IEEE Transactions on Multimedia最新文献_第3页

Separating Domain-Private Classes for Universal Unsupervised Cross-Domain 3D Model Retrieval 面向通用无监督跨领域三维模型检索的领域私有类分离

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2025-10-20 DOI: 10.1109/TMM.2025.3623513

Jiayu Li;Yuting Su;Dan Song;Wenhui Li;Zan Gao;An-An Liu

{"title":"Separating Domain-Private Classes for Universal Unsupervised Cross-Domain 3D Model Retrieval","authors":"Jiayu Li;Yuting Su;Dan Song;Wenhui Li;Zan Gao;An-An Liu","doi":"10.1109/TMM.2025.3623513","DOIUrl":"https://doi.org/10.1109/TMM.2025.3623513","url":null,"abstract":"Unsupervised cross-domain 3D model retrieval (UCD3DMR), which enables the transfer of knowledge from existing labeled data to new unlabeled 3D models, has emerged as an effective tool for managing 3D models recently. However, most existing UCD3DMR methods focus on closed-set scenarios, requiring the source and target domains to share identical categories, which is idealized and impractical. Consequently, we explore a more practical yet demanding task known as universal unsupervised cross-domain 3D model retrieval. This task faces significant data distribution discrepancies and uncertain category overlap across domains, posing significant challenges for cross-domain adaptation. To address these challenges, we introduce an innovative universal UCD3DMR method named Separate Domain-Private Classes (SDPC), which integrates a Weighted Alignment Mechanism (WAM) and a Domain-private Separation Mechanism (DSM). Specifically, we formulate a couple of transferability criteria to select domain-common class samples for cross-domain alignment. Additionally, we design a couple of separation losses to mitigate interference from domain-private class samples. The transferability criteria and separation losses can mutually enhance the cross-domain alignment, leading to further cross-domain retrieval performance improvement. Extensive experiments on two well-established cross-domain 3D model datasets (MI3DOR and NTU/PSB), validate and highlight the superior performance of our SDPC.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"309-320"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148489379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MPSS: A Model Pruning Method for Semantic Image Segmentation Networks 语义图像分割网络的模型剪枝方法

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2026-03-03 DOI: 10.1109/TMM.2026.3668487

Yeqiang Qian;Qihang Su;Chunxiang Wang;Ming Yang

{"title":"MPSS: A Model Pruning Method for Semantic Image Segmentation Networks","authors":"Yeqiang Qian;Qihang Su;Chunxiang Wang;Ming Yang","doi":"10.1109/TMM.2026.3668487","DOIUrl":"https://doi.org/10.1109/TMM.2026.3668487","url":null,"abstract":"This paper proposes a model pruning named MPSS for semantic image segmentation networks, so that semantic image segmentation models can be deployed into embedded devices. Most existing model pruning methods aim at image classification models. Since semantic segmentation is a fine-grained task, the directly use of traditional model pruning methods greatly reduces the model accuracy. The core problems of model pruning in the semantic segmentation task are to determine the appropriate pruning kernels and the pruning structure. We propose a new composite index that defines the similarity between convolution kernels to determine the pruning kernels. Furthermore, we propose a structure mending method based on the neural architecture search to determine the pruning structure. Compared with the method of manually defining the pruning rate, the proposed structure mending method obtains a better pruning structure. We conduct experiments based on two semantic segmentation networks, the FCN and the FASSD-Net. The experimental results show that the proposed model pruning method enables the pruned network to obtain higher accuracy under the same compression rate. In addition, we deploy the compressed models on an embedded platform, and the FASSD-Net inference speed is twice as fast as the unpruned model on NVIDIA Xavier NX.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"5672-5681"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148490068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

F2M: Improving Skin Disease Recognition by Fusing Multi-Source and Multi-Scale Image Features F2M：融合多源、多尺度图像特征提高皮肤病识别

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2026-02-27 DOI: 10.1109/TMM.2026.3668532

