IEEE Transactions on Computational Imaging最新文献

{"title":"Gradient-Aware Gamma Adjustment for Robust Diffusion-Based Computational Imaging","authors":"Zhangjing Yang;Tangchun Yang;Rongjin Su;Pu Huang;Fanlong Zhang","doi":"10.1109/TCI.2026.3669384","DOIUrl":"https://doi.org/10.1109/TCI.2026.3669384","url":null,"abstract":"Restoring images degraded by spatially variant distortions remains a fundamental challenge in computational imaging. While diffusion-based methods like Denoising Diffusion with Preconditioned Guidance (DDPG) offer efficient solvers, they typically rely on a static, globally fixed trade-off between Back-Projection (BP) and Least-Squares (LS) guidance. This static scheduling prevents the sampling process from adapting to heterogeneous local signal-to-noise characteristics, often leading to suboptimal restoration in complex or mixed-content regions. We propose Gradient-Aware Gamma Adjustment (GAGA), a spatially adaptive framework that modulates the preconditioned guidance in a pixel-wise manner. By leveraging multi-scale gradient cues extracted from intermediate reconstructions, GAGA dynamically adjusts the BP–LS balance to better accommodate local structural variations. From a theoretical perspective, we refine the LS guidance by explicitly aligning it with the Gaussian likelihood score via the noise-dependent scaling factor <inline-formula><tex-math>$sigma _{e}^{-2}$</tex-math></inline-formula>. We further show that the resulting spatially adaptive preconditioner remains strictly positive definite under bounded modulation, guaranteeing well-posed and numerically stable guidance for ill-posed inverse problems. Extensive experiments on CelebA-HQ and ImageNet, as well as on spatially variant degradations and computational imaging tasks including super-resolution, inpainting, CT, and MRI reconstruction, demonstrate consistent improvements in both fidelity (PSNR) and perceptual quality (LPIPS) over static preconditioned baselines, without introducing noticeable computational overhead.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"630-645"},"PeriodicalIF":4.8,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ozone Cues Mitigate Reflected Downwelling Radiance in LWIR Absorption-Based Ranging","authors":"Unay Dorken Gallastegi;Wentao Shangguan;Vaibhav Choudhary;Akshay Agarwal;Hoover Rueda-Chacón;Martin J. Stevens;Vivek K Goyal","doi":"10.1109/TCI.2026.3668998","DOIUrl":"https://doi.org/10.1109/TCI.2026.3668998","url":null,"abstract":"Passive long-wave infrared (LWIR) absorption-based ranging relies on atmospheric absorption to estimate distances to objects from their emitted thermal radiation. First demonstrated decades ago for objects much hotter than the air and recently extended to scenes with low temperature variations, this ranging has depended on reflected radiance being negligible. Downwelling radiance is especially problematic, sometimes causing large inaccuracies. In two new ranging methods, we use characteristic features from ozone absorption to estimate the contribution of reflected downwelling radiance. The quadspectral method gives a simple closed-form range estimate from four narrowband measurements, two at a water vapor absorption line and two at an ozone absorption line. The hyperspectral method uses a broader spectral range to improve accuracy while also providing estimates of temperature, emissivity profiles, and contributions of downwelling from a collection of zenith angles. Experimental results demonstrate improved ranging accuracy, in one case reducing error from over 100 m when reflected light is not modeled to 6.8 m with the quadspectral method and 1.2 m with the hyperspectral method.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"587-600"},"PeriodicalIF":4.8,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reflection-Mode Multi-Slice Fourier Ptychographic Tomography","authors":"Jiabei Zhu;Tongyu Li;Hao Wang;Yi Shen;Guorong Hu;Lei Tian","doi":"10.1109/TCI.2026.3668501","DOIUrl":"https://doi.org/10.1109/TCI.2026.3668501","url":null,"abstract":"Diffraction tomography (DT) has been widely explored in transmission-mode configurations, enabling high-resolution, label-free 3D imaging. However, industrial metrology applications, such as semiconductor inspection, typically involve opaque or highly reflective substrates (e.g., silicon or metal), necessitating a reflection-mode imaging configuration. In this work, we introduce reflection-mode Multi-Slice Fourier Ptychographic Tomography (rMS-FPT) that achieves high-resolution, volumetric imaging of multi-layered, strongly scattering samples on reflective substrates. We develop a reflection-mode multi-slice beam propagation method (rMSBP) to model multiple scattering and substrate interactions, enabling precise 3D reconstruction. By incorporating darkfield measurements, rMS-FPT enhances resolution beyond the traditional brightfield