您的检索：
学者姓名：施云惠
精炼检索结果：
年份
成果类型
收录类型
来源
综合
合作者
语言
清除所有精炼条件
摘要 ：
Guided depth map super-resolution (GDSR) is one of the mainstream methods in depth map super-resolution, as high-resolution color images can guide the reconstruction of the depth maps and are often easy to obtain. However, how to make full use of extracted guidance information of the color image to improve the depth map reconstruction remains a challenging problem. In this paper, we first design a multi-scale feedback module (MF) that extracts multi-scale features and alleviates the information loss in network propagation. We further propose a novel multi-scale feedback network (MSF-Net) for guided depth map super-resolution, which can better extract and refine the features by sequentially joining MF blocks. Specifically, our MF block uses parallel sampling layers and feedback links between multiple time steps to better learn information at different scales. Moreover, an inter-scale attention module (IA) is proposed to adaptively select and fuse important features at different scales. Meanwhile, depth features and corresponding color features are interacted using cross-domain attention conciliation module (CAC) after each MF block. We evaluate the performance of our proposed method on both synthetic and real captured datasets. Extensive experimental results validate that the proposed method achieves state-of-the-art performance in both objective and subjective quality.
关键词 ：
super-resolution super-resolution Task analysis Task analysis Superresolution Superresolution Depth map Depth map Image reconstruction Image reconstruction Feature extraction Feature extraction multi-scale multi-scale Color Color feedback feedback Optimization Optimization Data mining Data mining
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wang, Jin , Li, Chenyang , Shi, Yunhui et al. MSF-Net: Multi-Scale Feedback Reconstruction for Guided Depth Map Super-Resolution [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (2) : 709-723 . |
| MLA | Wang, Jin et al. "MSF-Net: Multi-Scale Feedback Reconstruction for Guided Depth Map Super-Resolution" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34 . 2 (2024) : 709-723 . |
| APA | Wang, Jin , Li, Chenyang , Shi, Yunhui , Wang, Dan , Wu, Mu-En , Ling, Nam et al. MSF-Net: Multi-Scale Feedback Reconstruction for Guided Depth Map Super-Resolution . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (2) , 709-723 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
The hyperspectral image (HSI) compressive imaging field has experienced significant progress in recent years, especially with the emergence of deep unfolding networks (DUNs), which have demonstrated remarkable advancements in reconstruction performance. However, these methods still face several challenges. Firstly, HSI data carries crucial prior knowledge in the feature space, and effectively leveraging these priors is essential for achieving high-quality HSI reconstruction. Existing methods either neglect the utilization of prior information or incorporate network modules designed based on prior information in a rudimentary manner, thereby limiting the overall reconstruction potential of these models. Secondly, the transformation between the data and feature domains poses a significant challenge for DUNs, leading to the loss of feature information across different stages. Existing methods fall short in adequately considering spectral characteristics when utilizing inter-stage information, resulting in inefficient transmission of feature information. In this paper, we introduce a novel deep unfolding network architecture that integrates local non-local and low-rank priors with spectral memory enhancement for precise HSI data reconstruction. Specifically, we design innovative modules for local non-local and low-rank priors to enrich the network's feature representation capability, fully exploiting the prior information of HSI data in the feature space. These designs also help the overall framework achieve superior reconstruction results with fewer parameters. Moreover, we extensively consider the spectral correlation characteristics of HSI data and devise a spectral memory enhancement network module to mitigate inter-stage feature information loss. Extensive experiments further demonstrate the superiority of our approach.
