Query:
学者姓名:施云惠
Refining:
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract :
Deep unfolding networks have gained increasing attention in the field of compressed sensing (CS) owing to their theoretical interpretability and superior reconstruction performance. However, most existing deep unfolding methods often face the following issues: (1) they learn directly from single-channel images, leading to a simple feature representation that does not fully capture complex features; and (2) they treat various image components uniformly, ignoring the characteristics of different components. To address these issues, we propose a novel wavelet-domain deep unfolding framework named WTDUN, which operates directly on the multi-scale wavelet sub-bands. Our method utilizes the intrinsic sparsity and multi-scale structure of wavelet coefficients to achieve a tree-structured sampling and reconstruction, effectively capturing and highlighting the most important features within images. Specifically, the design of tree-structured reconstruction aims to capture the inter-dependencies among the multi-scale sub-bands, enabling the identification of both fine and coarse features, which can lead to a marked improvement in reconstruction quality. Furthermore, a wavelet domain adaptive sampling method is proposed to greatly improve the sampling capability, which is realized by assigning measurements to each wavelet sub-band based on its importance. Unlike pure deep learning methods that treat all components uniformly, our method introduces a targeted focus on important sub-bands, considering their energy and sparsity. This targeted strategy lets us capture key information more efficiently while discarding less important information, resulting in a more effective and detailed reconstruction. Extensive experimental results on various datasets validate the superior performance of our proposed method.
Keyword :
wavelet tree wavelet tree Compressed sensing Compressed sensing deep unfolding deep unfolding
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Han, Kai , Wang, Jin , Shi, Yunhui et al. WTDUN: Wavelet Tree-Structured Sampling and Deep Unfolding Network for Image Compressed Sensing [J]. | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2025 , 21 (1) . |
MLA | Han, Kai et al. "WTDUN: Wavelet Tree-Structured Sampling and Deep Unfolding Network for Image Compressed Sensing" . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 21 . 1 (2025) . |
APA | Han, Kai , Wang, Jin , Shi, Yunhui , Cai, Hanqin , Ling, Nam , Yin, Baocai . WTDUN: Wavelet Tree-Structured Sampling and Deep Unfolding Network for Image Compressed Sensing . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2025 , 21 (1) . |
Export to | NoteExpress RIS BibTex |
Abstract :
The surge in image data has significantly increased the pressure on storage and transmission, posing new challenges for image compression technology. The structural texture of an image implies its statistical characteristics, which is effective for image encoding and decoding. Consequently, content-adaptive compression methods based on learning can better capture the content attributes of images, thereby enhancing encoding performance. However, learned image compression methods do not comprehensively account for both the global and local correlations among the pixels within an image. Moreover, they are constrained by rate-distortion optimization, which prevents the attainment of a compact representation of image attributes. To address these issues, we propose a syntax-guided content-adaptive transform framework that efficiently captures image attributes and enhances encoding efficiency. Firstly, we propose a syntax-refined side information module that fully leverages syntax and side information to guide the adaptive transformation of image attributes. Moreover, to more thoroughly exploit the global and local correlations in image space, we designed global-local modules, local-global modules, and upsampling/downsampling modules in codecs, further eliminating local and global redundancies. The experimental findings indicate that our proposed syntax-guided content-adaptive image compression model successfully adapts to the diverse complexities of different images, which enhances the efficiency of image compression. Concurrently, the method proposed has demonstrated outstanding performance across three benchmark datasets.
Keyword :
image compression image compression deep learning deep learning adaptive compression adaptive compression
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Shi, Yunhui , Ye, Liping , Wang, Jin et al. Syntax-Guided Content-Adaptive Transform for Image Compression [J]. | SENSORS , 2024 , 24 (16) . |
MLA | Shi, Yunhui et al. "Syntax-Guided Content-Adaptive Transform for Image Compression" . | SENSORS 24 . 16 (2024) . |
APA | Shi, Yunhui , Ye, Liping , Wang, Jin , Wang, Lilong , Hu, Hui , Yin, Baocai et al. Syntax-Guided Content-Adaptive Transform for Image Compression . | SENSORS , 2024 , 24 (16) . |
Export to | NoteExpress RIS BibTex |
Abstract :
Recently, deep unfolding network methods have significantly progressed in hyperspectral snapshot compressive imaging. Many approaches directly employ Transformer models to boost the feature representation capabilities of algorithms. However, they often fall short of leveraging the full potential of self-attention mechanisms. Additionally, current methods lack adequate consideration of both intra-stage and inter-stage feature fusion, which hampers their overall performance. To tackle these challenges, we introduce a novel approach that hybridizes the sparse Transformer and wavelet fusion-based deep unfolding network for hyperspectral image (HSI) reconstruction. Our method includes the development of a spatial sparse Transformer and a spectral sparse Transformer, designed to capture spatial and spectral attention of HSI data, respectively, thus enhancing the Transformer's feature representation capabilities. Furthermore, we incorporate wavelet-based methods for both intra-stage and inter-stage feature fusion, which significantly boosts the algorithm's reconstruction performance. Extensive experiments across various datasets confirm the superiority of our proposed approach.