limit and provides sub-micrometer lateral resolution while achieving optical sectioning. We validate rMS-FPT through numerical simulations on a four-layer resolution target and experimental demonstrations using a reflection-mode LED array microscope. Experiments on a two-layer resolution target and a multi-layer scattering sample confirm the method's effectiveness. Our optimized implementation enables rapid imaging, covering a <inline-formula><tex-math>${1.2,{mathrm{mm}} times 1.2},{mathrm{mm}}$</tex-math></inline-formula> area in 1.6 seconds, reconstructing over <inline-formula><tex-math>$10^{9}$</tex-math></inline-formula> voxels within a <inline-formula><tex-math>${0.4},{{mathrm{mm}}^{3}}$</tex-math></inline-formula> volume. This work represents a significant step in extending DT to reflection-mode configurations, providing a robust and scalable solution for 3D metrology and industrial inspection.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"548-557"},"PeriodicalIF":4.8,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Kernel-Guided Transformer-CNN Network for Low-Cost Pathological Whole Slide Imaging: Hardware-Algorithm Synergy","authors":"Haichao Yang;Tao Luo;Yuqing Zhang;Jiyun Yang;Changbao Yan;Chenggui Zhang;Yi Li;Runbiao Yang","doi":"10.1109/TCI.2026.3668106","DOIUrl":"https://doi.org/10.1109/TCI.2026.3668106","url":null,"abstract":"High-cost commercial digital pathology systems limit their accessibility in resource-constrained healthcare settings. While low-cost alternatives with only XY-axis stages reduce expenses, they often produce blurry images due to defocus (blur induced by hardware constraints leading to poor focus). We present a hardware-algorithm co-design solution that combines simplified, low-cost hardware with targeted intelligent software to address this problem. Our method uses a basic XY-axis scanning system and a three-step automated pipeline: a lightweight model first classifies defocus levels, then estimates “blur kernels” (mathematical representations of blur), and finally uses our Kernel-Guided Transformer-CNN Network (KGTCN) to restore clarity. Tests on clinical datasets show the system generates diagnostic-grade images—reaching up to 38.76 dB PSNR (image sharpness index) and 0.968 SSIM (similarity to clear images), even 35.53 dB/0.941 for severely blurred ones—while processing 43.45 images per second (FPS) with modest resources. Our Global Optimization Registration Algorithm (GORA) also significantly reduces stitching alignment errors, eliminating cumulative misalignments at tile boundaries. This “simplified hardware + targeted software” approach enables sub-$10k systems to produce high-quality Whole Slide Images (WSI), advancing accessible digital pathology in underserved regions.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"558-572"},"PeriodicalIF":4.8,"publicationDate":"2026-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast Electrical Impedance Tomography With Hybrid Priors","authors":"Shuaikai Shi;Ruiyuan Kang;Panos Liatsis","doi":"10.1109/TCI.2026.3664753","DOIUrl":"https://doi.org/10.1109/TCI.2026.3664753","url":null,"abstract":"Electrical impedance tomography (EIT) is a non-ionizing and non-invasive imaging technique that reconstructs the electrical conductivity patterns within an object. Due to its low cost, real-time nature and portability, it is popular in a variety of applications ranging from medical imaging to industrial monitoring and geoscience. When electrical currents are injected, EIT reveals the internal conductivity distribution through boundary voltage measurements. However, EIT image reconstruction is an ill-posed problem due to the significant disparity between sparse boundary voltage measurements and the desired high-resolution conductivity images. Both conventional and deep learning approaches have been developed to address this challenge, primarily through spatial regularization and image regression techniques. While conventional methods employing regularizers can generate physically plausible conductivity distributions, their linear nature often limits reconstruction accuracy. Deep learning models achieve superior results but require substantial training datasets. In this work, we propose a novel iterative conductivity image reconstruction method for EIT, termed PnPEIT, which integrates both handcrafted and plug-and-play (PnP) priors within the alternating direction method of multipliers (ADMM) framework. Specifically, the objective function of PnPEIT contains the voltage reconstruction error and a sparse constraint, a graph regularization, and a PnP prior to the conductivity images. Next, the PnP prior term is optimized by a denoising operator and implemented by block-matching and 3D filtering (BM3D) or pre-trained denoising networks. Through alternating iterations, the algorithm converges rapidly and the desired conductivity image is obtained. Moreover, we provide a simple proof that the graph Laplacian regularization is not only equivalent to the non-local means denoising algorithm, but also accelerates convergence. Experiments on both synthetic and real-world datasets emphasize the advantage of the proposed method over traditional and cutting-edge EIT image reconstruction approaches.