IEEE Transactions On Image Processing[JOURNAL]
Sun
200 papers
DA2-LiDAR: A Generic Density-Adaptive Framework for Unsupervised Domain Adaptation in LiDAR Segmentation.
Chen Y, Sun R, Li W … +4 more , Luo N, Wang Y, Zhang T, Wu F
IEEE Trans Image Process · 2026 · PMID 42139124 · Publisher ↗
This paper addresses the critical challenge of domain adaptation for LiDAR-based semantic segmentation, particularly the significant density disparities that emerge when transferring models from synthetic to real-world e...
This paper addresses the critical challenge of domain adaptation for LiDAR-based semantic segmentation, particularly the significant density disparities that emerge when transferring models from synthetic to real-world environments. We present DA2-LiDAR, a novel density-adaptive domain adaptation framework that bridges domain gaps through the construction of intermediate domains with density-varying point distributions. Our approach employs a simple yet effective masking strategy that systematically reduces density discrepancies between domains while extracting more effective supervisory signals, as well as preserving critical semantic information. The framework consists of three key components: (1) a Density Adaptation Module that establishes a continuous spectrum of intermediate domains through dataset-agnostic masking operations; (2) a Contextual Consistency Module that enforces relational coherence across differently masked variants of the same scan at varying degrees, providing additional supervision signals, enhancing the model's ability to extract features; and (3) a Semantic Preservation Module that mitigates information loss in heavily masked scans by reconstructing domain-specific data distributions. Extensive experiments on synthetic-to-real and other benchmarks demonstrate that DA2-LiDAR consistently outperforms state-of-the-art methods, achieving significant improvements in cross-domain generalization without requiring dataset-specific prior knowledge or introducing computational overhead.
RAW-CLIP Fusion: Unleashing Semantic-Aware Denoising for Sensor-Agnostic Low-Light Imaging.
Qiao M, Jiang J, Ma Q … +3 more , Zhao Z, Hou J, Ma J
IEEE Trans Image Process · 2026 May · PMID 42139123 · Publisher ↗
Denoising images captured under extreme low-light conditions remains a persistent challenge in computational photography, primarily due to low signal-to-noise ratios and sensor-specific noise characteristics. These varia...
Denoising images captured under extreme low-light conditions remains a persistent challenge in computational photography, primarily due to low signal-to-noise ratios and sensor-specific noise characteristics. These variations often require persensor noise calibration to achieve effective denoising. Although recent calibration-free methods aim to reduce this dependency through synthetic noise modeling or few-shot fine-tuning, their performance often degrades in extreme low-light scenarios across different sensors due to mismatches between synthetic and real-world noise. To address this gap, we introduce CLIP-Guided Denoising (CLD), the first framework to leverage large-scale vision models pretrained on sRGB images for cross-domain feature fusion, effectively guiding RAW image denoising across diverse sensors. Although not trained on RAW data, CLIP embeddings offer semantically robust and noise-invariant features that help guide the denoising network to focus on the underlying image content rather than fitting to specific noise distributions. Extensive experiments on the SID and ELD datasets demonstrate that CLD achieves state-of-the-art performance in calibration-free settings, significantly outperforming prior methods under extreme low-light conditions and achieving robust generalization across unseen sensor domains.
Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation.
You L, Wu Z, Liu W … +5 more , Yang X, Cheng J, Zhou W, Veeravalli B, Lin G
IEEE Trans Image Process · 2026 · PMID 42133516 · Publisher ↗
Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data. They usually focus on the 3D doma...
Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data. They usually focus on the 3D domain only, without leveraging the complementary nature of 2D and 3D data. Besides, some methods extend original labels or generate pseudo labels to guide the training, but they often fail to fully use these labels or address the noise within them. Meanwhile, the emergence of comprehensive and adaptable foundation models has offered effective solutions for segmenting 2D data. Leveraging this advancement, we present a novel approach that maximizes the utility of sparsely available 3D annotations by incorporating segmentation masks generated by 2D foundation models. We further propagate the 2D segmentation masks into the 3D space by establishing geometric correspondences between 3D scenes and 2D views. We extend the highly sparse annotations to encompass the areas delineated by 3D masks, thereby substantially augmenting the pool of available labels. Furthermore, we apply confidence- and uncertainty-based consistency regularization on augmentations of the 3D point cloud and select the reliable pseudo labels, which are further spread on the 3D masks to generate more labels. This innovative strategy bridges the gap between limited 3D annotations and the powerful capabilities of 2D foundation models, ultimately improving the performance of 3D weakly supervised segmentation.
