检索结果-内蒙古大学图书馆

2025 IEEE International conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Qiao, Xiaoyu Li, Weisheng Xiao, Bin Huang, Yuping Yang, Lijian Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications Ministry of Education Chongqing China

ISBN: (纸本)9798350368741

Model-based networks have shown convincing performance in MRI reconstruction. However, the unrolled cascades within the networks are constrained to solely obtain information from the preceding counterpart, resulting in potential error accumulation. Moreover, the linear structure fails to address the challenge of recovering fine-grained details. To tackle these problems, we propose to redesign the information flow in model-based networks. Our method features a large U-shaped network, where the nodes are built with unrolled cascades and U-Net-based regularizers. We design an input-level integration module to help the cascades acquire information from adjacent and skip-connected counterparts, building robust mappings to the target. We further design a coarse-to-fine feature-level integration module, aiming at guiding the network to progressively recover fine details. Intermediate reconstructions produced by subnetworks of different scales are integrated, enabling the extraction of complementary information to enhance the final performance. Compared with cutting-edge methods on different datasets, our method exhibits superior performances. © 2025 IEEE.

关键词： compressed sensing deep learning model-based MRI reconstruction U-Net

来源：评论

学校读者我要写书评

暂无评论

EqGAN: Reformation-based Feature Equalization Fusion for Few-shot image Generation

EqGAN: Reformation-based Feature Equalization Fusion for Few...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhou, Yingbo Yue, Zhihao Ye, Yutong Zhang, Pengyu Wei, Xian Chen, Mingsong MoE Eng. Research Center of SW/HW Co-Design Tech. and App. East China Normal University China

ISBN: (纸本)9798350368741

Due to the absence or mismatch of semantic information, existing few-shot image generation methods suffer from unsatisfactory generation quality and diversity, which have minimal benefits as data augmentation for downstream classification tasks. Reformatting the contextual and textural information of features at different scales, we propose a novel Feature Equalization Fusion Generative Adversarial Network (EqGAN) for few-shot image generation. Specifically, we first decompose the encoded features into textual and structural components to mitigate the influence of irrelevant and redundant information. Based on feature correlation learning and attention mechanism, we then obtain fused features by refining different contents (i.e., textures and structures) with a more fine-grained semantic alignment. Moreover, an attention-based reconstruction loss and a consistency-based equalization loss are devised to provide better training stability and generation performance. Comprehensive experiments on three public datasets demonstrate that EqGAN not only significantly improves the FID scores (by up to 14.10%) and LPIPS scores (by up to 3.17%) of generated images, but also outperforms the state-of-the-art in terms of accuracy (by up to 3.89%) for downstream classification. © 2025 IEEE.

关键词： Equalization Fusion Few-shot image Generation Generative Adversarial Network

来源：评论

学校读者我要写书评

暂无评论

Appearance-adapter: A Self-supervised Pose-guided Human image Synthesis Approach

Appearance-adapter: A Self-supervised Pose-guided Human Imag...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sameer Malik Moyuru Yamada Fujitsu Research India Private Limited Bengaluru India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Human image synthesis with pose guidance generates images of a specified human in a given pose, a task complicated by dis-occlusions and varying body articulations. While generative model-based approaches are effective, they often require paired training data, limiting generalizability. Recent selfsupervised methods, such as reconstruction from body parts and jigsaw puzzle-solving, face issues like pose leaking and inadequate appearance encoding. We propose a novel approach that learns to reconstruct images from body parts using a body symmetricity loss, leveraging human body symmetries. Our method preserves appearance information and mitigates pose leaking by aligning appearance features of corresponding body parts from symmetric left-right halves. Additionally, we leverage pretrained models, specifically stable-diffusion, to enhance performance and training efficiency. Extensive experiments and ablation studies on the deepfashion dataset demonstrate our method’s effectiveness.