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"573-586"},"PeriodicalIF":4.8,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11396012","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Snapshot Compressive Hyperspectral Image Reconstruction via Complementary Priors","authors":"Yaning Zang;Min Huang;Lianru Gao;Lina Zhuang","doi":"10.1109/TCI.2026.3664689","DOIUrl":"https://doi.org/10.1109/TCI.2026.3664689","url":null,"abstract":"Coded aperture snapshot spectral imaging (CASSI) systems compressively project 3D hyperspectral data onto 2D measurements, offering high imaging speed and data efficiency. However, existing CASSI reconstruction algorithms still suffer from suboptimal reconstruction quality due to the ill-posed nature of hyperspectral compressive sensing reconstruction, which demands effective prior modeling. This paper proposes a novel reconstruction framework that integrates multiple complementary priors, jointly modeling spectral low-rankness, spatial nonlocal self-similarity, and deep image priors to comprehensively capture the intrinsic structure of hyperspectral images across spectral and spatial domains. By combining the strengths of model-based and data-driven priors, the proposed method achieves both strong generalization and expressive capacity. To tackle the optimization challenges posed by multiple regularization terms and parameters, an efficient ADMM-based solver is developed, which decomposes the problem into subproblems with closed-form solutions or those solvable via plug-and-play denoisers. In addition, an adaptive noise estimation mechanism is introduced to automatically tune the regularization parameters, eliminating the need for manual parameter adjustment. Extensive experiments demonstrate that the proposed method consistently outperforms state-of-the-art approaches in terms of reconstruction accuracy and robustness across multiple datasets.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"519-532"},"PeriodicalIF":4.8,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"KAN-KT-Unet: Keystone Transform-Based Method for ISAR Range Migration Compensation and Auto-Focusing","authors":"Zhipeng Qing;Shunsheng Zhang;Jing Yang;Zhijin Wen;Youlei Pu","doi":"10.1109/TCI.2026.3657291","DOIUrl":"https://doi.org/10.1109/TCI.2026.3657291","url":null,"abstract":"Clear inverse synthetic aperture radar (ISAR) images are essential for applications such as area surveillance and target recognition. Achieving high-resolution ISAR imaging often requires wide signal bandwidth and significant target rotation during the imaging period. However, large rotation angles usually induce range migration, complicating the imaging process. While existing methods typically employ the keystone transform to correct range migration, they may fail under complex maneuvering conditions. Additionally, these methods usually neglect azimuth defocusing, which significantly impacts ISAR imaging clarity. This study addresses these challenges by proposing a KAN-KT-Unet model. This model can compensate for range migration using parametric resampling and keystone transform, which accounts for first-order and second-order rotational components. An adaptive parameter extraction network based on the Kolmogorov-Arnold network (KAN) replaces traditional iterative search processes, improving efficiency and accuracy. Additionally, azimuth defocusing is mitigated through an enhanced Unet architecture with reduced channels, balancing resolution improvement and noise suppression. Simulation and measured-data experiments validate the effectiveness of the proposed method, demonstrating its superior generalization and noise resistance compared to traditional algorithms. These results highlight the KAN-KT-Unet model's potential for improving ISAR imaging quality under maneuvering-target and noisy conditions, making it suitable for practical applications.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"457-469"},"PeriodicalIF":4.8,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wide Color Gamut Imaging System Using a Multispectral Image Sensor for a Mobile Device","authors":"Woo-Shik Kim;Satoshi Nagayama;Jisu Ohk;Sangyoon Lee;Jaesung Lee;Youngshin Kwak;Hyochul Kim","doi":"10.1109/TCI.2026.3663972","DOIUrl":"https://doi.org/10.1109/TCI.2026.3663972","url":null,"abstract":"In this paper a system for a mobile device to generate a wide color gamut image is proposed. A RGB camera on a smartphone is combined with a multispectral image sensor, which is fabricated on top of a complementary metal-oxide semiconductor image sensor for a mobile device, capturing scenes with 16 spectral bands. Images from these sensors are fused using a color transfer technique to leverage the accurate color reproduction capability of the multispectral image sensor while preserving the image structures in the RGB image. It is claimed that the proposed multispectral image sensor improved color reproduction accuracy by 25% compared to a mobile RGB sensor, and the proposed system effectively produce a high-resolution wide color gamut image with high color fidelity.