Xingyi Wang;Ying Huang;Wen Huang;Liaoyaqi Wang;Junhui Chen;Jian Peng;Yuping Ran;Xin Ran

{"title":"F2M: Improving Skin Disease Recognition by Fusing Multi-Source and Multi-Scale Image Features","authors":"Xingyi Wang;Ying Huang;Wen Huang;Liaoyaqi Wang;Junhui Chen;Jian Peng;Yuping Ran;Xin Ran","doi":"10.1109/TMM.2026.3668532","DOIUrl":"https://doi.org/10.1109/TMM.2026.3668532","url":null,"abstract":"Skin diseases are one of the most common diseases worldwide, and the mismatch between skin disease patients and dermatologists leads to a huge waste of healthcare resources. Accurately matching skin disease patients to appropriate dermatologists by an image-based method of skin disease recognition can reduce the waste of healthcare resources. However, existing image-based methods of skin disease recognition do not fully utilize multi-source and multi-scale features, which leaves us the chance to improve skin disease recognition further. In this paper, we propose a fusion method of multi-source image features and multi-scale image features to improve skin disease recognition. First, we design a fusion module of multi-source image features to integrate multi-source image information. By dual Convolutional Block Attention Module (CBAM) blocks, the fusion module of multi-source image features enhances the feature representation of key regions and then obtains a comprehensive representation of skin diseases. Second, we propose a fusion module of multi-scale image features. By two parallel backbone networks, the fusion module of multi-scale image features can extract deep feature representations from different scales and exploit their complementarity. To validate the effectiveness of our method, we conduct extensive experiments. The experiment results demonstrate that our method outperforms the state-of-the-art method, achieving improvements of 6.30%, 12.52%, 10.85%, 12.16%, and 5.06% in accuracy, precision, recall, F1-score, and AUC, respectively.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"5631-5642"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148490070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Prompt Learning With Knowledge Regularization for Pre-Trained Vision-Language Models 基于知识正则化的预训练视觉语言模型的快速学习

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2025-12-03 DOI: 10.1109/TMM.2025.3639886

Boyang Guo;Liang Li;Jiehua Zhang;Yaoqi Sun;Chenggang Yan;Xichun Sheng

{"title":"Prompt Learning With Knowledge Regularization for Pre-Trained Vision-Language Models","authors":"Boyang Guo;Liang Li;Jiehua Zhang;Yaoqi Sun;Chenggang Yan;Xichun Sheng","doi":"10.1109/TMM.2025.3639886","DOIUrl":"https://doi.org/10.1109/TMM.2025.3639886","url":null,"abstract":"Prompt learning is an effective way to adapt pre-trained models to downstream tasks by training a small number of additional learnable prompts. Recent studies address several early challenges by combining generalized knowledge from frozen pre-trained VL models with task-specific knowledge from training data as guidance for prompt learning. However, existing methods still struggle with the generalization-adaptation (GA) trade-off dilemma: excessive reliance on generalized knowledge hinders adaptation to downstream tasks, while overemphasis on task-specific knowledge undermines the inherent generalization capabilities of pre-trained models. To address this issue, we propose a novel prompt learning method called Prompt Learning with Knowledge Regularization (PLKR). PLKR effectively mitigates the GA trade-off dilemma by offering greater flexibility in adapting to task-specific knowledge while minimizing the disruption of pre-trained knowledge. Specifically, we propose category-invariant and topology-invariant knowledge regularization to preserve generalized knowledge: the former enhances category-level discriminative capabilities while allowing flexible task-specific learning, and the latter maintains global topological stability during adaptation to new tasks. Through the proposed regularization, PLKR improves the performance on both base and new tasks. We evaluate the effectiveness of our approach on four representative tasks over 11 datasets. Experimental results show our method outperforms existing SOTA methods by a large margin.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"1457-1468"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148490284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ICDSR: Integrated Conditional Diffusion Model for Single Image Super-Resolution 单幅图像超分辨率的综合条件扩散模型

