检索结果-内蒙古大学图书馆

Sam's Net: A Self-Augmented Multistage Deep-Learning Network for End-to-End reconstruction of Limited Angle CT

IEEE TRANSACTIONS ON MEDICAL IMAGING 2022年第10期41卷 2912-2924页

作者： Chen, Changyu Xing, Yuxiang Gao, Hewei Zhang, Li Chen, Zhiqiang Tsinghua Univ Dept Engn Phys Beijing 100084 Peoples R China Tsinghua Univ Minist Educ Key Lab Particle & Radiat Imaging Beijing 100084 Peoples R China

Limited angle reconstruction is a typical ill-posed problem in computed tomography (CT). Given incomplete projection data, images reconstructed by conventional analytical algorithms and iterative methods suffer from severe structural distortions and artifacts. In this paper, we proposed a self-augmented multi-stage deep-learning network (Sam's Net) for end-to-end reconstruction of limited angle CT. With the merit of the alternating minimization technique, Sam's Net integrates multi-stage self-constraints into cross-domain optimization to provide additional constraints on the manifold of neural networks. In practice, a sinogram completion network (SCNet) and artifact suppression network (ASNet), together with domain transformation layers constitute the backbone for cross-domain optimization. An online self-augmentation module was designed following the manner defined by alternating minimization, which enables a self-augmented learning procedure and multi-stage inference manner. Besides, a substitution operation was applied as a hard constraint for the solution space based on the data fidelity and a learnable weighting layer was constructed for data consistency refinement. Sam's Net forms a new framework for ill-posed reconstruction problems. In the training phase, the self-augmented procedure guides the optimization into a tightened solution space with enriched diverse data distribution and enhanced data consistency. In the inference phase, multi-stage prediction can improve performance progressively. Extensive experiments with both simulated and practical projections under 90-degree and 120-degree fan-beam configurations validate that Sam's Net can significantly improve the reconstruction quality with high stability and robustness.

关键词： image reconstruction Optimization Computed tomography Training Minimization Iterative methods Artificial neural networks Computed tomography (CT) limited angle reconstruction deep learning alternating minimization online augmentation

来源：评论

学校读者我要写书评

暂无评论

Some Geometric and Tomographic Results on Gray-Scale images 3rd

Some Geometric and Tomographic Results on Gray-Scale Images

引用

3rd International Joint conference on Discrete Geometry and Mathematical Morphology (DGM)

作者： Ascolese, Michela Duno, Paolo Pagani, Silvia M. C. Univ Firenze Dipartimento Matemat & Informat U Dini Florence Italy Politecn Milan Dipartimento Matemat Milan Italy Univ Cattolica Sacro Cuore Dipartimento Matemat & Fis N Tartaglia Brescia Italy

ISBN: (纸本)9783031577925;9783031577932

Discrete tomography deals with the reconstruction of images from a (usually small) set of X-ray projections. This is achieved by modeling the tomographic problem as a linear system of equations and then applying a suitable discrete reconstruction algorithm based on iterations. In this paper we adopt the well-known grid model and prove some geometric properties of integer solutions consisting of p >= 2 gray levels. In particular, we show that all gray-scale solutions having the same two-norm belong to a same hypersphere, centered at the uniform image related to the data and having radius ranging in an interval whose bounds are explicitly computed. Moving from a uniqueness theorem for gray-scale images, we compute special sets of directions that guarantee uniqueness of reconstruction and exploit them as the input of the Conjugate Gradient Least Squares algorithm. Then we apply an integer rounding to the resulting output and, basing on previously described geometric parameters, we test the quality of the obtained reconstructions for an increasing number of iterations, which leads to a progressive improvement of the percentage of correctly reconstructed pixels, until perfect reconstruction is achieved. Differently, using sets of directions which are classically employed, but far from being sets of uniqueness, only partial reconstructions are obtained.

关键词： Discrete tomography Gray-scale image Grid model Minimum norm solution Projection Unique reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-modal image Super-Resolution via Deep Convolutional Transform Learning 32

Multi-modal Image Super-Resolution via Deep Convolutional Tr...

