检索结果-内蒙古大学图书馆

Learning omni-frequency region-adaptive representations for real image super-resolution

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xin Jin, Xin Yu, Tao Pang, Yingxue Sun, Simeng Zhang, Zhizheng Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. In this paper, we propose an Omni-frequency Region-adaptive Network (OR-Net) to address both challenges, here we call features of all low, middle and high frequencies omni-frequency features. Specifically, we start from the frequency perspective and design a Frequency Decomposition (FD) module to separate different frequency components to comprehensively compensate the information lost for real LR image. Then, considering the different regions of real LR image have different frequency information lost, we further design a Region-adaptive Frequency Aggregation (RFA) module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions. The extensive experiments endorse the effective, and scenario-agnostic nature of our OR-Net for RealSR. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical resolving power

learning disentangled feature representation for Hybrid-distorted image restoration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xin Jin, Xin Lin, Jianxin Yu, Tao Liu, Sen Wu, Yaojun Zhou, Wei Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions. Specifically, we propose the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization. We also propose a feature aggregation module (FAM) with channel-wise attention to adaptively filter out the distortion representations and aggregate useful content information from different channels for the construction of raw image. The effectiveness of the proposed scheme is verified by visualizing the correlation matrix of features and channel responses of different distortions. Extensive experimental results also prove superior performance of our approach compared with the latest HD-IR schemes. Copyright © 2020, The Authors. All rights reserved.

关键词： Image reconstruction

Deep multi-scale features learning for distorted image quality assessment

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhou, Wei Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Image quality assessment (IQA) aims to estimate human perception based image visual quality. Although existing deep neural networks (DNNs) have shown significant effectiveness for tackling the IQA problem, it still needs to improve the DNN-based quality assessment models by exploiting efficient multi-scale features. In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction. Our model is based on both residual maps and distorted images in luminance domain, where the proposed network contains spatial pyramid pooling and feature pyramid from the network structure. Our proposed network is optimized in a deep end-to-end supervision manner. To validate the effectiveness of the proposed method, extensive experiments are conducted on four widely-used image quality assessment databases, demonstrating the superiority of our algorithm. © 2020, CC BY.

关键词： Deep neural networks

Towards Semantically Scalable Image Coding using Semantic Map

学校读者我要写书评

暂无评论

Towards Semantically Scalable Image Coding using Semantic Ma...

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Ning Yan Dong Liu Houqiang Li Feng Wu Zhiwei Xiong Zheng-Jun Zha CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei 230027 China

ISBN: (数字)9781728133201

ISBN: (纸本)9781728133218

We propose an image coding scheme that compresses image into semantically scalable bitstream using deep neural networks. This scheme is expected to support intelligent analysis when the bitstream is partially decoded, as well as high-fidelity reconstruction of image when the bitstream is completely decoded. We implement such a semantically scalable image coding scheme based on semantic map. In the proposed scheme, the original image is firstly semantically segmented and the semantic map is compressed as the base layer. Then, the original image is segmented into several individual objects according to the semantic map, and each object is coded separately. A recurrent neural network-based encoder is used to compress these objects at several quality levels. At the decoder side, the semantic map can be directly applied for intelligent analysis. A generative adversarial network is used to synthesize a rough image using the semantic map. If user is interested in a certain object, more bits can be transmitted to enhance the quality of the object. Experimental results show that the proposed method achieves comparable compression performance with JPEG2000 at high bit rates, while facilitates intelligent analysis at low bit rates.

关键词： Semantics Image coding Image reconstruction Transform coding Encoding Image segmentation Scalability

Blind omnidirectional image quality assessment with viewport oriented graph convolutional networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Jiahua Zhou, Wei Chen, Zhibo CAS Key Laboratory of Technology Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Quality assessment of omnidirectional images has become increasingly urgent due to the rapid growth of virtual reality applications. Different from traditional 2D images and videos, omnidirectional contents can provide consumers with freely changeable viewports and a larger field of view covering the 360° × 180° spherical surface, which makes the objective quality assessment of omnidirectional images more challenging. In this paper, motivated by the characteristics of the human vision system (HVS) and the viewing process of omnidirectional contents, we propose a novel Viewport oriented Graph Convolution Network (VGCN) for blind omnidirectional image quality assessment (IQA). Generally, observers tend to give the subjective rating of a 360-degree image after passing and aggregating different viewports information when browsing the spherical scenery. Therefore, in order to model the mutual dependency of viewports in the omnidirectional image, we build a spatial viewport graph. Specifically, the graph nodes are first defined with selected viewports with higher probabilities to be seen, which is inspired by the HVS that human beings are more sensitive to structural information. Then, these nodes are connected by spatial relations to capture interactions among them. Finally, reasoning on the proposed graph is performed via graph convolutional networks. Moreover, we simultaneously obtain global quality using the entire omnidirectional image without viewport sampling to boost the performance according to the viewing experience. Experimental results demonstrate that our proposed model outperforms state-of-the-art full-reference and no-reference IQA metrics on two public omnidirectional IQA databases. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Target Amplitude Characteristic Analysis With Neighborhood information Using C-band Circular SAR Data

学校读者我要写书评

暂无评论

Target Amplitude Characteristic Analysis With Neighborhood I...