Uncertainty-Driven Generative Prior Learning for Sparse Model-Guided Hyperspectral Image Fusion.
Xu J, Feng T, Fang Z … +6 more , Wu F, Dong L, Huang T, Yang Z, Dong W, Li X
IEEE Trans Image Process · 2026 · PMID 42133515 · Publisher ↗
As an alternative to acquiring high-resolution hyperspectral images (HR-HSI), Hyperspectral Image Fusion (HIF) aims to recover clean HR-HSIs by fusing degraded low spatial resolution hyperspectral images and high spatial...
As an alternative to acquiring high-resolution hyperspectral images (HR-HSI), Hyperspectral Image Fusion (HIF) aims to recover clean HR-HSIs by fusing degraded low spatial resolution hyperspectral images and high spatial resolution multispectral images. Among existing HIF approaches, model-guided HIF methods stand out by integrating physical degradation constraints with the learning capabilities of data-driven networks. However, most of them learn deep priors only from degraded-clean pairs without degradation-free knowledge, making them struggle with severe or unseen degradations. To address these issues, we propose a Vector-Quantized Prior-Guided Network (VPG-Net), an unfolding-based HIF framework enhanced by sparse representation and novel uncertainty-driven generative priors. Specifically, VPG-Net unfolds the Maximum A Posteriori (MAP) estimation with a sparse representation model into an uncertainty-aware VQ prior-guided network implementation. Within this framework, the sparse representation prior is integrated into the MAP formulation to improve noise resistance. As the core of our method, we leverage a high-quality vector-quantized (VQ) prior, which serves as a powerful degradation-free generative prior for the HIF process. We pre-train a discrete codebook and encoder on clean HR-HSIs to generate a VQ-prior representation (VQPR), which preserves complete spatial-spectral information. To effectively bridge the gap between degraded inputs and the learned degradation-free codebook, we further incorporate a novel uncertainty-driven probabilistic matching strategy that improves feature alignment and suppresses artifacts. The learned VQPR is then incorporated into the deep prior module as dynamic modulation parameters to enhance the fidelity and realism of the reconstructed results, particularly for severely degraded inputs. Extensive experiments on clean and degraded synthetic and real-world datasets demonstrate that our approach outperforms state-of-the-art HIF methods in both quantitative metrics and visual quality.
RA-COD: Retrieval-Augmented Camouflaged Object Detection.
Du J, Wu J, Kong D … +3 more , Hao F, Xu J, Li P
IEEE Trans Image Process · 2026 · PMID 42133514 · Publisher ↗
Camouflaged Object Detection (COD) is pivotal for segmenting objects that seamlessly blend into their surroundings. While prior endeavors demonstrate impressive performance through training on predefined labels, they hea...
Camouflaged Object Detection (COD) is pivotal for segmenting objects that seamlessly blend into their surroundings. While prior endeavors demonstrate impressive performance through training on predefined labels, they heavily rely on labor-intensive data annotation and struggle to adapt to open-world scenarios. In this light, we propose RA-COD, a training-free paradigm that enables COD by retrieving the most similar samples from the prototype repository. The efficacy of RA-COD hinges on 1) capturing the nuanced resemblance between objects and their environments and 2) excelling in dense prediction tasks. To achieve (1), the crux lies in ensuring diversity and discriminability within the prototype repository. In this context, we propose GenPro, an automated pipeline for crafting Generative Prototypes. GenPro integrates a range of foundation models, including the Diffusion Model, Vision-Language Model, Segment Anything Model (SAM), and DINOv2, in a complementary manner that synergistically generates diverse and distinguishable prototype samples. To achieve (2), we propose C2F to retrieve camouflaged objects in a Coarse-to-Fine regime. We commence with pixel-level retrieval in the feature space, which generates a coarse mask that effectively captures class discrimination and object localization. Further refinement is achieved by extracting bounding boxes from this coarse mask to prompt SAM in generating mask proposals for region-level retrieval. Evaluations on four benchmarks showcase that RA-COD achieves state-of-the-art performance compared to existing training-free methods.