引用

32nd European Signal Processing conference (EUSIPCO)

作者： Kumar, Kriti Majumdar, Angshul Kumar, A. Anil Chandra, M. Girish TCS Res Pune Maharashtra India IIIT Delhi New Delhi India TCG CREST Inst Adv Intelligence Kolkata India

ISBN: (纸本)9789464593617;9798331519773

Real-world situations often involve processing data from diverse imaging modalities like Multispectral (MS), Near Infrared (NIR), and RGB, each capturing different aspects of the same scene. These modalities often vary in spatial and spectral resolution. Hence, Multi-modal image Super-Resolution (MISR) techniques are required to improve the spatial/spectral resolution of target modality, taking help from High Resolution (HR) guidance modality that shares common features like textures, edges, and other structures. Traditional MISR approaches using Convolutional Neural Networks (CNNs) typically employ an encoder-decoder architecture, which is prone to overfit in data-limited scenarios. This work proposes a novel deep convolutional analysis sparse coding method, utilizing convolutional transforms within a fusion framework that eliminates the need for a decoder network. Thus, reducing the trainable parameters and enhancing the suitability for data-limited application scenarios. A joint optimization framework is proposed, which learns deep convolutional transforms for Low Resolution (LR) images of the target modality and HR images of the guidance modality, along with a fusion transform that combines these transform features to reconstruct HR images of the target modality. In contrast to dictionary-based synthesis sparse coding methods for MISR, the proposed approach offers improved performance with reduced complexity, leveraging the inherent advantages of transform learning. The efficacy of the proposed method is demonstrated using RGB-NIR and RGB-MS datasets, showing superior reconstruction performance compared to state-of-the-art techniques without introducing additional artifacts from the guidance image.

关键词： Multimodal image super-resolution Convolutional transform learning Joint optimization Convolutional sparse coding Deep models

来源：评论

学校读者我要写书评

暂无评论

image-based Pose Estimation and Shape reconstruction for Robot Manipulators and Soft, Continuum Robots via Differentiable Rendering

Image-based Pose Estimation and Shape Reconstruction for Rob...

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Lu, Jingpei Liu, Fei Girerd, Cedric Yip, Michael C. Univ Calif San Diego Dept Elect & Comp Engn La Jolla CA 92093 USA Univ Montpellier CNRS LIRMM Montpellier France UCSD La Jolla CA USA

ISBN: (纸本)9798350323658

State estimation from measured data is crucial for robotic applications as autonomous systems rely on sensors to capture the motion and localize in the 3D world. Among sensors that are designed for measuring a robot's pose, or for soft robots, their shape, vision sensors are favorable because they are information-rich, easy to set up, and cost-effective. With recent advancements in computer vision, deep learning-based methods no longer require markers for identifying feature points on the robot. However, learning-based methods are data-hungry and hence not suitable for soft and prototyping robots, as building such bench-marking datasets is usually infeasible. In this work, we achieve image-based robot pose estimation and shape reconstruction from camera images. Our method requires no precise robot meshes, but rather utilizes a differentiable renderer and primitive shapes. It hence can be applied to robots for which CAD models might not be available or are crude. Our parameter estimation pipeline is fully differentiable. The robot shape and pose are estimated iteratively by back-propagating the image loss to update the parameters. We demonstrate that our method of using geometrical shape primitives can achieve high accuracy in shape reconstruction for a soft continuum robot and pose estimation for a robot manipulator.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Learning from History: Task-agnostic Model Contrastive Learning for image Restoration 38

Learning from History: Task-agnostic Model Contrastive Learn...

引用

38th AAAI conference on Artificial Intelligence (AAAI) / 36th conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Wu, Gang Jiang, Junjun Jiang, Kui Liu, Xianming Harbin Inst Technol rac Comp Harbin 150001 Peoples R China

ISBN: (纸本)1577358872

Contrastive learning has emerged as a prevailing paradigm for high-level vision tasks, which, by introducing properly negative samples, has also been exploited for low-level vision tasks to achieve a compact optimization space to account for their ill-posed nature. However, existing methods rely on manually predefined and task-oriented negatives, which often exhibit pronounced task-specific biases. To address this challenge, our paper introduces an innovative method termed 'learning from history', which dynamically generates negative samples from the target model itself. Our approach, named Model Contrastive Learning for image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks. We propose the Self-Prior guided Negative loss (SPN) to enable it. This approach significantly enhances existing models when retrained with the proposed model contrastive paradigm. The results show significant improvements in image restoration across various tasks and architectures. For example, models retrained with SPN outperform the original FFANet and DehazeFormer by 3.41 and 0.57 dB on the RESIDE indoor dataset for image dehazing. Similarly, they achieve notable improvements of 0.47 dB on SPA-data over IDT for image deraining and 0.12 dB on Manga109 for a 4x scale super-resolution over lightweight SwinIR, respectively. Code and retrained models are available at https://***/Aitical/MCLIR.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

