2019 Data Compression Conference (DCC)最新文献_第5页

Perceptually Optimized Bit-Allocation and Associated Distortion Measure for Block-Based Image or Video Coding 基于块的图像或视频编码的感知优化比特分配和相关失真测量

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00025

Christian R. Helmrich, S. Bosse, Mischa Siekmann, H. Schwarz, D. Marpe, T. Wiegand

{"title":"Perceptually Optimized Bit-Allocation and Associated Distortion Measure for Block-Based Image or Video Coding","authors":"Christian R. Helmrich, S. Bosse, Mischa Siekmann, H. Schwarz, D. Marpe, T. Wiegand","doi":"10.1109/DCC.2019.00025","DOIUrl":"https://doi.org/10.1109/DCC.2019.00025","url":null,"abstract":"It is well known that input-invariant quantization in perceptual image or video coding often leads to visually suboptimal results and that quantization parameter adaptation (QPA) based on a model of the human visual system can improve subjective coding quality. This paper introduces a simple low-complexity QPA algorithm, controlled using a block-wise perceptually weighted distortion measure representing a generalization of the PSNR metric. The weighting scheme of this WPSNR metric is based on a psychovisual model. It directly leads to a perceptually adapted scaling of the block-wise Lagrange parameter used in the bit-allocation process in the encoder and, consequently, to a block-wise QPA. Unlike prior QPA approaches, the proposal avoids classifications of picture regions and easily extends from still-image or grayscale to video or chromatic coding. The WPSNR metric also uses fewer algorithmic operations than e. g. the multiscale structural similarity measure (MS-SSIM). Due to the results of two formal subjective tests indicating its visual benefit, the QPA proposal has been adopted into VTM, the currently developed Versatile Video Coding (VVC) reference software.","PeriodicalId":167723,"journal":{"name":"2019 Data Compression Conference (DCC)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130528072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 19

Perception-Optimized Encoding for Visually Lossy Image Compression 视觉有损图像压缩的感知优化编码

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00104

Yuzhang Lin, Feng Liu, Miguel Hernández-Cabronero, Eze Ahanonu, M. Marcellin, A. Bilgin, A. Ashok

引用次数: 1

Incremental Deep Neural Network Pruning Based on Hessian Approximation 基于Hessian逼近的增量深度神经网络剪枝

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00102

Li Li, Zhu Li, Yue Li, B. Kathariya, S. Bhattacharyya

{"title":"Incremental Deep Neural Network Pruning Based on Hessian Approximation","authors":"Li Li, Zhu Li, Yue Li, B. Kathariya, S. Bhattacharyya","doi":"10.1109/DCC.2019.00102","DOIUrl":"https://doi.org/10.1109/DCC.2019.00102","url":null,"abstract":"In this paper, based on the Hessian approximation, an incremental pruning method is proposed to compress the deep neural network. The proposed method starts from the idea of using the Hessian to measure the \"importance\" of each weight in a deep neural network, and it mainly has the following key contributions. First, we propose to use the second moment in Adam optimizer as a measure of the \"importance\" of each weight to avoid calculating the Hessian matrix. Second, an incremental method is proposed to prune the neural network step by step. The incremental method can adjust the remaining non-zero weights of the whole network after each pruning to help boost the performance of the pruned network. Last but not least, the proposed method applies an automatically-generated global threshold for all the weights among all the layers, which achieves the inter-layer bit allocation automatically. Such a method can improve performance and save the complexity of adjusting the pruning threshold layer by layer. We perform a number of experiments on MNIST and ImageNet using commonly used neural networks such as AlexNet and VGG16 to show the benefits of the proposed algorithm. The experimental results show that the proposed algorithm is able to compress the network significantly with almost no loss of accuracy, which demonstrates the effectiveness of the proposed algorithm.","PeriodicalId":167723,"journal":{"name":"2019 Data Compression Conference (DCC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121287622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Hybrid Video Coding with Trellis-Coded Quantization 基于网格编码量化的混合视频编码

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00026

H. Schwarz, Tung Nguyen, D. Marpe, T. Wiegand

引用次数: 25

Texture-Classification Accelerated CNN Scheme for Fast Intra CU Partition in HEVC HEVC中纹理分类加速CNN方案的快速内部CU划分