关键词 ：
deep unfolding network deep unfolding network Degradation Degradation Spectral snapshot compressive imaging Spectral snapshot compressive imaging compressive sensing compressive sensing Transformers Transformers Correlation Correlation Image reconstruction Image reconstruction Optimization Optimization Imaging Imaging Three-dimensional displays Three-dimensional displays
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Ying, Yangke , Wang, Jin , Shi, Yunhui et al. Spectral Memory-Enhanced Network With Local Non-Local and Low-Rank Priors for Hyperspectral Image Compressive Imaging [J]. | IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING , 2024 , 10 : 1664-1679 . |
| MLA | Ying, Yangke et al. "Spectral Memory-Enhanced Network With Local Non-Local and Low-Rank Priors for Hyperspectral Image Compressive Imaging" . | IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 10 (2024) : 1664-1679 . |
| APA | Ying, Yangke , Wang, Jin , Shi, Yunhui , Ling, Nam , Yin, Baocai . Spectral Memory-Enhanced Network With Local Non-Local and Low-Rank Priors for Hyperspectral Image Compressive Imaging . | IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING , 2024 , 10 , 1664-1679 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Adaptive transform coding is gaining more and more attention for better mining of image content over fixed transforms such as discrete cosine transform (DCT). As a special case, graph transform learning establishes a novel paradigm for the graph-based transforms. However, there still exists a challenge for graph transform learning-based image codecs design on natural image compression, and graph representation cannot describe regular image samples well over graph-structured data. Therefore, in this article, we propose a cross-channel graph-based transform (CCGBT) for natural color image compression. We observe that neighboring pixels having similar intensities should have similar values in the chroma channels, which means that the prominent structure of the luminance channel is related to the contours of the chrominance channels. A collaborative design of the learned graphs and their corresponding distinctive transforms lies in the assumption that a sufficiently small block can be considered smooth, meanwhile, guaranteeing the compression of the luma and chroma signals at the cost of a small overhead for coding the description of the designed luma graph. In addition, a color image compression framework based on the CCGBT is designed for comparing DCT on the classic JPEG codec. The proposed method benefits from its flexible transform block design on arbitrary sizes to exploit image content better than the fixed transform. The experimental results show that the unified graph-based transform outperforms conventional DCT, while close to discrete wavelet transform on JPEG2000 at high bit-rates.
关键词 ：
graph-based transform (GBT) graph-based transform (GBT) discrete cosine transform discrete cosine transform image compression image compression dual graph dual graph Graph fourier transform (GFT) Graph fourier transform (GFT) graph learning graph learning
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wang, Lilong , Shi, Yunhui , Wang, Jin et al. Graph Based Cross-Channel Transform for Color Image Compression [J]. | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (4) . |
| MLA | Wang, Lilong et al. "Graph Based Cross-Channel Transform for Color Image Compression" . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20 . 4 (2024) . |
| APA | Wang, Lilong , Shi, Yunhui , Wang, Jin , Chen, Shujun , Yin, Baocai , Ling, Nam . Graph Based Cross-Channel Transform for Color Image Compression . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (4) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
In the Coded Aperture Snapshot Spectral Imaging (CASSI) systems, hyperspectral images (HSIs) reconstruction methods are employed to recover 3D signals from 2D compressive measurements. Among these methods, deep unfolding networks exhibit the benefits of interpretability and high efficiency, but they still have some notable shortcomings. Firstly, existing methods primarily exploit the spatial-spectral domain information of HSIs, neglecting exploration of the frequency domain, which is also beneficial to 3D HSIs. Secondly, current unfolding networks have limited utilization of information between different stages, failing to fully explore their relevance and thereby limiting the effectiveness of the overall framework. To address these issues, in this paper, we propose an integrated framework with dual-domain feature fusion and multi-level memory enhancement. Specifically, the former represents the first attempt to utilize frequency domain information in the feature space of HSIs overcoming the limitation of spatial-spectral domain features and thereby improving the data expression ability of the network by extracting dual-domain features. Simultaneously, our verification experiments also show that the proposed dual-domain feature representation can indeed extract complementary feature information in HSIs. Moreover, the latter aims to use the structural characteristics of the U-Net network to fully extract the correlation of information between different stages by designing a multi-level memory enhancement network. Extensive experimental results on various datasets validate the superiority of the proposed approach in both subjective and objective outcomes. Our proposed method achieves an average of 0.4dB improvement over the best counterpart method. And the code can be obtained from the link: https://github.com/yingyangke/DFFMM.
