检索结果-内蒙古大学图书馆

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

3D reconstruction and error analysis of multi-view space-borne SAR images under different configurations

学校读者我要写书评

暂无评论

3D reconstruction and error analysis of multi-view space-bor...

IET International Radar Conference 2018, IRC 2018

作者： Wang, Chao Qiu, Xiaolan Li, Fangfang Lei, Bin University of the Chinese Academy of Sciences Beijing China Institute of Electrics Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electrics Chinese Academy of Sciences Beijing China

Synthetic aperture radar (SAR) has a good ability to detect the microwave scattering characteristics of the target and has a good capability of slant range Doppler positioning. Using multi-view SAR images in combination with image matching and positioning equations, the 3D position of the target can be obtained. In the past, multi-view 3D reconstruction mainly used side-looking images with parallel trajectories but different incident angles. That method is not universal for different configurations and lacks analysis of the relationship between solution and parameter error. This study aims at the problem of multi-view SAR 3D reconstruction. The authors establish general 3D reconstruction equations that can be used for non-parallel track and non-side-looking and the solution method is deduced. Based on this, an analysis method of error sensitivity is proposed and the dependence relationship between the reconstruction error and configuration, velocity, position, and slant range is analysed. The correctness of this method is verified by simulation experiments, which provides guidance for selection of configuration and sensor accuracy when applying 3D reconstruction. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Synthetic aperture radar

Deep learning-based video coding: A review and a case study

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Dong Li, Yue Lin, Jianping Li, Houqiang Wu, Feng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

The past decade has witnessed great success of deep learning technology in many disciplines, especially in computer vision and image processing. However, deep learning-based video coding remains in its infancy. This paper reviews the representative works about using deep learning for image/video coding, which has been an actively developing research area since the year of 2015. We divide the related works into two categories: new coding schemes that are built primarily upon deep networks (deep schemes), and deep network-based coding tools (deep tools) that shall be used within traditional coding schemes or together with traditional coding tools. For deep schemes, pixel probability modeling and auto-encoder are the two approaches, that can be viewed as predictive coding scheme and transform coding scheme, respectively. For deep tools, there have been several proposed techniques using deep learning to perform intra-picture prediction, inter-picture prediction, cross-channel prediction, probability distribution prediction, transform, post- or in-loop filtering, down- and up-sampling, as well as encoding optimizations. According to the newest reports, deep schemes have achieved comparable or even higher compression efficiency than the state-of-the-art traditional schemes, such as High Efficiency Video Coding (HEVC) based scheme, for image coding;deep tools have demonstrated the compression capability beyond HEVC for video coding. However, deep schemes have not yet reached the current height of HEVC for video coding, and deep tools remain largely unexplored at many aspects including the tradeoff between compression efficiency and encoding/decoding complexity, the optimization for perceptual naturalness or semantic quality, the speciality and universality, the federated design of multiple deep tools, and so on. In the hope of advocating the research of deep learning-based video coding, we present a case study of our developed prototype video codec, namely Deep Learning Vi

关键词： Video signal processing

LIQA: Lifelong blind image quality assessment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Jianzhao Zhou, Wei Xu, Jiahua Li, Xin An, Shukun Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Existing blind image quality assessment (BIQA) methods are mostly designed in a disposable way and cannot evolve with unseen distortions adaptively, which greatly limits the deployment and application of BIQA models in real-world scenarios. To address this problem, we propose a novel Lifelong blind Image Quality Assessment (LIQA) approach, targeting to achieve the lifelong learning of BIQA. Without accessing to previous training data, our proposed LIQA can not only learn new distortions, but also mitigate the catastrophic forgetting of seen distortions. Specifically, we adopt the Split-and-Merge distillation strategy to train a single-head network that makes task-agnostic predictions. In the split stage, we first employ a distortion-specific generator to obtain the pseudo features of each seen distortion. Then, we use an auxiliary multi-head regression network to generate the predicted quality of each seen distortion. In the merge stage, we replay the pseudo features paired with pseudo labels to distill the knowledge of multiple heads, which can build the final regressed single head. Experimental results demonstrate that the proposed LIQA method can handle the continuous shifts of different distortion types and even datasets. More importantly, our LIQA model can achieve stable performance even if the task sequence is long. Copyright © 2021, The Authors. All rights reserved.

关键词： Distillation

A New Non-local Video Denoising Scheme Using Low-Rank Representation and Total Variation Regularization

学校读者我要写书评

暂无评论

A New Non-local Video Denoising Scheme Using Low-Rank Repres...