UniEmo: Unifying Emotional Understanding and Generation With Learnable Expert Queries.
Zhu Y, Zhang L, Yu Z … +3 more , Shao R, Tan T, Nie L
IEEE Trans Image Process · 2026 · PMID 42118624 · Publisher ↗
Emotional understanding and generation are often treated as separate tasks, yet they are inherently complementary and can mutually enhance each other. In this paper, we propose the UniEmo, a unified framework that seamle...
Emotional understanding and generation are often treated as separate tasks, yet they are inherently complementary and can mutually enhance each other. In this paper, we propose the UniEmo, a unified framework that seamlessly integrates these two tasks. The key challenge lies in the abstract nature of emotions, necessitating the extraction of visual representations beneficial for both tasks. To address this, we propose a hierarchical emotional understanding chain with learnable expert queries that progressively extracts multi-scale emotional features, thereby serving as a foundational step for unification. Simultaneously, we fuse these expert queries and emotional representations to guide the diffusion model in generating emotion-evoking images. To enhance the diversity and fidelity of the generated emotional images, we further introduce the emotional correlation coefficient and emotional condition loss into the fusion process. This step facilitates fusion and alignment for emotional generation guided by the understanding. In turn, we demonstrate that joint training allows the generation component to provide implicit feedback to the understanding part. Furthermore, we propose a novel data filtering algorithm to select high-quality and diverse emotional images generated by the well-trained model, which explicitly feedback into the understanding part. Together, these generation-driven dual feedback processes enhance the model's understanding capacity. Extensive experiments show that UniEmo significantly outperforms state-of-the-art methods in both emotional understanding and generation tasks. The code for the proposed method is available at https://github.com/JiuTian-VL/UniEmo.
WAS-Mamba: 3D Medical Image Segmentation via Windowed Attention State Space Model.
Zhang X, Wang X, Tong N … +6 more , Jin P, Du J, Ding M, Yu L, Yuan Y, Niu T
IEEE Trans Image Process · 2026 May · PMID 42118623 · Publisher ↗
Mamba, the state space model (SSM), has attracted significant attention for its ability to model long-range dependencies with linear complexity, achieving success in medical image segmentation. However, the previous cros...
Mamba, the state space model (SSM), has attracted significant attention for its ability to model long-range dependencies with linear complexity, achieving success in medical image segmentation. However, the previous cross-scanning approach in Mamba struggles to capture both long-range and short-range dependencies simultaneously and treats the features of each path equally. This imbalance between local and global modeling capabilities can adversely impact segmentation performance. To address these challenges, we propose WAS-Mamba, a novel method specifically designed for Mamba-based medical image segmentation. WAS-Mamba introduces a cross-channel window scanning strategy (CCWScan) that enables sequences to preserve original local image features during the transformation process. Furthermore, WAS-Mamba employs a weighted state space model (WSSM) to dynamically fuse spatial and frequency domain information, improving the capture of local details and global context for accurate segmentation. We validated the superior performance of WAS-Mamba across five datasets covering different anatomical regions, which include CT and MRI images: Synapse, BTCV, ACDC, BraTS, and Decathlon-Lung. In particular, we achieved a Dice coefficient of 88.09% on the Synapse dataset, with a 33% reduction in computational complexity and inference time compared to the second-best model. The code and model will be released at https://github.com/1605066114/WAS-Mamba.
GBNet: Gated Boundary-Aware Network for Camouflaged Object Detection.
Wang X, Yao F, Zhong G … +3 more , Cai Q, Wang S, Kwok JT
IEEE Trans Image Process · 2026 · PMID 42118622 · Publisher ↗
Camouflaged object detection involves identifying camouflaged objects visually blended into the surroundings, holding crucial significance in various visual applications. Existing methods primarily focus on leveraging bo...