关键词 ：
Spectral snapshot compressive imaging Spectral snapshot compressive imaging Feature extraction Feature extraction Image coding Image coding Frequency-domain analysis Frequency-domain analysis Correlation Correlation Image reconstruction Image reconstruction Imaging Imaging deep unfolding network deep unfolding network Task analysis Task analysis compressive sensing compressive sensing
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Ying, Yangke , Wang, Jin , Shi, Yunhui et al. Dual-Domain Feature Fusion and Multi-Level Memory-Enhanced Network for Spectral Compressive Imaging [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (10) : 9562-9577 . |
| MLA | Ying, Yangke et al. "Dual-Domain Feature Fusion and Multi-Level Memory-Enhanced Network for Spectral Compressive Imaging" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34 . 10 (2024) : 9562-9577 . |
| APA | Ying, Yangke , Wang, Jin , Shi, Yunhui , Ling, Nam , Yin, Baocai . Dual-Domain Feature Fusion and Multi-Level Memory-Enhanced Network for Spectral Compressive Imaging . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (10) , 9562-9577 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
基于窗口注意力的神经数据依赖变换的图像压缩方法属于计算机视觉领域。考虑每个输入图像的率失真RD性能很有意义，现有方法没有充分考虑每个图像的概率属性和局部纹理，RD性能有待进一步提高。本发明中扩展的窗口注意力模型(EWAM)联合学习图像的概率属性和局部纹理。一种基于卷积神经网络的框架，包括以下组件：语法生成器和权重生成器，通过模型流来学习语法和语法权重；上下文模型，通过内容流来学习内容；超先验模型，通过潜在表示学习分布；以及EWAM，通过窗口注意力进一步提高概率属性的精度和局部纹理的清晰度。本发明不仅能够在线优化每张图像的RD性能，而且具有更清晰的纹理和结构，在客观指标上优于目前最先进的方法。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 施云惠 , 叶莉萍 , 王瑾 et al. 基于窗口注意力的神经数据依赖变换的图像压缩方法 : CN202310580643.7[P]. | 2023-05-23 . |
| MLA | 施云惠 et al. "基于窗口注意力的神经数据依赖变换的图像压缩方法" : CN202310580643.7. | 2023-05-23 . |
| APA | 施云惠 , 叶莉萍 , 王瑾 , 尹宝才 . 基于窗口注意力的神经数据依赖变换的图像压缩方法 : CN202310580643.7. | 2023-05-23 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
一种基于超先验可变码率图像压缩的精准R‑λ模型码率控制方法属于计算机视觉领域，针对基于超先验可变码率图像压缩框架无法对于单张图像的目标码率给出相应的拉格朗日乘子。本方法为任意图像和任意基于超先验可变码率图像压缩模型建立拉格朗日乘子λ和码率R的关系，提出精准R‑λ模型。通过3次编码拟合单张图像的精准R‑λ模型。计算出对应目标码率应该输入的拉格朗日乘子。最后对于该图像的任意输入码率，都可以输出与输入码率相近的输出码率，平均误差控制在0.6％下，实现精准的码率控制。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 施云惠 , 王鹏权 , 王瑾 et al. 一种基于超先验可变码率图像压缩的精准R-λ模型码率控制方法 : CN202310579557.4[P]. | 2023-05-23 . |
| MLA | 施云惠 et al. "一种基于超先验可变码率图像压缩的精准R-λ模型码率控制方法" : CN202310579557.4. | 2023-05-23 . |
| APA | 施云惠 , 王鹏权 , 王瑾 , 尹宝才 . 一种基于超先验可变码率图像压缩的精准R-λ模型码率控制方法 : CN202310579557.4. | 2023-05-23 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
a variable-rate image compression conditioned on a pixel-wise quality map achieved an outstanding rate-distortion trade-off compared to the approaches based on multiple models. However, it is hard to find an appropriate pixel-wise quality map for the target rate, and the hyperprior is only used to capture the probability distribution of latent representation, which causes its inefficient utilization. In this paper, we propose a variable-rate image compression network with shallow to deep hyperprior trained with a uniform quality map generated by the trade-off parameter 1 of the rate-distortion optimization. The shallow to deep hyperprior structure enables the shallow hyperprior to improve the reconstruction image quality by compensating the latent representation as side information while estimating its distribution. Inspired by the fact that a uniform quality map can continuously scale the latent representations with the continuous change of 1, we build an individual R-? model, which characterizes the relation between R and 1. With this R-? model, we can perform precise and continuous rate control in the compression. To the best of our knowledge, this R-? model is the first work to propose a continuous rate control for variable-rate learning-based image compression. Meanwhile, benefiting from the uniform values of the map, our method can handle various distortion metrics, such as MS-SSIM. Extensive experimental results show that the proposed model has achieved SOTA compression performance in variable-rate learning-based methods, achieving comparable compression performance compared with VVC. Furthermore, the rate control of our scheme shows very high accuracy.
关键词 ：
rate control rate control variable rate variable rate Image compression Image compression side information compensation side information compensation deep learning deep learning
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Shi, Yunhui , Zhang, Kangfu , Wang, Jin et al. Variable-Rate Image Compression Based on Side Information Compensation and R-? Model Rate Control [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2023 , 33 (7) : 3488-3501 . |
| MLA | Shi, Yunhui et al. "Variable-Rate Image Compression Based on Side Information Compensation and R-? Model Rate Control" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 33 . 7 (2023) : 3488-3501 . |
| APA | Shi, Yunhui , Zhang, Kangfu , Wang, Jin , Ling, Nam , Yin, Baocai . Variable-Rate Image Compression Based on Side Information Compensation and R-? Model Rate Control . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2023 , 33 (7) , 3488-3501 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
In the coded aperture snapshot spectral compressive imaging (CASSI) system, hyperspectral image (HSI) reconstruction methods are employed to recover 3D signals from 2D compressive measurements. Among these methods, although the deep unfolding networks show the advantages of interpretability and high efficiency, they still have the limitations of insufficient feature utilization and low efficiency of information interaction between stages. To solve these problems, in this paper two well-designed techniques, dubbed as dual-domain feature learning and feature memory-enhanced module, are introduced into a deep unfolding network. The former is proposed to enhance the representation ability of deep networks, while the latter is designed to efficiently promote the cross-stage information interaction. Extensive experimental results validate the efficiency and effectiveness of the proposed method.