Keyword :
hyperspectral image reconstruction hyperspectral image reconstruction compressive sensing compressive sensing snapshot compressive imaging snapshot compressive imaging deep unfolding network deep unfolding network
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Ying, Yangke , Wang, Jin , Shi, Yunhui et al. Hybrid Sparse Transformer and Wavelet Fusion-Based Deep Unfolding Network for Hyperspectral Snapshot Compressive Imaging [J]. | SENSORS , 2024 , 24 (19) . |
MLA | Ying, Yangke et al. "Hybrid Sparse Transformer and Wavelet Fusion-Based Deep Unfolding Network for Hyperspectral Snapshot Compressive Imaging" . | SENSORS 24 . 19 (2024) . |
APA | Ying, Yangke , Wang, Jin , Shi, Yunhui , Ling, Nam . Hybrid Sparse Transformer and Wavelet Fusion-Based Deep Unfolding Network for Hyperspectral Snapshot Compressive Imaging . | SENSORS , 2024 , 24 (19) . |
Export to | NoteExpress RIS BibTex |
Abstract :
本发明涉及一种基于局部几何一致性与特征一致性的点云补全方法,用于解决点云补全任务中补全结果细节丢失严重以及补全的点云分布不均匀的问题,具体方案包括:基于特征一致性的方法通过加强预测值与真实值之间对应局部区域点云分布的一致性,解决细节丢失问题;此外,在点云生成过程中,本发明采用“粗糙到细节”多阶段方式生成不同尺度的点云,所以,基于特征一致性的方法通过将不同尺度点云映射到特征空间,通过加强不同尺度点云在特征空间的一致性,使得不同尺度的点云在几何形状上更加一致,使得最终的补全结果更加接近真实值。本发明与现有的方法比,很大程度上克服了上述提及的问题,本发明具有明显的提升效果。
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 施云惠 , 王一波 , 王瑾 et al. 一种基于局部几何一致性与特征一致性的点云补全方法 : CN202210195181.2[P]. | 2022-03-01 . |
MLA | 施云惠 et al. "一种基于局部几何一致性与特征一致性的点云补全方法" : CN202210195181.2. | 2022-03-01 . |
APA | 施云惠 , 王一波 , 王瑾 , 尹宝才 . 一种基于局部几何一致性与特征一致性的点云补全方法 : CN202210195181.2. | 2022-03-01 . |
Export to | NoteExpress RIS BibTex |
Abstract :
本发明为了解决球面图像压缩效率问题,提出了一种基于球面小波变换的球面图像压缩方法,包括采用现有的基于球面测度的球面图像表示SMSIR对球面三角像元进行索引,利用基于SMSIR的球面小波变换对球面三角像元进行变换,利用SMSIR图像压缩方案S‑SPIHT对变换后的球面小波系数进行扫描编解码完成球面图像压缩,所述的S‑SPIHT是对SPIHT的改进,改进之处在于像素坐标的设置,即球形图像使用三维坐标dk(pk, qk, mk)表示,除此之外改进之处还可以是同时改变像素坐标的设置以及重新设计SPIHT的扫描顺序,具体包括有序根树索引扫描ORTIS、二进索引逐行扫描DIPS、以及二进索引交叉扫描DICS。
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 施云惠 , 王欢 , 王瑾 et al. 基于球面小波变换的球面图像压缩方法 : CN202210019249.1[P]. | 2022-01-07 . |
MLA | 施云惠 et al. "基于球面小波变换的球面图像压缩方法" : CN202210019249.1. | 2022-01-07 . |
APA | 施云惠 , 王欢 , 王瑾 , 吴刚 , 尹宝才 . 基于球面小波变换的球面图像压缩方法 : CN202210019249.1. | 2022-01-07 . |
Export to | NoteExpress RIS BibTex |
Abstract :
本发明涉及一种基于学习的边信息补偿图像压缩方法,用于解决图像和视频的压缩问题,具体包括本发明通过引入多尺度表示提取两层边信息作为浅层超先验和深层超先验,从而实现更准确和灵活的熵模型。此外,浅层超先验可以捕获潜在表示的空间依赖,同时也可以微调潜在表示来提升重建质量。其次,本发明提取的深层超先验作为浅层超先验的超先验,可以提升浅层超先验的有效性和准确性。最后,本发明设计了一种有效的残差通道注意力块,可以增强潜在表示通道之间的交互关系以及适用于我们基于残差的网络结构。
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 施云惠 , 张康富 , 王瑾 et al. 一种基于学习的超先验边信息补偿图像压缩方法 : CN202210011926.5[P]. | 2022-01-06 . |
MLA | 施云惠 et al. "一种基于学习的超先验边信息补偿图像压缩方法" : CN202210011926.5. | 2022-01-06 . |
APA | 施云惠 , 张康富 , 王瑾 , 尹宝才 . 一种基于学习的超先验边信息补偿图像压缩方法 : CN202210011926.5. | 2022-01-06 . |