IEEE International Conference on Radar

作者： Xiaoyang Yue Fei Teng Yun Lin Wen Hong Key Laboratory of Spatial Information Processing and Application System Technology Areospace Information Research Institute Chinese Academy of Sciences Beijing China School of Electronic Information Engineering North China University of Technology Beijing China

ISBN: (纸本)9781665468893

The circular synthetic aperture radar (SAR) can observe the experimental scene from all angles. The backscatter intensity of the target in the scene can be obtained. Different targets in the imaging scene show different amplitude characteristics. For example, significant targets such as buildings and oil tanks show strong response characteristics at certain angles, and secondly, weak response characteristics for targets is shown such as grass and ground. In this article, the omnidirectional scattering intensity data of the target obtained from the radar is used to analyze the amplitude characteristics, and the model is established for different targets to obtain the final result. The fuzzy C-means (FCM) model combined with neighborhood information is used to analyze the target amplitude characteristics. The amplitude characteristics of the target are divided into two categories: strong response and weak response for analysis. The initial two types of cluster centers are set for iteration and finally the target amplitude characteristic reference values at different angles are obtained. C-band circular SAR data is used to validate our method. As a result, the amplitude characteristics of the whole scene using membership degree can be described.

关键词： Analytical models C-band Buildings Scattering Imaging Fuel storage Radar scattering

LIRA: Lifelong image restoration from unknown blended distortions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianzhao Lin, Jianxin Li, Xin Zhou, Wei Liu, Sen Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-trained expert models specializing in individual distortion removal task work cooperatively and adaptively to handle blended distortions. When the input is degraded by a new distortion, inspired by adult neurogenesis in human memory system, we develop a neural growing strategy where the previously trained model can incorporate a new expert branch and continually accumulate new knowledge without interfering with learned knowledge. Experimental results show that the proposed approach can not only achieve state-of-the-art performance on blended distortions removal tasks in both PSNR/SSIM metrics, but also maintain old expertise while learning new restoration tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Image reconstruction

Impulsive Formation Control of Nonlinear Leader-Following Multi-agent systems with Input Saturation*

学校读者我要写书评

暂无评论

Impulsive Formation Control of Nonlinear Leader-Following Mu...

Industrial Cyber-Physical systems (ICPS)

作者： Ni Zhang Xiaowei Jiang Xianhe Zhang Le You School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China School of Electrical Engineering and Automation Hubei Normal University Huangshi China

Leader-following formation analysis problem for a second-order nonlinear multi-agent system(MAS) with input saturation is investigated in this paper. And the impulsive formation control algorithm is introduced in the designed protocol which only works at the impulse times. Owing to the real-world limited communication channels, input saturation is considered in the impulsive controller. Furthermore, based on Lyapunov stability theories, Kronecker properties, eigenvalue and so on, some sufficient conditions that guarantee the leader-following consensus of MAS are obtained. Lastly, several simulations are worked out to verify the correctness and effectiveness of the theoretical results.

关键词： Sufficient conditions Protocols Simulation Communication channels Cyber-physical systems Control systems Formation control

A Compact and Robust 3d Local Feature Descriptor Based on Cumulative Multi-Feature Images

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Li, Raobo Yuan, Xiping Gan, Shu Bi, Rui Gao, Sha Luo, Weidong Hu, Lin Chen, Cheng School of Land and Resources Engineering Kunming University of Science and Technology Kunming650093 China Plication Engineering Research Center of Spatial Information Surveying and Mapping Technology in Plateau and Mountainous Areas Set by Universities in Yunnan Province Kunming650093 China Key Laboratory of Mountain Real Scene Point Cloud Data Processing Application for Universities West Yunnan University of Applied Sciences Dali671006 China

The 3D local surface description is a crucial aspect within the domain of computer vision. This paper advances a novel approach that leverages a repeatable local reference frame (LRF) and a cumulative multi-feature images (CMFI) for a more thorough representation of the feature space. The method starts by estimating the z-axis of the LRF using a weighted covariance matrix derived from the partial points in the neighborhood of the key points, while the x-axis is calculated through the utilization of spatial mechanics model. Subsequently, the neighboring points of the key points are projected onto three orthogonal planes, the spatial features (point cloud density, depth and horizontal distance) of the projected points are estimated, and the statistics of these features are defined as CMFI after accumulation. Finally, the performance of the CMFI is analyzed comprehensively through comparison with state-of-the-art descriptors, with the results demonstrating the descriptiveness and compactness of the CMFI. © 2023, The Authors. All rights reserved.

关键词： Covariance matrix