检索结果-内蒙古大学图书馆

Learned video compression with feature-level residuals

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Feng, Runsen Wu, Yaojun Guo, Zongyu Zhang, Zhizheng Jin, Xin Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China

In this paper, we present an end-to-end video compression network for P-frame challenge on CLIC. We focus on deep neural network (DNN) based video compression, and improve the current frameworks from three aspects. First, we notice that pixel space residuals is sensitive to the prediction errors of optical flow based motion compensation. To suppress the relative influence, we propose to compress the residuals of image feature rather than the residuals of image pixels. Furthermore, we combine the advantages of both pixel-level and feature-level residual compression methods by model ensembling. Finally, we propose a step-by-step training strategy to improve the training efficiency of the whole framework. Experiment results indicate that our proposed method achieves 0.9968 MS-SSIM on CLIC validation set and 0.9967 MS-SSIM on test set. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Learned Video Compression with Feature-level Residuals

学校读者我要写书评

暂无评论

Learned Video Compression with Feature-level Residuals

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Runsen Feng Yaojun Wu Zongyu Guo Zhizheng Zhang Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

关键词： Image coding Training Optical imaging Adaptive optics Motion compensation Optical distortion Decoding

Multi-scale grouped dense network for VVC intra coding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xin 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

Versatile Video Coding (H.266/VVC) standard achieves better image quality when keeping the same bits than any other conventional image codec, such as BPG, JPEG, and etc. However, it is still attractive and challenging to improve the image quality with high compression ratio on the basis of traditional coding techniques. In this paper, we design the multi-scale grouped dense network (MSGDN) to further reduce the compression artifacts by combining the multi-scale and grouped dense block, which are integrated as the post-process network of VVC intra coding. Besides, to improve the subjective quality of compressed image, we also present a generative adversarial network (MSGDN-GAN) by utilizing our MSGDN as generator. Across the extensive experiments on validation set, our MSGDN trained by MSE losses yields the PSNR of 32.622 on average with teams"IMC" and"haha" at the bit-rate of 0.15 in Low-rate track. Moreover, our MSGDN-GAN could achieve the better subjective performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Image quality

From multi-view to hollow-3D: Hallucinated hollow-3D R-CNN for 3D object detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Deng, Jiajun Zhou, Wengang Zhang, Yanyong Li, Houqiang The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230026 China The Department of Computer Science University of Science and Technology of China Hefei230026 China

As an emerging data modal with precise distance sensing, LiDAR point clouds have been placed great expectations on 3D scene understanding. However, point clouds are always sparsely distributed in the 3D space, and with unstructured storage, which makes it difficult to represent them for effective 3D object detection. To this end, in this work, we regard point clouds as hollow-3D data and propose a new architecture, namely Hallucinated Hollow-3D R-CNN (H23D R-CNN), to address the problem of 3D object detection. In our approach, we first extract the multi-view features by sequentially projecting the point clouds into the perspective view and the bird-eye view. Then, we hallucinate the 3D representation by a novel bilaterally guided multi-view fusion block. Finally, the 3D objects are detected via a box refinement module with a novel Hierarchical Voxel RoI Pooling operation. The proposed H23D R-CNN provides a new angle to take full advantage of complementary information in the perspective view and the bird-eye view with an efficient framework. We evaluate our approach on the public KITTI Dataset and Waymo Open Dataset. Extensive experiments demonstrate the superiority of our method over the state-of-the-art algorithms with respect to both effectiveness and efficiency. The code will be made available at https://***/djiajunustc/H-23D_R-CNN. Copyright © 2021, The Authors. All rights reserved.

关键词： Object recognition

Texture-enhanced Light Field Super-resolution with Spatio-Angular Decomposition Kernels

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Zexi Chen, Xiaoming Wing, Henry Yeung, Fung Chung, Yuk Ying Chen, Zhibo School of Computer Science University of Sydney Australia School of Computer Science and Engineering Beijing Technology and Business University China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China China

Despite the recent progress in light field super-resolution (LFSR) achieved by convolutional neural networks, the correlation information of light field (LF) images has not been sufficiently studied and exploited due to the complexity of 4D LF data. To cope with such high-dimensional LF data, most of the existing LFSR methods resorted to decomposing it into lower dimensions and subsequently performing optimization on the decomposed sub-spaces. However, these methods are inherently limited as they neglected the characteristics of the decomposition operations and only utilized a limited set of LF sub-spaces ending up failing to sufficiently extract spatio-angular features and leading to a performance bottleneck. To overcome these limitations, in this paper, we comprehensively discover the potentials of LF decomposition and propose a novel concept of decomposition kernels. In particular, we systematically unify the decomposition operations of various sub-spaces into a series of such decomposition kernels, which are incorporated into our proposed Decomposition Kernel Network (DKNet) for comprehensive spatio-angular feature extraction. The proposed DKNet is experimentally verified to achieve considerable improvements compared with the state-of-the-art methods. To further improve DKNet in producing more visually pleasing LFSR results, based on the VGG network, we propose a LFVGG loss to guide the Texture-Enhanced DKNet (TE-DKNet) to generate rich authentic textures and enhance LF images’ visual quality significantly. We also propose an indirect evaluation metric by taking advantage of LF material recognition to objectively assess the perceptual enhancement brought by the LFVGG loss. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical resolving power

ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Muhan Zhang, Zhe Qiu, Xiaolan Gao, Silin Wang, Yue Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology China Suzhou Aerospace Information Research Institute Jiangsu Suzhou China Aerospace Information Research Institute Chinese Academy of Sciences China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Electrical and Computer Engineering Department George Mason University FairfaxVA United States

Tomographic SAR technique has attracted remarkable interest for its ability of three-dimensional resolving along the elevation direction via a stack of SAR images collected from different cross-track angles. The emerged compressed sensing (CS)-based algorithms have been introduced into TomoSAR considering its super-resolution ability with limited samples. However, the conventional CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity, and complex parameter fine-tuning. Aiming at efficient TomoSAR imaging, this paper proposes a novel efficient sparse unfolding network based on the analytic learned iterative shrinkage thresholding algorithm (ALISTA) architecture with adaptive threshold, named Adaptive Threshold ALISTA-based Sparse Imaging Network (ATASI-Net). The weight matrix in each layer of ATASI-Net is pre-computed as the solution of an offline optimization problem, leaving only two scalar parameters to be learned from data, which significantly simplifies the training stage. In addition, adaptive threshold is introduced for each azimuth-range pixel, enabling the threshold shrinkage to be not only layer-varied but also element-wise. Moreover, the final learned thresholds can be visualized and combined with the SAR image semantics for mutual feedback. Finally, extensive experiments on simulated and real data are carried out to demonstrate the effectiveness and efficiency of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

Efficient Sparse MIMO SAR Imaging with Fast Iterative Method Based on Back Projection and Approximated Observation

学校读者我要写书评

暂无评论

Efficient Sparse MIMO SAR Imaging with Fast Iterative Method...

Electronics and Electrical Engineering technology (EEET), International Conference on

作者： Pengyu Jiang Zhe Zhang Bingchen Zhang Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Suzhou Aerospace Information Research Institute Suzhou China

Compressed sensing technique is widely used in the field of multiple input multiple output (MIMO) radar imaging to suppress sidelobes and noise, bringing better imaging performance. However, many constraints are introduced to the sparse reconstruction model, current sparse microwave imaging model is based on several assumptions, such as far field assumption, which might not hold in some circumstances. In this paper, a novel two-dimensional sparse reconstruction method based on approximated observation is proposed. First, we obtain the measurement matrix by the inverse back-projection operator, and construct a two-dimensional sparse reconstruction model. Then, we adopt the minimax concave constraint as the regularization term and use the iterative soft threshold algorithm (ISTA) for sparse reconstruction. The method retains the advantages of the BP algorithm and the sparse reconstruction algorithm at the same time, and the distance between the target and the antenna array is not constrained by image reconstruction performance of the sparse reconstruction algorithm. Simulations and experiments demonstrate the effectiveness of the proposed method.

关键词： MIMO radar Simulation Imaging Radar imaging Reconstruction algorithms Sparse matrices Velocity measurement

Reinforced Bit Allocation under Task-Driven Semantic Distortion Metrics

学校读者我要写书评

暂无评论

Reinforced Bit Allocation under Task-Driven Semantic Distort...

IEEE International Symposium on Circuits and systems (IScas)

作者： Jun Shi Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (数字)9781728133201

ISBN: (纸本)9781728133218

Rapid growing intelligent applications require optimized bit allocation in image/video coding to support specific task-driven scenarios such as detection, classification, segmentation, etc. Some learning-based frameworks have been proposed for this purpose due to their inherent end-to-end optimization mechanisms. However, it is still quite challenging to integrate these task-driven metrics seamlessly into traditional hybrid coding framework. To the best of our knowledge, this paper is the first work trying to solve this challenge based on reinforcement learning (RL) approach. Specifically, we formulate the bit allocation problem as a Markovian Decision Process (MDP) and train RL agents to automatically decide the quantization parameter (QP) of each coding tree unit (CTU) for HEVC intra coding, according to the task-driven semantic distortion metrics. This bit allocation scheme can maximize the semantic level fidelity of the task, such as classification accuracy, while minimizing the bit-rate. We also employ gradient class activation map (Grad-CAM) and Mask R-CNN tools to extract task-related importance maps to help the agents make decisions. Extensive experimental results demonstrate the superior performance of our approach by achieving 43.1% to 73.2% bit-rate saving over the anchor of HEVC under the equivalent task-related distortions.

关键词： Task analysis Distortion Bit rate Image coding Semantics Encoding

Deep Learning-Based Nonlinear Transform for HEVC Intra Coding

学校读者我要写书评

暂无评论

Deep Learning-Based Nonlinear Transform for HEVC Intra Codin...

IEEE Visual Communications and Image processing (VCIP)

作者： Kun Yang Dong Liu Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

In the hybrid video coding framework, transform is adopted to exploit the dependency within the input signal. In this paper, we propose a deep learning-based nonlinear transform for intra coding. Specifically, we incorporate the directional information into the residual domain. Then, a convolutional neural network model is designed to achieve better decorrelation and energy compaction than the conventional discrete cosine transform. This work has two main contributions. First, we propose to use the intra prediction signal to reduce the directionality in the residual. Second, we present a novel loss function to characterize the efficiency of the transform during the training. To evaluate the compression performance of the proposed transform, we implement it into the High Efficiency Video Coding reference software. Experimental results demonstrate that the proposed method achieves up to 1.79% BD-rate reduction for natural videos.

关键词： Transforms Discrete cosine transforms Neural networks Transform coding Video coding Image coding Decoding