Export to | NoteExpress RIS BibTex |
Abstract :
As the core technology of deep learning, convolutional neural networks have been widely applied in a variety of computer vision tasks and have achieved state-of-the-art performance. However, it's difficult and inefficient for them to deal with high dimensional image signals due to the dramatic increase of training parameters. In this paper, we present a lightweight and efficient MS-Net for the multi-dimensional(MD) image processing, which provides a promising way to handle MD images, especially for devices with limited computational capacity. It takes advantage of a series of one dimensional convolution kernels and introduces a separable structure in the ConvNet throughout the learning process to handle MD image signals. Meanwhile, multiple group convolutions with kernel size 1 x 1 are used to extract channel information. Then the information of each dimension and channel is fused by a fusion module to extract the complete image features. Thus the proposed MS-Net significantly reduces the training complexity, parameters and memory cost. The proposed MS-Net is evaluated on both 2D and 3D benchmarks CIFAR-10, CIFAR-100 and KTH. Extensive experimental results show that the MS-Net achieves competitive performance with greatly reduced computational and memory cost compared with the state-of-the-art ConvNet models.
Keyword :
Multi-dimensional image processing Multi-dimensional image processing Separable convolution neural network Separable convolution neural network Matricization Matricization Feature extraction and representation Feature extraction and representation
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Hou, Zhenning , Shi, Yunhui , Wang, Jin et al. MS-Net: A lightweight separable ConvNet for multi-dimensional image processing [J]. | MULTIMEDIA TOOLS AND APPLICATIONS , 2021 , 80 (17) : 25673-25688 . |
MLA | Hou, Zhenning et al. "MS-Net: A lightweight separable ConvNet for multi-dimensional image processing" . | MULTIMEDIA TOOLS AND APPLICATIONS 80 . 17 (2021) : 25673-25688 . |
APA | Hou, Zhenning , Shi, Yunhui , Wang, Jin , Cui, Yingxuan , Yin, Baocai . MS-Net: A lightweight separable ConvNet for multi-dimensional image processing . | MULTIMEDIA TOOLS AND APPLICATIONS , 2021 , 80 (17) , 25673-25688 . |
Export to | NoteExpress RIS BibTex |
Abstract :
简单线性迭代聚类(simple linear iterative clustering,SLIC)超像素分割算法可以直接用于等距柱状投影(equirectangular projection,ERP)的球面图像,但是投影所造成的球面数据局部相关性破坏,会导致SLIC算法在ERP图像的部分区域无法生成合适的超像素分类,从而影响该算法的性能.为解决这一问题,首先对ERP格式的球面图像进行重采样,生成球面上近似均匀分布的球面像元数据;然后在保持球面图像数据局部相关性的基础上,将重采样数据重组为一个新的球面图像二维表示;并基于此二维表示,将球面数据的几何关系整合到SLIC算法中,最终建立球面图像SLIC算法.针对多组ERP图像分别应用SLIC算法和本文提出的算法,对比2种算法在不同聚类数量下的超像素分割结果.实验结果表明:所提出的球面图像SLIC算法在客观质量上优于原SLIC算法,所生成的超像素分割结果不受球面区域变化影响,且轮廓闭合,在球面上表现出了较好的相似性和一致性.
