Valenzise;Ce Zhu;Alex C. Kot

引用次数: 0

Normalize-and-Realign: Controllable Image Enhancement Across Multiple Exposure Levels 归一化和重新调整：可控制的图像增强跨多个曝光水平

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-06-25 DOI: 10.1109/JSTSP.2025.3583179

Jiahao Wu;Dandan Zhan;Xing Luo;Zhi Jin

{"title":"Normalize-and-Realign: Controllable Image Enhancement Across Multiple Exposure Levels","authors":"Jiahao Wu;Dandan Zhan;Xing Luo;Zhi Jin","doi":"10.1109/JSTSP.2025.3583179","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3583179","url":null,"abstract":"The objective of image enhancement is to improve the visual quality of images. It is an ill-posed task that inherently allows for multiple enhanced versions to be obtained from a given image. However, prevailing image enhancement methods yield a deterministic result for each low-quality input, disregarding different preferences and requirements. To address this issue, we propose a Reference-guided Image Enhancement Network (RIENet), which employs a normalize-and-realign paradigm for achieving multi-exposure image enhancement with precise control over brightness and color. Specifically, RIENet comprises two subnets: an Exposure Normalizing Subnet for normalizing inputs, and a reference-guided Image Realigning Subnet for realigning the normalized images according to reference images. By assigning different reference images, our method is capable of producing customized enhanced images with precise control over brightness and color faithful to the reference image. Extensive experiments demonstrate that the proposed method achieves state-of-the-art in both qualitative and quantitative results, and is able to generate training data for other low-level and high-level vision tasks. Furthermore, the potential of RIENet for video enhancement is also exhibited. To the best of our knowledge, RIENet is the first attempt to introduce reference images as guidance for achieving controllable image enhancement across multiple exposure levels.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1589-1602"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semantic-Guided Diffusion Sampling: A Generalized Strategy for Enhancing Object Segmentation Oriented Multimodal Image Fusion 语义引导扩散采样：一种增强面向目标分割的多模态图像融合的通用策略

IF 8.5 1区工程技术

IEEE Journal of Selected Topics in Signal Processing Pub Date : 2025-12-01 Epub Date: 2025-06-25 DOI: 10.1109/JSTSP.2025.3583188

Yu Shi;Yu Liu;Juan Cheng;Huafeng Li;Xun Chen

{"title":"Semantic-Guided Diffusion Sampling: A Generalized Strategy for Enhancing Object Segmentation Oriented Multimodal Image Fusion","authors":"Yu Shi;Yu Liu;Juan Cheng;Huafeng Li;Xun Chen","doi":"10.1109/JSTSP.2025.3583188","DOIUrl":"https://doi.org/10.1109/JSTSP.2025.3583188","url":null,"abstract":"Diffusion models have demonstrated impressive generative capabilities in various computer vision tasks, providing a novel technological approach to the study of multimodal image fusion. However, existing diffusion model-based multimodal image fusion methods still fail to address the problem of concentrating exclusively on the fusion process itself while neglecting downstream tasks. In this paper, we propose a semantic-guided diffusion sampling strategy that enhances the performance of existing multimodal image fusion methods in target regions by incorporating downstream semantic segmentation tasks, thereby improving both fusion quality and practical applicability. Specifically, our method consists of two primary steps. First, we select an existing multimodal image fusion method and utilize its fusion results to pre-train a fusion diffusion model, thereby ensuring that the performance of the diffusion model aligns with that of the selected method. Subsequently, we use the proposed semantic-guided diffusion sampling strategy to incorporate target region information into the diffusion sampling process in the form of gradients derived from a trained segmentation network. By incorporating semantic information from image segmentation into the diffusion framework, our approach enables the model to focus more on target regions during the generation process, thereby enhancing the fusion performance of existing methods in those areas. Experiments on brain tumor segmentation and infrared-visible road traffic multimodal datasets demonstrate the effectiveness of the proposed strategy and its potential for practical applications.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 8","pages":"1603-1616"},"PeriodicalIF":8.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148513685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0