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2025-12-03 DOI: 10.1109/TMM.2025.3639910

Cong Hu;Xiao-Zhong Wei;Xiao-Jun Wu

{"title":"ICDSR: Integrated Conditional Diffusion Model for Single Image Super-Resolution","authors":"Cong Hu;Xiao-Zhong Wei;Xiao-Jun Wu","doi":"10.1109/TMM.2025.3639910","DOIUrl":"https://doi.org/10.1109/TMM.2025.3639910","url":null,"abstract":"Diffusion Probabilistic Models (DPMs) have recently demonstrated considerable potential for single image super-resolution (SISR) by utilizing a conditional generation process that transforms Gaussian noise into high-resolution (HR) images based on low-resolution (LR) inputs. Current Image-Conditional DPMs (icDPMs) have demonstrated promising results by leveraging LR images as a condition to guide the generation of HR images. However, icDPMs fail to effectively integrate LR images and other conditional information to generate accurate and natural output. To address this issue, we propose an Integrated Conditional Diffusion Model for Single Image Super-Resolution (ICDSR). Our approach encodes the LR image as a condition to generate the prior feature, simultaneously integrating it with timestep information to establish intermediate constraints. To further enhance these constraints, we designed a multi-scale guidance structure for the U-shaped concatenation of the diffusion model during the integration of conditions. This constraint serves as multi-scale guidance specifically designed for the U-shaped concatenation of the diffusion model during the integration of conditions. Specifically, multi-scale integrated information is injected into the diffusion model basic block, informing about the coarse structure of the sharp image at the intermediate layers with spatially adaptive conditions. Additionally, ICDSR employs a lightweight U-Net to provide initial guidance and leverages the diffusion model to learn residual guidance for faster convergence. Extensive experiments on facial and general benchmarks, including the CelebA and DIV2K datasets, demonstrate that ICDSR surpasses existing methods, achieving state-of-the-art perceptual quality while maintaining competitive distortion metrics.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"1302-1313"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148490586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

REPAIR: Rank Correlation and Noisy Pair Half-Replacing With Memory for Noisy Correspondence 修正：秩相关和带记忆的噪声对半替换

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2025-10-20 DOI: 10.1109/TMM.2025.3623547

Ruochen Zheng;Jiahao Hong;Changxin Gao;Nong Sang

{"title":"REPAIR: Rank Correlation and Noisy Pair Half-Replacing With Memory for Noisy Correspondence","authors":"Ruochen Zheng;Jiahao Hong;Changxin Gao;Nong Sang","doi":"10.1109/TMM.2025.3623547","DOIUrl":"https://doi.org/10.1109/TMM.2025.3623547","url":null,"abstract":"The presence of noise in acquired data invariably leads to performance degradation in cross-modal matching. Unfortunately, obtaining precise annotations in the multimodal field is expensive, which has prompted some methods to tackle the mismatched data pair issue in cross-modal matching contexts, termed as noisy correspondence. However, most of these existing noisy correspondence methods exhibit the following limitations: a) the problem of self-reinforcing error accumulation, and b) improper handling of noisy data pair. To tackle the two problems, we propose a generalized framework termed as Rank corrElation and noisy Pair hAlf-replacing wIth memoRy (REPAIR), which benefits from maintaining a memory bank for features of matched pairs. Specifically, we calculate the distances between the features in the memory bank and those of the target pair for each respective modality, and use the rank correlation of these two sets of distances to estimate the soft correspondence label of the target pair. Estimating soft correspondence based on memory bank features rather than using a similarity network can avoid the accumulation of errors due to incorrect network identifications. For pairs that are completely mismatched, REPAIR searches the memory bank for the most matching feature to replace one feature of one modality, instead of using the original pair directly or merely discarding the mismatched pair. We conduct experiments on three cross-modal datasets, i.e., Flickr30 K, MS-COCO, and CC152 K, proving the effectiveness and robustness of our REPAIR on synthetic and real-world noise.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"465-478"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148490596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing Cross-Task Transferability of Adversarial Examples via Spatial and Channel Attention 通过空间和通道注意增强对抗性例子的跨任务可转移性