Keyword :
SLIC算法 SLIC算法 聚类 聚类 超像素 超像素 重采样 重采样 球面图像 球面图像 图像分割 图像分割
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 吴刚 , 施云惠 , 尹宝才 . 球面图像的SLIC算法 [J]. | 北京工业大学学报 , 2021 , 47 (3) : 216-223 . |
MLA | 吴刚 et al. "球面图像的SLIC算法" . | 北京工业大学学报 47 . 3 (2021) : 216-223 . |
APA | 吴刚 , 施云惠 , 尹宝才 . 球面图像的SLIC算法 . | 北京工业大学学报 , 2021 , 47 (3) , 216-223 . |
Export to | NoteExpress RIS BibTex |
Abstract :
球面图像的SLIC算法
Keyword :
图像分割 图像分割 超像素 超像素 SLIC算法 SLIC算法 重采样 重采样 球面图像 球面图像 聚类 聚类
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 吴刚 , 施云惠 , 尹宝才 et al. 球面图像的SLIC算法 [J]. | 吴刚 , 2021 , 47 (3) : 216-223 . |
MLA | 吴刚 et al. "球面图像的SLIC算法" . | 吴刚 47 . 3 (2021) : 216-223 . |
APA | 吴刚 , 施云惠 , 尹宝才 , 北京工业大学学报 . 球面图像的SLIC算法 . | 吴刚 , 2021 , 47 (3) , 216-223 . |
Export to | NoteExpress RIS BibTex |
Abstract :
This paper presents a spherical measure based spherical image representation(SMSIR) and sphere-based resampling methods for generating our representation. On this basis, a spherical wavelet transform is also proposed. We first propose a formal recursive definition of the spherical triangle elements of SMSIR and a dyadic index scheme. The index scheme, which supports global random access and needs not to be pre-computed and stored, can efficiently index the elements of SMSIR like planar images. Two resampling methods to generate SMSIR from the most commonly used ERP(Equirectangular Projection) representation are presented. Notably, the spherical measure based resampling, which exploits the mapping between the spherical and the parameter domain, achieves higher computational efficiency than the spherical RBF(Radial Basis Function) based resampling. Finally, we design high-pass and low-pass filters with lifting schemes based on the dyadic index to further verify the efficiency of our index and deal with the spherical isotropy. It provides novel Multi-Resolution Analysis(MRA) for spherical images. Experiments on continuous synthetic spherical images indicate that our representation can recover the original image signals with higher accuracy than the ERP and CMP(Cubemap) representations at the same sampling rate. Besides, the resampling experiments on natural spherical images show that our resampling methods outperform the bilinear and bicubic interpolations concerning the subjective and objective quality. Particularly, as high as 2dB gain in terms of S-PSNR is achieved. Experiments also show that our spherical image transform can capture more geometric features of spherical images than traditional wavelet transform.
Keyword :
Feature extraction Feature extraction Interpolation Interpolation spherical measure spherical measure Image representation Image representation Geometry Geometry indexing scheme indexing scheme Indexing Indexing spherical RBF spherical RBF Extraterrestrial measurements Extraterrestrial measurements image resampling image resampling Spherical images Spherical images Surface treatment Surface treatment
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Wu, Gang , Shi, Yunhui , Sun, Xiaoyan et al. SMSIR: Spherical Measure Based Spherical Image Representation [J]. | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2021 , 30 : 6377-6391 . |
MLA | Wu, Gang et al. "SMSIR: Spherical Measure Based Spherical Image Representation" . | IEEE TRANSACTIONS ON IMAGE PROCESSING 30 (2021) : 6377-6391 . |
APA | Wu, Gang , Shi, Yunhui , Sun, Xiaoyan , Wang, Jin , Yin, Baocai . SMSIR: Spherical Measure Based Spherical Image Representation . | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2021 , 30 , 6377-6391 . |
Export to | NoteExpress RIS BibTex |
Export
Results: |
Selected to |
Format: |