Camouflaged object detection involves identifying camouflaged objects visually blended into the surroundings, holding crucial significance in various visual applications. Existing methods primarily focus on leveraging boundary information to enhance camouflaged object detection. However, they often overlook the background interference near the object boundaries, which leads to coarse boundary predictions and results in suboptimal detection performance. In this paper, to address this problem, we propose GBNet, a gated boundary-aware network designed to enhance boundary precision and improve overall detection performance. Specifically, GBNet incorporates a boundary-enhanced module that selectively filters extraneous background information through a boundary gate block, ensuring the generation of high-quality boundary information. Additionally, a boundary-aware decoder is designed to enrich the representation ability of the decoder by injecting high-quality boundary features and aggregating contextual features. With meticulous design, GBNet excels in accurately segmenting camouflaged objects in challenging scenarios. Extensive experiments demonstrate that GBNet outperforms 19 state-of-the-art methods significantly across four widely-used benchmark datasets. The source code is publicly available at https://github.com/wooownn/GBNet.
A Policy-Driven Black-Box Adversarial Example With Location Optimization Against 3D Object Detection.
Han T, Wang H, Wu X … +5 more , Wang C, Luo H, Cao X, Liu L, Chen Y
IEEE Trans Image Process · 2026 · PMID 42118621 · Publisher ↗
Adversarial attack strategies for 3D object detection have highlighted the critical importance of addressing security concerns in this domain. However, white-box methods require full access to the victim model in large-s...
Adversarial attack strategies for 3D object detection have highlighted the critical importance of addressing security concerns in this domain. However, white-box methods require full access to the victim model in large-scale point cloud applications. To this end, we propose a novel Policy-Driven Black-box Attack (BAT) that is designed to optimize attack locations without necessitating detailed knowledge of the victim models. First, we introduce a density-aware pattern generator that creates scene-adaptive attack clusters. Second, we leverage the deep deterministic policy gradient in deep reinforcement learning to train an attack agent capable of targeting the victim model. Ultimately, the attack agent is iteratively directed towards optimal attack locations through the joint application of critic loss and actor loss. To the best of our knowledge, this represents the first reinforcement learning-based black-box attack applied to practical 3D object detection. Experimental results on the KITTI, nuScenes, and Waymo datasets demonstrate that BAT effectively diminishes the accuracy of notable models. Importantly, BAT significantly enhances the attack success rate (surpassing state-of-the-art both white-box and black-box methods) and increases transferability (by 20 times) through simple deep deterministic policy gradient, thus establishing a new baseline for adversarial attacks in 3D object detection.
AWM-Fuse: Multi-Modality Image Fusion for Adverse Weather via Global and Local Text Perception.
Li X, Liu H, Li X … +3 more , Ye T, Kuang Z, Li H
IEEE Trans Image Process · 2026 · PMID 42118620 · Publisher ↗
Multi-modality image fusion (MMIF) in adverse weather aims to address the loss of visual information caused by weather-related degradations, providing clearer scene representations. Although a few studies have attempted...
Multi-modality image fusion (MMIF) in adverse weather aims to address the loss of visual information caused by weather-related degradations, providing clearer scene representations. Although a few studies have attempted to incorporate textual information to improve semantic perception, they often lack effective categorization and thorough analysis of textual content. To address these limitations, we propose AWM-Fuse, a unified fusion framework that handles diverse weather degradations via global and local text perception with shared parameters. In particular, a global text perception module leverages BLIP-generated captions to extract overall scene features and identify primary degradation types, thus promoting generalization across various adverse weather conditions. Complementing this, the local module employs detailed scene descriptions produced by ChatGPT to concentrate on specific degradation effects through concrete textual cues, enabling the recovery of subtle details. Furthermore, textual descriptions are used to constrain the generation of fused images, effectively steering the network learning process toward better alignment with semantic labels, thereby promoting the learning of more meaningful visual features. To facilitate text-guided fusion under adverse weather, we construct AWMM-Text, a large-scale benchmark providing paired global and local annotations for multi-modality image pairs. Extensive experiments demonstrate that AWM-Fuse consistently outperforms state-of-the-art methods under complex weather conditions and on multiple downstream tasks. Our code is available at https://github.com/Feecuin/AWM-Fuse.
Text-Visible/Infrared Person Retrieval: Attribute-Guided Feature Decoupling and Collaborative Alignment and a Unified Benchmark.
Li C, Xu Z, Deng Y … +2 more , Zheng A, Tang J
IEEE Trans Image Process · 2026 · PMID 42118619 · Publisher ↗
Existing research on text-to-image person retrieval primarily focuses on visible images, which are not suitable under low-light scenarios. Infrared imaging becomes necessary in many visual systems, and matching text with...
Existing research on text-to-image person retrieval primarily focuses on visible images, which are not suitable under low-light scenarios. Infrared imaging becomes necessary in many visual systems, and matching text with both visible and infrared images is required. However, visible and infrared images are heterogeneous with different visual characteristics, so matching text with them in a unified framework is very challenging. In this work, we design a new task called Text-Visible/Infrared person retrieval and contribute a novel approach and a unified benchmark to promote the research and development of this field. On one hand, we propose a novel Attribute-guided feature decoupling and Collaborative Alignment Network (ACANet) that pursues accurate alignment from the text modality to both visible and infrared modalities in a unified framework according to the texture and color attribute information of text descriptions. In particular, we decouple the color features of visible images supervised by the text labels and integrate them into the infrared features to eliminate the impact of the absence of color information in infrared images during cross-modal collaborative alignment. Moreover, we also decouple the texture information from visible images supervised by the text labels and perform the collaborative alignment of texture and infrared features with a fusion agent. In addition, we extend conventional masked language modeling to a cross-modal paradigm to help ACANet learn uniform fine-grained alignment in multiple image modalities. On the other hand, we contribute a unified high-quality MM01LLCM-Text dataset, which provides person images in both visible and infrared modalities paired with fine-grained text descriptions. Experimental results show that the proposed ACANet outperforms existing state-of-the-art methods on MM01LLCM-Text dataset.
Frequency-Aware Domain Generalization.
Xiang X, Ma J, Li H … +1 more , Tran TD
IEEE Trans Image Process · 2026 · PMID 42118618 · Publisher ↗
Deep Neural Networks (DNNs) exhibit surprising zero-shot generalization and emergent phenomena across various tasks. However, the underlying mechanisms behind these behaviors remain unclear. By analyzing the perception o...
Deep Neural Networks (DNNs) exhibit surprising zero-shot generalization and emergent phenomena across various tasks. However, the underlying mechanisms behind these behaviors remain unclear. By analyzing the perception of image frequencies by DNNs, we establish the association between the generalization behavior and frequency-aware regions. DNNs with stronger generalization exhibit wider frequency-aware regions. Therefore, we improve the generalization performance by broadening the frequency awareness. Specifically, we enable DNNs to learn the relations between high-frequency components and semantic labels through frequency decomposition and mixup. Based on hierarchical feature alignment, we allow larger submodels to guide the frequency awareness of smaller submodels. Beyond training, we ensemble submodels to extract features from different frequency bands to enrich DNNs' frequency awareness during inference. We validate the effectiveness of our proposed method in image classification and object detection tasks in single and multi-source domain generalization scenarios. We also demonstrate the plug-and-play scalability of our method across existing approaches and different DNNs.
Spectral-Spatial Dynamic Scan Mamba for Multi-Source Remote Sensing Data Classification.
Duan P, Shang Y, Wang Z … +2 more , Kang X, Li S
IEEE Trans Image Process · 2026 · PMID 42113667 · Publisher ↗
Multi-source remote sensing data classification refers to the process of categorizing ground objects by integrating complementary strengths of multiple remote sensing data, such as hyperspectral image (HSI), light detect...
Multi-source remote sensing data classification refers to the process of categorizing ground objects by integrating complementary strengths of multiple remote sensing data, such as hyperspectral image (HSI), light detection and ranging (LiDAR) and synthetic aperture radar (SAR) data. However, current Mamba-based multisource remote sensing data classification approaches rely on fixed scanning patterns that are inadequate in characterizing spectral-spatial information. Additionally, current fusion techniques adopt concatenation or attention-based fusion rules without considering the complementary characteristics between different modalities. To address these limitations, we propose a spectral-spatial dynamic scan Mamba (SDSM) for multi-source remote sensing data classification. Specifically, a dynamic scan Mamba network is proposed to extract the spectral-spatial features of multi-source remote sensing data, in which a dynamic scan module is designed to adaptively capture the important spatial and spectral information. Furthermore, a bidirectional cross-modal fusion rule is proposed to merge the extracted features, in which a global-local frequency feature extraction module is designed to extract the salient structural features of multi-source remote sensing data as clues to guide heterogeneous feature fusion. Comprehensive experiments on four multi-source remote sensing datasets, i.e., MUUFL, Augsburg, Italy and Yellow River, demonstrate that the proposed method outperforms other state-of-the-art methods with respect to quantitative and qualitative results. The code of this article is available at https://github.com/PuhongDuan/SDSM.