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2024-01-15 DOI: 10.1109/TMM.2024.3349925

Weiwei Feng;Nanqing Xu;Tianzhu Zhang;Yongdong Zhang;Feng Wu

{"title":"Enhancing Cross-Task Transferability of Adversarial Examples via Spatial and Channel Attention","authors":"Weiwei Feng;Nanqing Xu;Tianzhu Zhang;Yongdong Zhang;Feng Wu","doi":"10.1109/TMM.2024.3349925","DOIUrl":"https://doi.org/10.1109/TMM.2024.3349925","url":null,"abstract":"Adversarial examples are well known to pose a security risk, when attacking deep learning models. While, most of existing adversarial attacks are designed to attack a single deep learning-based task, such as image classification. In practical scenarios, it is more necessary to study adversarial examples transferring across different vision tasks. However, it is challenging to create cross-task adversarial examples that can destroy multiple vision tasks at once due to unavailable various task-specific models and loss functions for attackers. To deal with this problem, we propose a Dual Attention-Guided Method (DAGM) for crafting cross-task adversarial examples by designing a spatial attention module and a channel attention module to capture overlapping discriminative regions and features that contribute to various tasks. Then we craft cross-task adversarial examples via reducing the dispersion (i.e., standard deviation) of feature maps re-weighted by both attention modules, which can destroy the overlapping discriminative regions and features for various tasks. Furthermore, to present theoretical explanation, we systematically analyze our method, and rigorously prove that both attention modules can provide better effectiveness of our adversarial examples, compared with existing cross-task adversarial attacks. Extensive experiments on two datasets demonstrate that our method can significantly degrade the performance of various tasks, even online CV APIs, and consistently outperform state-of-the-art methods by a large margin.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"2016-2030"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148492507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Arbitrary-Scale Fusion Operator for High-Resolution Hyperspectral Imaging 高分辨率高光谱成像的任意尺度融合算子

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2026-01-26 DOI: 10.1109/TMM.2026.3655472

Junwei Zhu;Honghui Xu;Wei Li;Jiawei Jiang;Zhi Liu;Jianwei Zheng

{"title":"Arbitrary-Scale Fusion Operator for High-Resolution Hyperspectral Imaging","authors":"Junwei Zhu;Honghui Xu;Wei Li;Jiawei Jiang;Zhi Liu;Jianwei Zheng","doi":"10.1109/TMM.2026.3655472","DOIUrl":"https://doi.org/10.1109/TMM.2026.3655472","url":null,"abstract":"For high-resolution hyperspectral (HrHs) imaging, spatial-spectral fusion offers a promising alternative to expensive equipment. However, retraining multiple models for varied scaling factors is currently unavoidable, costing extra computational resource and human labor. To address this issue, we propose Arbitrary-scale Fusion Operator (AFO), a lightweight solution for HrHs fusion given arbitrary scalings, turning the retraining strategy into “training-free” ones. Specifically, AFO treats low-resolution hyperspectral (LrHs) images and high-resolution multispectral (HrMs) images as light-wise degraded functions within the spectrum, which are initially embedded into a high-dimensional space to simulate the original light signals, tapping the potential of enriched prior learning. Then, a flow of kernel integration (KI) is meticulously crafted, followed by a rival step of dimension reduction for HrHs generation. For a well-behaved KI computation, an Attention-Driven Convolution Integration (ADCI) is engineered to restore the broken discretization invariance derived by convolutions, yet with the locally inductive bias preserved. In addition, we propose an Implicit Neural Functional Integration (INFI) to achieve cross-domain interaction of spatial degradation functions, followed by the use of Galerkin-type Integration (GI) as a decoder to handle high-frequency information. Finally, the bonded activation functions are improved for the principle of continuous-discrete equivalence. Extensive experiments validate the superiority of our approach over cutting-edge methods. Notably, our proposal holds significantly better generalization on arbitrary scaling factors, yet requires only 0.07 M parameters.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"4219-4232"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148492593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Geo-SelfSSC: Integrating Dense Geometric Priors for Enhanced Self-Supervised Semantic Scene Completion 基于密集几何先验的自监督语义场景补全

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2026-02-27 DOI: 10.1109/TMM.2026.3668555

Hao Zhu;Pute Guo;Xiaotong Li;Longsheng Qu;Jinjian Wu

{"title":"Geo-SelfSSC: Integrating Dense Geometric Priors for Enhanced Self-Supervised Semantic Scene Completion","authors":"Hao Zhu;Pute Guo;Xiaotong Li;Longsheng Qu;Jinjian Wu","doi":"10.1109/TMM.2026.3668555","DOIUrl":"https://doi.org/10.1109/TMM.2026.3668555","url":null,"abstract":"Accurate 3D scene understanding is vital for applications like autonomous driving and robotics. However, existing voxel-based methods struggle with the reliance on large-scale labeled data, inherent voxel-pixel misalignments, and high computational costs. Recent self-supervised Semantic Scene Completion (SSC) methods using Neural Radiance Fields (NeRF) reduce 3D annotation needs but assume Lambertian surfaces and rely on photometric consistency, which fails in real-world scenes with non-Lambertian effects and sparse camera coverage. In this paper, we introduce Geo-SelfSSC, a self-supervised framework that leverages temporal information from consecutive frames and slight variations in camera poses for supervision, while integrating dense geometric cues to enhance the reconstruction quality and efficiency of neural implicit models. Specifically, Geo-SelfSSC leverages depth priors along with complementary semi-local and local geometric supervision to facilitate efficient sampling, while ensuring effective complementarity between photometric and geometric cues. Our method yields significant improvements in reconstructing reflective and under-observed regions where conventional photometric-based strategies struggle. Comprehensive experiments on challenging tasks demonstrate that Geo-SelfSSC not only achieves strong results in semantic scene completion but also establishes competitive performance in geometry-only 3D occupancy prediction and monocular depth estimation.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"6052-6065"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

D2C-SID: A Divergence to Convergence Strategy for Sonar Image Denoising D2C-SID：一种从发散到收敛的声纳图像去噪策略

IF 9.9 1区计算机科学

IEEE Transactions on Multimedia Pub Date : 2026-01-01 Epub Date: 2026-02-27 DOI: 10.1109/TMM.2026.3668561

Weiling Chen;Fengquan Lan;Boqin Cai;Mingjie Wang;Dongjie Chen;Tiesong Zhao

{"title":"D2C-SID: A Divergence to Convergence Strategy for Sonar Image Denoising","authors":"Weiling Chen;Fengquan Lan;Boqin Cai;Mingjie Wang;Dongjie Chen;Tiesong Zhao","doi":"10.1109/TMM.2026.3668561","DOIUrl":"https://doi.org/10.1109/TMM.2026.3668561","url":null,"abstract":"Sonar imaging serves as a crucial sensing modality in underwater environments, yet its outputs are inherently degraded by substantial speckle noise arising from background interference, biological activity, and device self-noise, posing unique challenges for effective denoising. Existing sonar image denoising techniques take a deterministic approach and produce only one outcome. However, this may neglect the complexities present in real-world situations, thereby limiting the effectiveness of denoising. To address this challenge, we first create a sonar noise dataset with corresponding reference images obtained through well esigned pairwise comparisons. Subsequently, we introduce the Divergence-to-Convergence Sonar Image Denoising (D2C-SID) network. This network treats denoising as an uncertainty problem and generates multiple plausible denoised samples. It accomplishes this by leveraging a latent space constructed via a conditional variational autoencode. By this process, our method reduces the reliance on any single estimation. Experimental results on both forward-looking and side-scan sonar images confirm the efficacy of the D2C-SID approach.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"28 ","pages":"6352-6364"},"PeriodicalIF":9.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148628114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0