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00032

Yongfei Zhang, Gang Wang, Rui Tian, Mai Xu, C.-C. Jay Kuo

{"title":"Texture-Classification Accelerated CNN Scheme for Fast Intra CU Partition in HEVC","authors":"Yongfei Zhang, Gang Wang, Rui Tian, Mai Xu, C.-C. Jay Kuo","doi":"10.1109/DCC.2019.00032","DOIUrl":"https://doi.org/10.1109/DCC.2019.00032","url":null,"abstract":"High Efficiency Video Coding (HEVC) achieves significant coding performance over H.264. However, the performance gain is achieved at the cost of substantially higher encoding complexity, in which the coding tree unit (CTU) partition is one of the most time-consuming parts due to the rate-distortion optimization-based ergodic search of all possible quad-tree partitions. To address this problem, this paper proposes a texture-classification accelerated convolutional neural network (CNN)-based fast intra CU partition scheme to reduce the encoding complexity for intra-coding in HEVC, by taking into consideration of the heterogeneous texture characteristics into the CNN-based classification. First, a threshold-based texture classification model is developed to identify the heterogeneous and homogeneous CTUs, through jointly consideration of the CU depth, quantization parameter and texture complexity. Second, three different CNN structures are designed and trained to predict the CU partition mode for each CU layer in the heterogeneous CTUs. Finally, extensive experimental results show that the proposed scheme can reduce intra-mode encoding time by 62.13% with negligible BD-rate loss of 2.01%, consistently outperforming two state-of-the-art CNN-based schemes in terms of both coding performance and complexity reduction.","PeriodicalId":167723,"journal":{"name":"2019 Data Compression Conference (DCC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127455876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

Multi-view Multi-modality Priors Residual Network of Depth Video Enhancement for Bandwidth Limited Asymmetric Coding Framework 带宽有限的非对称编码框架下多视点多模先验残差深度视频增强网络

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00072

Siqi Chen, Qiong Liu, You Yang

引用次数: 3

Selective Dynamic Compression 选择性动态压缩

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00095

S. T. Klein, Elina Opalinsky, Dana Shapira

引用次数: 4

Parameterized Text Indexing with One Wildcard 使用一个通配符的参数化文本索引

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00023

A. Ganguly, W. Hon, Yu-An Huang, S. Pissis, R. Shah, Sharma V. Thankachan

{"title":"Parameterized Text Indexing with One Wildcard","authors":"A. Ganguly, W. Hon, Yu-An Huang, S. Pissis, R. Shah, Sharma V. Thankachan","doi":"10.1109/DCC.2019.00023","DOIUrl":"https://doi.org/10.1109/DCC.2019.00023","url":null,"abstract":"Two equal-length strings X and Y over an alphabet Σ of size σ are a parameterized match iff X can be transformed to Y by renaming the character X[i] to the character Y[i] for 1 ≤ i ≤ |X| using a one-to-one function from the set of characters in X to the set of characters in Y. The parameterized text indexing problem is defined as: Index a text T of n characters over an alphabet set Σ of size σ, such that whenever a pattern P[1, p] comes as a query, we can report all occ parameterized occurrences of P in T. A position i ∊ [1, n] is a parameterized occurrence of P in T, iff P and T[i,(i+p-1)] are a parameterized match. We study an interesting generalization of this problem, where the pattern contains one wildcard character ϕ ∉ Σ that matches with any other character in Σ. Therefore, for a pattern P[1, p] = P_1ϕP_2, our task is to report all positions i in T, such that the string P_1 P_2 and the string obtained by concatenating T[i,(i+|P_1|-1)] and T[(i+|P_1|+1),(i+p-1)] are a parameterized match. We show that such queries can be answered in optimal O(p+occ) time per query using an O(n log n) space index. We then show how to compress our index into O(n log σ) space but with a higher query cost of O(p(log log n+logσ)+occ logσ).","PeriodicalId":167723,"journal":{"name":"2019 Data Compression Conference (DCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129848482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Extended Quad-Tree Partitioning for Future Video Coding 未来视频编码的扩展四叉树分区

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00038

Meng Wang, Junru Li, Li Zhang, Kai Zhang, Hongbin Liu, Shiqi Wang, S. Kwong, Siwei Ma

引用次数: 20

Hybrid Point Cloud Geometry Coding Using Planes and Octree Representation Models 使用平面和八叉树表示模型的混合点云几何编码

2019 Data Compression Conference (DCC) Pub Date : 2019-03-26 DOI: 10.1109/DCC.2019.00081

Antoine Dricot, J. Ascenso

{"title":"Hybrid Point Cloud Geometry Coding Using Planes and Octree Representation Models","authors":"Antoine Dricot, J. Ascenso","doi":"10.1109/DCC.2019.00081","DOIUrl":"https://doi.org/10.1109/DCC.2019.00081","url":null,"abstract":"Nowadays, point clouds are considered as a promising representation model for future 3D applications, such as augmented reality. However, large amounts of data are required to offer high quality immersive experiences, and therefore, compression efficiency is an important factor. Many of the current coding techniques rely on octree data structures, that offer several advantages such as scalability with layers offering multiple levels of detail. Although octrees are capable to efficiently represent a point cloud, geometric representations may also play an important role. In this context, the objective of this paper is to propose a hybrid point cloud compression solution based on plane estimation and coding that enhances the octree structure, thus exploiting two representation models for point clouds. In the proposed solution, the octree partitioning is adaptive and includes this novel plane coding mode for leaf nodes at different layers of the octree. A large increase in coding efficiency against the pure octree coding case is observed with average BD-rate gains of 35%, up to 68% reported. Moreover, in several cases it can also significantly outperform state-of-the-art solutions that are nowadays considered for standardization.","PeriodicalId":167723,"journal":{"name":"2019 Data Compression Conference (DCC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127912877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3