ReCoTR: Reducing Semantic Cognitive Shift via Dual-Consensus Token Compression for Remote Sensing Image-Text Retrieval.
Huang J, Chen Y, Du C … +2 more , Xiong S, Lu X
IEEE Trans Image Process · 2026 · PMID 42113666 · Publisher ↗
With the rapid advancement of vision-language models (VLMs) in general-purpose settings, their application to cross-modal retrieval and semantic understanding of large-scale multimodal remote sensing (RS) data is emergin...
With the rapid advancement of vision-language models (VLMs) in general-purpose settings, their application to cross-modal retrieval and semantic understanding of large-scale multimodal remote sensing (RS) data is emerging as a key enabler for urban governance, environmental monitoring, and disaster response. However, the pervasive issue of semantic shift in RS image poses a significant challenge to the transferability of pre-trained VLMs. To address this limitation, we propose ReCoTR, an enhanced CLIP-based cross-modal retrieval framework tailored for remote sensing applications. ReCoTR tackles region-level granularity bias and contextual semantic drift through a Dual Consensus Token Evaluation (DCTE) module, which leverages a mixture-of-experts strategy to fuse inter-modal semantic consensus with intra-modal structural consistency, enabling fine-grained estimation of semantic confidence for visual tokens. Moreover, to mitigate representational contamination caused by background noise, we introduce the Semantic Confidence Token Compression (SCTC) module. This module selectively filters and aggregates tokens with high semantic relevance, thus reducing redundancy and alleviating the noise amplification inherent in CLIP's average pooling. Experimental results on three benchmark RS cross-modal retrieval datasets demonstrate that ReCoTR consistently outperforms existing methods on bidirectional image-text retrieval tasks, validating its effectiveness and robustness in remote sensing semantic alignment scenarios. Our source codes are available at: https://github.com/Jerry710/ReCoTR.git.
FANet: Fovea Attention Network for Robust Aerial Geo-Localization Across Diverse Weather Conditions.
Wen J, Yu H, Zheng Z
IEEE Trans Image Process · 2026 · PMID 42113665 · Publisher ↗
Cross-view geo-localization between drone and satellite images is severely challenged by rapid weather variations, which induce appearance shifts, occlusions, and texture degradation. Inspired by human foveal attention,...
Cross-view geo-localization between drone and satellite images is severely challenged by rapid weather variations, which induce appearance shifts, occlusions, and texture degradation. Inspired by human foveal attention, we propose the Fovea Attention Network (FANet), a robust dual-branch framework comprising: 1) the Weather-Adaptive Global Branch (WAGB) that explicitly injects weather cues (e.g., 'rain/snow') into the feature space via a style-modulation encoder, then captures large-scale structural consistency through a Learnable Region Reassembly (LRR) mechanism; and 2) the Local Semantic Attention Branch (LSAB) that leverages a pretrained segmentation model to generate high-confidence masks, distilling discriminative features from salient regions. An adaptive fusion strategy module fuses global context with fine-grained semantic cues. We further adopt multi-weather adaptive training, treating weather types as related tasks with shared parameters to reduce cross-weather confounding. Extensive experiments on University-1652, SUES-200, and CVUSA show that FANet achieves competitive Recall@1 across all conditions, attaining the highest overall mean with the lowest variance. Notably, it improves Recall@1 by 6.79% under severe low-illumination ('dark') conditions, demonstrating robustness and stability. Our code is available at https://github.com/Jahawn-Wen/FANet.
FSAPF: A De-Scattering Framework With Stepwise Adjustment of Polarization Features.
Lin B, Fan X, Guo Z
IEEE Trans Image Process · 2026 · PMID 42113664 · Publisher ↗
Deep learning has made significant advancements in polarization imaging through scattering media. However, there remains a deficiency in effective analysis and control of the abundant information embedded in polarization...