关键词 ：
Compressed Sensing Compressed Sensing Image Restoration Image Restoration Spectral Snapshot Compressive Imaging Spectral Snapshot Compressive Imaging Deep Learning Deep Learning
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Ying, Yangke , Wang, Jin , Shi, Yunhui et al. Dual-Domain Feature Learning and Memory-Enhanced Unfolding Network for Spectral Compressive Imaging [J]. | 2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME , 2023 : 1589-1594 . |
| MLA | Ying, Yangke et al. "Dual-Domain Feature Learning and Memory-Enhanced Unfolding Network for Spectral Compressive Imaging" . | 2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME (2023) : 1589-1594 . |
| APA | Ying, Yangke , Wang, Jin , Shi, Yunhui , Yin, Baocai . Dual-Domain Feature Learning and Memory-Enhanced Unfolding Network for Spectral Compressive Imaging . | 2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME , 2023 , 1589-1594 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Point cloud upsampling is used to densify the sparse set of points collected by 3D sensors, which is widely used in the field of robotics. In this paper, a two-stage method is used to generate upsampling point cloud. In the first stage, the rough upsampling point cloud is generated, and in the second stage, the rough point cloud is refined to obtain high-quality point cloud. The generation of high quality point cloud heavily relies on feature extractors. In the first stage, we introduce a transformer model to improve the feature extraction effect, which helps to fully extract the features of different location points. A Refinement Unit is proposed in the second stage to improve the rough upsampling point cloud generated in the first stage. The Refinement Unit is based on another transformer model in which the relative position coding function improves the coordinates of the deviation points generated in the first stage. We evaluate our approach on synthetic data sets. Experimental results show that the performance of this method is better than other methods.
关键词 ：
point cloud upsampling point cloud upsampling deep learning deep learning transformer transformer
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Shi, Yunhui , Dong, Chao , Wang, Jin . A Two-Stage Transformer-Based Point Cloud Upsampling [J]. | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 : 1152-1157 . |
| MLA | Shi, Yunhui et al. "A Two-Stage Transformer-Based Point Cloud Upsampling" . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC (2023) : 1152-1157 . |
| APA | Shi, Yunhui , Dong, Chao , Wang, Jin . A Two-Stage Transformer-Based Point Cloud Upsampling . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 , 1152-1157 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
3D reconstruction has been applied to many research fields such as robots and computer vision with the fast development of technology. Despite significant progress, current 3D human pose and shape estimation methods still remain challenge to recovery 3D human mesh under occlusions. Previous works use a Iterative Error Feedback (IEF) loop to construct the regressor and often have disregarded information at occluded regions that make them difficult to handle occlusions. However, we argue that occluded regions have strong correlations with human body so that they can offer effective information for 3D human pose and shape estimation. To address this, we propose a multi-scale feature injection network MFINet, that utilizes the information at occluded regions as a secondary clews to enrich the image features in a coarse-to-fine manner. In MFInet, given the image feature at current scale, a Transformer-based module, called feature inject transformer module (FIM) is used to inject human feature into occluded region by considering their correlation. To this end, experiments show that our method is effective in both object and subject results on several benchmarks including Human3.6M, 3DPW, LSP and COCO.
关键词 ：
multi-scale multi-scale 3D human reconstruction 3D human reconstruction transformer transformer
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Shi, Yunhui , Ge, Yangyang , Wang, Jin . Multi-scale Feature Injection for Occluded 3D Human Pose and Shape Estimation [J]. | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 : 4881-4886 . |
| MLA | Shi, Yunhui et al. "Multi-scale Feature Injection for Occluded 3D Human Pose and Shape Estimation" . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC (2023) : 4881-4886 . |
| APA | Shi, Yunhui , Ge, Yangyang , Wang, Jin . Multi-scale Feature Injection for Occluded 3D Human Pose and Shape Estimation . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 , 4881-4886 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