关键词： Training Limiting image coding Training data Encoding data models Human image synthesis Speech processing image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

image reconstruction from radially incomplete spherical Radon data

引用

EUROPEAN JOURNAL OF APPLIED MATHEMATICS 2018年第3期29卷 470-493页

作者： Ambartsoumian, Gaik Gouia-Zarrad, Rim Krishnan, Venkateswaran P. Roy, Souvik Univ Texas Arlington Dept Math Arlington TX 76019 USA Amer Univ Sharjah Dept Math & Stat Sharjah U Arab Emirates Tata Inst Fundamental Res Ctr Applicable Math Bangalore Karnataka India Univ Wurzburg Dept Math Wurzburg Germany

We study inversion of the spherical Radon transform with centres on a sphere (the data acquisition set). Such inversions are essential in various image reconstruction problems arising in medical, radar and sonar imaging. In the case of radially incomplete data, we show that the spherical Radon transform can be uniquely inverted recovering the image function in spherical shells. Our result is valid when the support of the image function is inside the data acquisition sphere, outside that sphere, as well as on both sides of the sphere. Furthermore, in addition to the uniqueness result, our method of proof provides reconstruction formulas for all those cases. We present a robust computational algorithm and demonstrate its accuracy and efficiency on several numerical examples.

关键词： spherical Radon transform medical imaging spherical harmonics Volterra integral equations truncated singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Bayesian image and pattern reconstruction from incomplete and noisy data

引用

Pattern Recognition and image Analysis 2012年第1期22卷 99-107页

作者： Vengrinovich, V.L. Institute of Applied Physics National Academy of Sciences Minsk Belarus

A Bayesian iterative method can be the basis for a wide range of technologies in the field of pattern recognition and image reconstruction. It involves finding the most probable solutions for images or patterns, if functionals describing the likelihood function and a priori information, respectively, are already known. The article describes the basic principles and recent advances in the development of BIM and its applications in various fields, mainly in tomography and restoration of functions from incomplete and noisy data. © 2012 Pleiades Publishing, Ltd.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

A Trust-Guided Approach to MR image reconstruction with Side Information

arXiv

引用

arXiv 2025年

作者： Atalık, Arda Chopra, Sumit Sodickson, Daniel K. The Bernard and Irene Schwartz Center for Biomedical Imaging Department of Radiology NYU Grossman School of Medicine United States The Courant Institute of Mathematical Sciences The Bernard and Irene Schwartz Center for Biomedical Imaging Department of Radiology NYU Grossman School of Medicine United States The Bernard and Irene Schwartz Center for Biomedical Imaging Department of Radiology NYU Grossman School of Medicine United States

Reducing MRI scan times can improve patient care and lower healthcare costs. Many acceleration methods are designed to reconstruct diagnostic-quality images from limited sets of acquired k-space data. This task can be framed as a linear inverse problem (LIP), where, as a result of undersampling, the forward operator may become rank-deficient or exhibit small singular values. This results in ambiguities in reconstruction, in which multiple generally incorrect or non-diagnostic images can map to the same acquired data. To address such ambiguities, it is crucial to incorporate prior knowledge, for example in the form of regularization. Another form of prior knowledge less commonly used in medical imaging is contextual side information garnered from other sources than the current acquisition. Here, we propose the Trust-Guided Variational Network (TGVN), a novel end-to-end deep learning framework that effectively integrates side information into LIPs. TGVN eliminates undesirable solutions from the ambiguous space of the forward operator while remaining faithful to the acquired data. We demonstrate its effectiveness in multi-coil, multi-contrast MR image reconstruction, where incomplete or low-quality measurements from one contrast are used as side information to reconstruct high-quality images of another contrast from heavily under-sampled data. Our method is robust across different contrasts, anatomies, and field strengths. Compared to baselines that also utilize side information, TGVN achieves superior image quality at challenging under-sampling levels, drastically speeding up acquisition while minimizing hallucinations. Our approach is also versatile enough to incorporate many different types of side information (including previous scans or even text) into any LIP. © 2025, CC BY-NC-ND.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Object-level data Augmentation for Visual 3D Object Detection in Autonomous Driving

Object-level Data Augmentation for Visual 3D Object Detectio...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haoran Cheng Junkai Xu Liang Peng Zheng Yang Xiaofei He Boxi Wu Zhejiang University Hangzhou China FABU Inc Hangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

data augmentation plays an important role in visual-based 3D object detection. Existing detectors typically employ image/BEV-level data augmentation techniques, failing to utilize flexible object-level augmentations because of 2D-3D inconsistencies. This limitation hinders us from increasing the diversity of training data. To alleviate this issue, we propose an object-level data augmentation approach that incorporates scene reconstruction and neural scene rendering. Specifically, we reconstruct the scene and objects by extracting image features from sequences and aligning them with associated LiDAR point clouds. This approach is intended to conduct the editing process within a 3D space, allowing for flexible object manipulation. Additionally, we introduce a neural scene renderer to project the edited 3D scene onto a specified camera plane and render it onto a 2D image. Combined with scene reconstruction, it overcomes the challenges stemming from 2D/3D inconsistencies, enabling the generation of object-level augmented images with corresponding labels for model training. To validate the proposed method, we apply our method to various multi-camera 3D object detectors, consistently boosting the performance.