Deep learning has made significant advancements in polarization imaging through scattering media. However, there remains a deficiency in effective analysis and control of the abundant information embedded in polarization images during training. Therefore, we propose a de-scattering framework with stepwise adjustment of polarization features (FSAPF) for high-performance imaging through scattering media. This framework implements a physically guided hierarchical learning, in which supervision processes are progressively refined from global structure to local polarization details. To directly embed polarization priors into feature representations, a polarization learning module (PLM) is introduced, which regulates feature interactions by enforcing physical consistency constraints, thereby enabling the FSAPF to learn robust representations. In addition, by directly embedding polarization priors into the dynamic loss mechanism, polarization features can be enhanced during training, which further enhances the FSAPF's generalized robustness in changing scenarios. We conduct a series of validation experiments to verify the validity and superiority of the FSAPF. The experimental results show that the FSAPF can perform significantly in target recovery tasks under different scattering environments. And comparative and ablation experiments can both achieve better results.
Asymmetric Feature Consistency Reinforcement Network for Visual-Depth-Thermal Salient Object Detection and a New Benchmark.
Xu C, Li Q, Zhao S … +1 more , Li H
IEEE Trans Image Process · 2026 · PMID 42113663 · Publisher ↗
Fusing Visual-Depth-Thermal (VDT) data holds immense potential for robust Salient Object Detection (SOD) in complex environments. However, current research is constrained by dataset scarcity and the limitations of symmet...
Fusing Visual-Depth-Thermal (VDT) data holds immense potential for robust Salient Object Detection (SOD) in complex environments. However, current research is constrained by dataset scarcity and the limitations of symmetric direct fusion strategies. To address these gaps, we first construct a comprehensive benchmark named LiTR-2654, comprising 2,654 spatially aligned VDT image triplets captured via LiDAR and dual-modality cameras. This dataset features high diversity and reduced center bias, designed to advance practical applications. With this benchmark, we propose the Asymmetric Feature Consistency Reinforcement Network (AFCRNet), effectively utilizing triple-modality cues to achieve accurate SOD. AFCRNet comprises mainly two core technical innovations: "Unify-then-Integrate" fusion strategy investigates modality-complementary information and context-guided decoder module enables the common focus of multi-level features. Specifically, cross-level thermal and visual features are densely interacted to obtain consistent feature representations. Meanwhile, taking depth features as supplements, same-level triple-modality features are integrated with the attention mechanism, significantly suppressing complex background interference and highlighting salient objects. To further improve the segmentation accuracy, high-level contextual information is introduced into multi-level features to accurately distinguish salient objects, and edge supervision is also utilized to optimize the object contour. Comprehensive analysis of different methods is conducted on published and self-built datasets, demonstrating the superiority of the proposed method. The constructed novel benchmark will be made publicly available at: github.com/215HH/LiTR-2654.
Reconstruction-Contrast Coupling Learning for Open-Set Semi-Supervised Hyperspectral Image Classification.
Sun H, Chen R, Chen Y … +3 more , Chen W, Xie W, Lu X
IEEE Trans Image Process · 2026 · PMID 42113662 · Publisher ↗
Although numerous semi-supervised learning methods have been elaborately designed for hyperspectral image (HSI) classification, most existing semi-supervised learning paradigms still rely on a closed-set assumption. Thes...
Although numerous semi-supervised learning methods have been elaborately designed for hyperspectral image (HSI) classification, most existing semi-supervised learning paradigms still rely on a closed-set assumption. These methods implicitly assume that the category spaces of labeled and unlabeled samples are completely aligned, that is, all unlabeled samples must belong to a pre-defined known category set. However, the closed-set assumption is particularly problematic in practical remote sensing scenarios because partial unlabeled data inevitably belong to unknown categories. To address this challenge, this paper proposes a reconstruction-contrast coupling learning (ReCoL) method for open-set semi-supervised HSI classification, fully leveraging the complementarity between masked feature reconstruction learning and contrastive learning to enhance the encoder's local detail sensitivity and global discriminative ability. Specifically, we first apply a masked feature reconstruction learning with an adaptive masking strategy to enhance the encoder's ability to capture local details by high-quality spectral-spatial feature reconstruction. Then, we employ contrastive learning to strengthen the encoder's capability to extract global characteristics by pulling semantically similar samples closer and pushing dissimilar ones farther apart in the feature space. Finally, a pixel-prototype deviation loss is proposed to further improve both inter-category distinguishability and intra-category compactness by reducing the distances between labeled sample features and their corresponding class anchors. Extensive experiments on three benchmark datasets demonstrate that our proposed ReCoL achieves superior classification performance in both known and unknown categories and significantly surpasses 10 state-of-the-art HSI classification methods. The code will be available at https://github.com/repository-AI-chen/ReCo2L.