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"505-518"},"PeriodicalIF":4.8,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Resolution Vortex Electromagnetic Wave Radar Sparse Imaging Using Efficient 2D-SLIM","authors":"Ting Yang;Hongyin Shi;Da Liu;Hu Hao;Liying Tian;Xing Wang;Jiuru Wang","doi":"10.1109/TCI.2026.3663911","DOIUrl":"https://doi.org/10.1109/TCI.2026.3663911","url":null,"abstract":"Vortex electromagnetic wave (VEMW) radar, leveraging orbital angular momentum (OAM) modes for azimuthal information encoding, has emerged as a promising technology for high-resolution staring imaging. However, its performance is fundamentally constrained by the Bessel function modulation (BFM) effect and limited OAM mode availability, leading to azimuth-range coupling artifacts and energy inefficiency. Existing compressive sensing (CS) methods, particularly conventional sparse recovery techniques, struggle with sidelobe interference, noise sensitivity, and computational bottlenecks. To address these challenges, this paper proposes an efficient two-dimensional sparse learning via iterative minimization (2D-SLIM) framework, integrating physics-driven preprocessing with accelerated optimization. First, we establish a comprehensive VEMW radar signal model that explicitly incorporates BFM effects and OAM mode orthogonality. Second, building upon the beam steering strategy, we introduce an explicit analytical compensation factor to suppress the azimuth-dependent energy attenuation caused by the squared Bessel term, thereby restoring the Fourier duality between azimuth angles and OAM mode indices. Third, we develop a dimensionally consistent 2D conjugate gradient least squares (2D-CGLS) algorithm, incorporating adaptive Barzilai-Borwein step sizes and non-convex group sparsity regularization. By leveraging Kronecker product factorization and matrix-form operations, the framework eliminates redundant vector-to-matrix conversions. Extensive numerical and EM simulations demonstrate that the proposed method achieves an improvement of more than 20% in image correlation value and a convergence rate more than 30% faster, while maintaining robust imaging performance under challenging conditions of limited OAM modes (e.g., <inline-formula><tex-math>${{|}}alpha {{|}} leq 20$</tex-math></inline-formula>) and low SNR (down to -5 dB), outperforming several established CS techniques.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"614-629"},"PeriodicalIF":4.8,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning-Based Probabilistic Subarray Switching for Robust Low-Cost Interferometric Imaging","authors":"Jianhua Wang;Mohammed Nabil El Korso;Lucien Bacharach;Pascal Larzabal","doi":"10.1109/TCI.2026.3663899","DOIUrl":"https://doi.org/10.1109/TCI.2026.3663899","url":null,"abstract":"Computational cost poses a significant challenge in next-generation interferometric imaging systems. In these systems, the large number of antennas makes it impractical to process all measurements simultaneously due to computational capacity constraints. To reduce the computational burden while preserving image reconstruction quality, we propose a subarray switching strategy that utilizes fewer antennas and different antenna configurations. To take into consideration the influence of the image reconstruction algorithm on the design of the subarray switching pattern and to fully exploit the flexibility of the switching strategy, we propose a probabilistic deep learning-based method for designing antenna switching patterns, named by Probabilistic Antenna Switcher (PAS). In addition to the computational challenge, interferometric systems are also particularly sensitive to the presence of radio frequency interferences (RFI), which heavily affects imaging quality. In order to address this issue, we show that it is possible to combine the proposed PAS with a RFI detection module. Specifically, this module is a neural network that is trained to identify and minimize the impact of RFI-affected antennas in the subarray selection process. This results in a RFI-aware PAS (RaPAS), which balances computational efficiency, imaging quality, and robustness against RFI.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"12 ","pages":"491-504"},"PeriodicalIF":4.8,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}