关键词： Visualization Three-dimensional displays Laser radar Training data Detectors Object detection data augmentation Rendering (computer graphics) Feature extraction image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Proceedings of SPIE: image reconstruction from incomplete data II

Proceedings of SPIE: Image reconstruction from incomplete da...

引用

image reconstruction from incomplete data II

The proceedings contains 22 papers from the SPIE conference on image reconstruction from incomplete data II. Topics discussed include: comparison of reconstruction algorithms for images from sparse-aperture systems;imaging fluorescence parameters by Bayesian optical diffusion tomography;blind deconvolution of speckle images constrained by wavefront sensing data;automated target morphing applied to objects in cluttered backgrounds;reconstruction of seismic data using adaptive regularization;and continuous and discrete space particle filters for predictions in acoustic positioning.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Orthogonal Latent Compression for Streaming Anomaly Detection in Industrial Vision 27th

Orthogonal Latent Compression for Streaming Anomaly Detecti...

引用

27th International conference on Pattern Recognition, ICPR 2024

作者： Gao, Han Luo, Huiyuan Shen, Fei Zhang, Zhengtao The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The Institute of Automation Chinese Academy of Sciences Beijing100190 China The Binzhou Institute of Technology Shandong Binzhou256606 China The CAS Engineering Laboratory for Intelligent Equipment and Technology of Industrial Vision Beijing100190 China

ISBN: (纸本)9783031781889

Although existing industrial anomaly detection methods perform well, they are trained on offline datasets collected in advance and remain unchanged once the training is complete. Simultaneously, they assume that the data is static without any drift. However, data in industrial scenarios, especially in sequential assembly lines, usually arrives dynamically in streams and suffers from data drift over time, such as lighting variations and digital noise. The offline training paradigm and inability to dynamically update of existing methods are inconsistent with the data characteristics of streaming dynamics, and it is also difficult to quickly adapt to streaming data drift. To this end, we propose a streaming anomaly detection method that can not only learn dynamically based on the production line data stream, but also adapt to data drift as quickly as possible by effectively utilizing a small amount of drifted training data. The core idea of the proposed method is to compress the features into an orthogonal latent space and constrain the features with nearest reconstruction and maximum separability to maximally capture the normal patterns of the data. Extensive experiments on three real industrial datasets demonstrate our method’s excellent performance in stream anomaly detection tasks and rapid adaptability to data drifts. Additionally, our method has lower modeling complexity and higher computational efficiency. It also achieves state-of-the-art performance in offline industrial image anomaly detection and localization tasks. Source code will be released upon paper acceptance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data streams

来源：评论

学校读者我要写书评

暂无评论

Hybrid Coding and Weakly-Supervised Approach for Depth Estimation from Wrapped Phase

Hybrid Coding and Weakly-Supervised Approach for Depth Estim...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jie Ren Chunqian Tan Wanzhong Song College of Computer Science Sichuan University Chengdu China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Fringe projection profilometry (FPP) is one of the widely used techniques for 3D surface imaging. Deep learning (DL)-based fringe-to-depth reconstruction methods have aroused extensive research interest. This paper presents a hybrid coding pattern to improve depth-reconstruction accuracy. The hybrid coding wrapped phase is used to replace the fringe image as the input to neural networks. This replacement improves the accuracy of the reconstruction and facilitates the transfer from simulated to real scenarios. A weakly supervised framework and a novel loss function are proposed for fine-tuning the pre-trained model using real data without labels. The proposed approach is evaluated on the largest real-scene dataset to date, which includes 9,000 samples. Experiments demonstrate that this method outperforms the three supervised methods and achieves depth accuracy in terms of a mean absolute error (MAE) of 0.264 mm within a depth range of 120 mm. The dataset and source code is available at https://***/K-Jie/Hybrid_wrapped_phase_to_depth.

关键词： Surface reconstruction Accuracy Three-dimensional displays Source coding Imaging Signal processing reconstruction algorithms data models Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：