IEEE International Symposium on Circuits and systems

作者： Qingbo Lu Zhenbo Lu Xiaoqing Tao Houqiang Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China

ISBN: (纸本)9781479934331

In this article, we present a novel non-local video denoising scheme using low-rank representation and total variation regularization. The proposed scheme attempts to make full use of the intrinsic properties that the grouping similar patches not only lie in a low-rank subspace but are also sparse in total variation (TV) domain. For a group of similar patches, we formulate video denoising problem into a concise model that combines nuclear norm, TV regularization and l_1 norm. The experiments demonstrate that the proposed scheme is capable of handling multi-type noise including dense Gaussian noise and random-valued sparse noise, while maintaining the texture information meantime. The results show that our scheme achieves noticeable performance improvement over the state-of-the-art video denoising methods.

关键词： video denoising low-rank representation total variation alternating direction method

SAR Image Compression Based on Low-Frequency Suppression and Target Perception 8th

学校读者我要写书评

暂无评论

SAR Image Compression Based on Low-Frequency Suppression and...

8th EAI International Conference on Machine Learning and Intelligent Communications, MLICOM 2023

作者： Deng, Jiawen Huang, Lijia Wu, Yifan Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783031717154

Synthetic Aperture Radar (SAR) images are widely used in the field of remote sensing. To store and transmit the growing amount of SAR image data, more efficient compression algorithms are required. In this paper, a new framework for compressing SAR images is proposed based on deep learning. Firstly, we propose a new two-stage transformation based on low-frequency suppression of input data to achieve high information entropy and low quantization loss. To explore the redundancy between regions of interest and regions of non-interest, an image compression model for target perception is proposed to convert the input SAR image into a compact latent representation together with the target perception map. To evaluate the performance of the algorithm, we conducted experiments on SAR image dataset. The results show that the proposed algorithm is significantly better than the traditional processing algorithm in terms of data input, and can effectively preserve and improve the performance of the image compression model. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Image compression

No-reference light field image quality assessment based on spatial-angular measurement

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shi, Likun 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

Light field image quality assessment (LFI-QA) is a significant and challenging research problem. It helps to better guide light field acquisition, processing and applications. However, only a few objective models have been proposed and none of them completely consider intrinsic factors affecting the LFI quality. In this paper, we propose a No-Reference Light Field image Quality Assessment (NR-LFQA) scheme, where the main idea is to quantify the LFI quality degradation through evaluating the spatial quality and angular consistency. We first measure the spatial quality deterioration by capturing the naturalness distribution of the light field cyclopean image array, which is formed when human observes the LFI. Then, as a transformed representation of LFI, the Epipolar Plane Image (EPI) contains the slopes of lines and involves the angular information. Therefore, EPI is utilized to extract the global and local features from LFI to measure angular consistency degradation. Specifically, the distribution of gradient direction map of EPI is proposed to measure the global angular consistency distortion in the LFI. We further propose the weighted local binary pattern to capture the characteristics of local angular consistency degradation. Extensive experimental results on four publicly available LFI quality datasets demonstrate that the proposed method outperforms state-of-the-art 2D, 3D, multi-view, and LFI quality assessment algorithms. Copyright © 2019, The Authors. All rights reserved.

关键词： Deterioration

Hierarchical co-segmentation of 3D point clouds for indoor scene

学校读者我要写书评

暂无评论

Hierarchical co-segmentation of 3D point clouds for indoor s...

International Conference on systems, Signals and Image processing, IWSSIP

作者： Yanting Lin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei City China

ISBN: (纸本)9781509063451

Segmentation of point clouds has been studied under a variety of scenarios. However, the segmentation of scanned point clouds for a clustered indoor scene remains significantly challenging due to noisy and incomplete data, as well as scene complexity. Based on the observation that objects in an indoor scene vary largely in scale but are typically supported by planes, we propose a co-segmentation approach. This technique utilizes the mutual agency between the point clouds captured at different times after the objects' poses change due to human actions. Hence, we hierarchically segment scenes from different times into patches and generate tree structures to store their relations. By iteratively clustering patches and co-analyzing them based on the relations between patches, we modify the tree structures and generate our results. To test the robustness of our method, we evaluate it on imperfectly scanned point clouds from a childroom, a bedroom, and two offices scenes.

关键词： Three-dimensional displays Image color analysis Geometry Mathematical model Principal component analysis Silicon

VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sheng, Xihua Li, Li Liu, Dong Li, Houqiang The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and – as usual – before being enhanced/analyzed by machine vision algorithms. Intuitively, it is more efficient to enhance/analyze the coded representations directly without decoding them into pixels. Therefore, we propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis, thereby being versatile for both human and machine vision. Our VNVC framework has a feature-based compression loop. In the loop, one frame is encoded into compact representations and decoded to an intermediate feature that is obtained before performing reconstruction. The intermediate feature can be used as reference in motion compensation and motion estimation through feature-based temporal context mining and cross-domain motion encoder-decoder to compress the following frames. The intermediate feature is directly fed into video reconstruction, video enhancement, and video analysis networks to evaluate its effectiveness. The evaluation shows that our framework with the intermediate feature achieves high compression efficiency for video reconstruction and satisfactory task performances with lower complexities. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks