IEEE Transactions on Image Processing最新文献_第7页

GIDDM: Generating Labels with Diffusion Model to Promote Cross-domain Open-set Image Recognition 用扩散模型生成标签促进跨域开集图像识别

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-08-25 DOI: 10.1109/tip.2025.3599929

Haoyu Wang, Yuhu Cheng, Wei Zhang, Xiaomin Liu, Xuesong Wang

引用次数: 0

CAN: Cascade Augmentations against Noise for Image Restoration. CAN：级联增强抗噪声图像恢复。

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-08-08 DOI: 10.1109/tip.2025.3595374

Yanyang Yan,Siyuan Yao,Wenqi Ren,Rui Zhang,Qi Guo,Xiaochun Cao

{"title":"CAN: Cascade Augmentations against Noise for Image Restoration.","authors":"Yanyang Yan,Siyuan Yao,Wenqi Ren,Rui Zhang,Qi Guo,Xiaochun Cao","doi":"10.1109/tip.2025.3595374","DOIUrl":"https://doi.org/10.1109/tip.2025.3595374","url":null,"abstract":"Image restoration aims to recover the latent clean image from a degraded counterpart. In general, the prevailing state-of-the-art image restoration methods concentrate on solving only a specific degradation type according to the task, e.g. deblurring or deraining. However, if the corresponding well-trained frameworks confront other real-world image corruptions, i.e., the corruptions are not covered in the training phase, and state-of-the-art restoration models will suffer from a lack of generalization ability. We have observed that an image restoration model can be easily confused by noise corruption. Towards improving the robustness of image restoration networks, in this paper, we focus on alleviating the corruption of noise in various image restoration tasks, which is almost inevitable in real-world scenes. To this end, we devise a novel Multifarious Augmentation strategy against Noise (CAN) to enhance the robustness of specific image restoration. Specifically, the given degraded images are sequentially augmented from different perspectives, i.e., noise-aware augmentation, and model-aware augmentation. The noise-aware augmentation is proposed to enrich the samples by introducing various noise operations. Moreover, to adapt to more unknown corruptions, we propose a novel model-aware augmentation mechanism, which enhances the scalability by exploring useful both spatial and frequency clues with the help of model randomness. It is worth noting that the proposed augmentation scheme is model-agnostic, and it can plug and play into arbitrary state-of-the-art image restoration architectures. In addition, we construct noise corruption benchmark datasets, derived from the validation set of standard image restoration datasets, to assist us in evaluating the robustness of restoration networks. Extensive quantitative and qualitative evaluations demonstrate that the proposed method has strong generalization capability which can enhance the robustness of various image restoration frameworks when facing diverse noises.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"169 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144802608","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

Multi-scale Autoencoder Suppression Strategy for Hyperspectral Image Anomaly Detection. 高光谱图像异常检测中的多尺度自编码器抑制策略。

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-08-08 DOI: 10.1109/tip.2025.3595408

Bing Tu,Tao Zhou,Bo Liu,Yan He,Jun Li,Antonio Plaza

{"title":"Multi-scale Autoencoder Suppression Strategy for Hyperspectral Image Anomaly Detection.","authors":"Bing Tu,Tao Zhou,Bo Liu,Yan He,Jun Li,Antonio Plaza","doi":"10.1109/tip.2025.3595408","DOIUrl":"https://doi.org/10.1109/tip.2025.3595408","url":null,"abstract":"Autoencoders (AEs) have received extensive attention in hyperspectral anomaly detection (HAD) due to their capability to separate the background from the anomaly based on the reconstruction error. However, the existing AE methods routinely fail to adequately exploit spatial information and may precisely reconstruct anomalies, thereby affecting the detection accuracy. To address these issues, this study proposes a novel Multi-scale Autoencoder Suppression Strategy (MASS). The underlying principle of MASS is to prioritize the reconstruction of background information over anomalies. In the encoding stage, the Local Feature Extractor, which integrates Convolution and Omni-Dimensional Dynamic Convolution (ODConv), is combined with the Global Feature Extractor based on Transformer to effectively extract multi-scale features. Furthermore, a Self-Attention Suppression module (SAS) is devised to diminish the influence of anomalous pixels, enabling the network to focus more intently on the precise reconstruction of the background. During the process of network learning, a mask derived from the test outcomes of each iteration is integrated into the loss function computation, encompassing only the positions with low anomaly scores from the preceding detection round. Experiments on eight datasets demonstrate that the proposed method is significantly superior to several traditional methods and deep learning methods in terms of performance.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"20 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144802660","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

Cognitive Contour Detection of Sparse-Structured Objects in the Alpha-Shape Scale Space α -形状尺度空间中稀疏结构物体的认知轮廓检测

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-07-31 DOI: 10.1109/tip.2025.3592862

Yuxiang Shen, Baojiang Zhong, Kai-Kuang Ma

引用次数: 0

Image-to-Image Bayesian Flow Networks with Structurally Informative Priors 具有结构信息先验的图像到图像贝叶斯流网络

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-07-30 DOI: 10.1109/tip.2025.3592546

Hongkun Dou, Jinyang Du, Xingyu Jiang, Hongjue Li, Wen Yao, Yue Deng

引用次数: 0

Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos 压缩视频条带伪影的主客观质量评价

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-07-30 DOI: 10.1109/tip.2025.3592543

Qi Zheng, Li-Heng Chen, Chenlong He, Neil Berkbeck, Yilin Wang, Balu Adsumilli, Alan C. Bovik, Yibo Fan, Zhengzhong Tu

引用次数: 0

Fourier-based Decoupling Network for Joint Low-Light Image Enhancement and Deblurring 基于傅里叶解耦网络的联合微光图像增强和去模糊

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-07-30 DOI: 10.1109/tip.2025.3592559

Luwei Tu, Jiawei Wu, Chenxi Wang, Deyu Meng, Zhi Jin

引用次数: 0

Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning 增强遥感影像变化字幕中关键变化的感知

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-07-22 DOI: 10.1109/tip.2025.3589096

Cong Yang, Zuchao Li, Hongzan Jiao, Zhi Gao, Lefei Zhang

引用次数: 0

Personalized Restoration via Dual-Pivot Tuning 通过双枢轴调谐个性化恢复

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-07-11 DOI: 10.1109/tip.2025.3586141

Pradyumna Chari, Sizhuo Ma, Daniil Ostashev, Achuta Kadambi, Gurunandan Krishnan, Jian Wang, Kfir Aberman

引用次数: 0

High-precision Edge Detection Guided by Flow Fields 基于流场的高精度边缘检测

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2025-06-09 DOI: 10.1109/tip.2025.3572763

Bing Li, Yuchen Han, Shiyin Zhang, Haowei Wang, Zhenbing Zhao, Yongjie Zhai

引用次数: 0