CT image Kernel Synthesis using Deep Regularization

CT Image Kernel Synthesis using Deep Regularization

引用

conference on Medical Imaging - image Processing

作者： Aggarwal, Hemant Kumar Langoju, Rajesh Das, Bipul GE HealthCare Adv Technol Grp Bangalore Karnataka India

ISBN: (纸本)9781510671577;9781510671560

Kernel Synthesis (KS) in CT is an advanced image processing technique that involves the conversion of an image acquired with one specific convolution kernel into an image that appears as if it were acquired with a different kernel. This process doesn't require raw sinogram or reconstruction algorithm to generate images. While kernel synthesis methods exhibit promise, they can introduce noise and artifacts during transformation, highlighting the importance of effective noise and artifact management in the input data before synthesis. In this work, we represent kernel synthesis as a deep neural network regularized inverse problem. We optimize the convolutional neural network (CNN) weights in a data-consistent manner where CNN acts as an implicit prior to regularize the solution. Since, the learned CNN priors are more generic than hand crafted priors (like sparsity and total-variation), they helps control artifacts while preserving the details in the image. Experimental results for a low-resolution kernel (STND) data to a high resolution kernel (LUNG) data conversion clearly indicates that the output images from the proposed method resemble closely with images reconstructed using high-resolution kernel (LUNG) while simultaneously reducing the noise and clutter.

关键词： Kernel Synthesis Deep Regularization Inverse Problems

来源：评论

学校读者我要写书评

暂无评论

SSCDUF: Spatial-Spectral Correlation Transformer Based on Deep Unfolding Framework for Hyperspectral image reconstruction 31st

SSCDUF: Spatial-Spectral Correlation Transformer Based on De...

引用

31st International conference on Multimedia Modeling

作者： Zhao, Hui Qi, Na Zhu, Qing Lin, Xiumin Beijing Univ Technol Coll Comp Sci Sch Software Engn Natl Pilot Software Coll Beijing 100124 Peoples R China

ISBN: (纸本)9789819620708;9789819620715

Reconstructing Hyperspectral images (HSIs) from Coded Aperture Snapshot Spectral Imaging (CASSI) is an important yet challenging task. The core issue lies in recovering reliable and detailed 3D HSI cube from 2D measurement. Deep unfolding framework which alternates between solving data subproblems and prior subproblems has made satisfactory progress in HSIs reconstruction task. However, current methods do not fully utilize the spatial spectral prior of HSIs. To solve this problem and further enhance the spectral-spatial representation capabilities in the prior subproblems, we propose a Spatial-Spectral Correlation Transformer Based on Deep Unfolding Framework (SSCDUF). Specifically, we introduce a multi-scale Spatial-Spectral Correlation Fusion Transformer (SSCT) module that simultaneously utilize the similarity and correlation of spectral features as well as local and non-local spatial features, jointly using spatial and spectral prior to enhance feature representation. Moreover, we further propose an Adaptive Aggregation Skip Connection (AASC) module to adaptively aggregate spatial and spectral features in multiple scales. Extensive experimental results on both simulated and real scenes demonstrate that SSCDUF outperforms the state-of-the-art methods in terms of quantitative metrics while maintaining low parameter costs and runtime.

关键词： Hyperspectral image reconstruction Deep Unfolding Framework Spatial-Spectral Transformer Adaptive Aggregation Skip Connection

来源：评论

学校读者我要写书评

暂无评论

Anomaly-focused Single image Super-resolution with Artifact Removal for Chest X-rays using Distribution-aware Diffusion Model 7

Anomaly-focused Single Image Super-resolution with Artifact ...

引用

7th International conference on Medical Imaging with Deep Learning, MIDL 2024

作者： Roy, Dattatreyo Paul, Angshuman Indian Institute of Technology Jodhpur Jodhpur India

Single image super-resolution (SISR) is a crucial task in the field of medical imaging. It transforms low-resolution images into high-resolution counterparts. Performing SISR on chest x-ray images enhances image quality, aiding better diagnosis. However, artifacts may be present in the images. We propose an anomaly-guided SISR process utilizing the denoising mechanism of the diffusion model to iteratively remove noise and restore the original image. We train the model to learn the data distribution, enabling it to eliminate artifacts within the images. Additionally, we ensure reconstruction of the disease regions by prioritizing their reconstruction. Our research experiment over the publicly available dataset and find that the existing SISR methods are unable to learn and remove these artificially added artifacts. On the other hand, our proposed model not only prioritizes superior image reconstruction but also remove the artifacts. Our method is found to outperform the existing methods. The code is publicly available at https://***/Datta-IITJ/MIDL_***. © 2024 CC-BY 4.0, D. Roy & A. Paul.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Supervised Transform Learning for Limited Angle Tomographic reconstruction

Supervised Transform Learning for Limited Angle Tomographic ...

引用

conference on Medical Imaging - image Processing

作者： Li, Zhipeng Chen, Gaoyu Gao, Hao Long, Yong Shanghai Jiao Tong Univ Univ Michigan Shanghai Jiao Tong Univ Joint Inst Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai Peoples R China Univ Kansas Med Ctr Dept Radiat Oncol Kansas City KS 66103 USA

ISBN: (纸本)9781510660335;9781510660342

Computed tomography (CT) reconstruction from X-ray projections acquired within a limited angle range is challenging. Both analytical and conventional iterative methods suffer from severe artifacts due to the incompleteness of sinogram. To obtain high-quality reconstructions from limited angle CT, it is crucial to integrate model-based methods with better learned priors from existing big databases of CT images. Transform learning is an unsupervised data-driven model that has recently shown promise in several medical imaging applications. However, its performance is limited due to the use of hand-crafted penalty terms on the learned transform and sparse coefficients. Inspired by the great success of convolutional neural network, we propose a supervised transform learning method for limited angle CT image reconstruction, where we redesign the conventional unsupervised iterative transform learning algorithm and learn the priors for both sparse coefficients and transform in a supervised manner. Clinical patient data results show that the proposed method significantly improves image quality of reconstructions, compared to a denoising deep convolutional neural network method, FBPConvNet, and a representative iterative neural network method, LEARN.

关键词： Limited angle CT image reconstruction deep learning transform learning

来源：评论

学校读者我要写书评

暂无评论

Cross Initialization for Face Personalization of Text-to-image Models

Cross Initialization for Face Personalization of Text-to-Ima...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Pang, Lianyu Yin, Jian Xie, Haoran Wang, Qiping Li, Qing Mao, Xudong Sun Yat Sen Univ Guangzhou Guangdong Peoples R China Guangdong Key Lab Big Data Anal & Proc Guangzhou Guangdong Peoples R China Lingnan Univ Hong Kong Peoples R China East China Normal Univ Shanghai Peoples R China Hong Kong Polytech Univ Hong Kong Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Recently, there has been a surge in face personalization techniques, benefiting from the advanced capabilities of pretrained text-to-image diffusion models. Among these, a notable method is Textual Inversion, which generates personalized images by inverting given images into textual embeddings. However, methods based on Textual Inversion still struggle with balancing the trade-off between reconstruction quality and editability. In this study, we examine this issue through the lens of initialization. Upon closely examining traditional initialization methods, we identified a significant disparity between the initial and learned embeddings in terms of both scale and orientation. The scale of the learned embedding can be up to 100 times greater than that of the initial embedding. Such a significant change in the embedding could increase the risk of overfitting, thereby compromising the editability. Driven by this observation, we introduce a novel initialization method, termed Cross Initialization, that significantly narrows the gap between the initial and learned embeddings. This method not only improves both reconstruction and editability but also reduces the optimization steps from 5,000 to 320. Furthermore, we apply a regularization term to keep the learned embedding close to the initial embedding. We show that when combined with Cross Initialization, this regularization term can effectively improve editability. We provide comprehensive empirical evidence to demonstrate the superior performance of our method compared to the baseline methods. Notably, in our experiments, Cross Initialization is the only method that successfully edits an individual's facial expression. Additionally, a fast version of our method allows for capturing an input image in roughly 26 seconds, while surpassing the baseline methods in terms of both reconstruction and editability. Code is available at https://***/lyuPang/CrossInitialization.

关键词： Embeddings

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：