Iterative Occlusion-Aware Light Field Depth Estimation Using 4-D Geometrical Cues.
Lourenco R, Thomaz LA, Da Silva EAB … +1 more , Faria SMM
IEEE Trans Image Process · 2026 · PMID 42113661 · Publisher ↗
Light field cameras and multi-camera arrays have emerged as promising solutions for accurately estimating depth by passively capturing light information. This is possible because the 3D information of a scene is embedded...
Light field cameras and multi-camera arrays have emerged as promising solutions for accurately estimating depth by passively capturing light information. This is possible because the 3D information of a scene is embedded in the 4-D light field geometry. Commonly, depth estimation methods extract this information relying on gradient information, heuristic-based optimisation models, or learning-based approaches. This paper focuses mainly on explicitly understanding and exploiting 4-D geometrical cues for light field depth estimation. Thus, a novel method is proposed, based on a non-learning-based optimisation approach for depth estimation that explicitly considers surface normal accuracy and occlusion regions by utilising a fully explainable 4-D geometric model of the light field. The 4-D model performs depth/disparity estimation by determining the orientations and analysing the intersections of key 2D planes in 4-D space, which are the images of 3D-space points in the 4-D light field. Experimental results show that the proposed method outperforms both learning-based and non-learning-based state-of-the-art methods in terms of surface normal angle accuracy, achieving a Median Angle Error on planar surfaces, on average, 26.3% lower than the state-of-the-art, and still being competitive with state-of-the-art methods in terms of MSE $\boldsymbol {\times } 100$ and Badpix 0.07.
Toward Universal Semantic Communication via Matchable Semantic Subspace Transmission.
Li B, Yang X, Duan S … +1 more , Wang N
IEEE Trans Image Process · 2026 · PMID 42113660 · Publisher ↗
Semantic communication targets reliable task execution at the receiver under stringent bandwidth and channel constraints. However, existing communication paradigms either focus on bit-level signal reconstruction, impedin...
Semantic communication targets reliable task execution at the receiver under stringent bandwidth and channel constraints. However, existing communication paradigms either focus on bit-level signal reconstruction, impeding the balance between task efficacy and bandwidth efficiency, or are limited by fixed vocabularies and lack generalization when facing unknown categories and open scenarios. To this end, we propose Universal Semantic Communication (UniSC), an open-vocabulary semantic communication framework that formulates transmission as a Matchable Semantic Subspace Transmission (MSST) problem. In this work, "universal" refers to the ability to handle arbitrary text-defined semantic categories beyond fixed vocabularies, rather than universality across all vision tasks. The transmitted representation is explicitly constrained to preserve cross-modal matchability after noisy transmission, rather than merely supporting latent recovery or closed-set inference. Concretely, UniSC comprises a Visual Semantic Engine (VSE), a Semantic Squeeze Network (SSN), a Noise-Adaptive Semantic Re-expansion (NASR) module, and a VLM-based Decoder. VSE and SSN project images into a compact semantic subspace for transmission. This subspace is optimized to preserve both robustness and cross-modal matchability under channel corruption. NASR denoises and lifts the received features back into a semantically complete visual space, from which the VLM-based Decoder performs open-category inference by matching arbitrary text queries rather than relying on a fixed classifier head. The VLM-based Decoder employs a Text Semantic Engine (TSE) to map natural language to text embeddings and, via a learnable Text-Visual Bridge (TVB), aligns them with the reconstructed visual structure for cross-modal matching. To improve cross-modal alignment and transmission robustness, a two-stage training strategy first establishes cross-modal anchors and then optimizes end-to-end robustness and compactness. Extensive experiments on semantic segmentation benchmarks demonstrate that UniSC achieves strong generalization and state-of-the-art performance under harsh channel conditions, outperforming existing methods in both low-SNR and extreme-compression regimes.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe