2023 Data Compression Conference (DCC)最新文献

Pixel-Wise Quantization for Image Compression 像素量化图像压缩

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00058

Liang Wei, Fangdong Chen, L. xilinx Wang, Xiaoyang Wu, Shiliang Pu

{"title":"Pixel-Wise Quantization for Image Compression","authors":"Liang Wei, Fangdong Chen, L. xilinx Wang, Xiaoyang Wu, Shiliang Pu","doi":"10.1109/DCC55655.2023.00058","DOIUrl":"https://doi.org/10.1109/DCC55655.2023.00058","url":null,"abstract":"This paper proposes a pixel-wise quantization (PWQ) method, which allows to reduce the quantization parameters (QPs) of simple pixels adaptively for the purpose of enhancing the subjective quality, since the distortions on simple pixels are more noticeable than those on complex pixels. For the pixel-wise prediction in Fig. 1, the pixel-wise reconstruction is implemented and the transformation is disabled, where the symbol “=” (or $^{prime prime}vee^{prime prime}/^{prime prime}gt^{prime prime}$) means the current prediction is the average value of the left and right reconstructions (or the upper/left reconstruction). And the PWQ method is applied in the same prediction direction and reconstruction order, with adjusting the current pixel QP $(Q_{pixel})$ adaptively by (1), where Qcb denotes the current block $mathrm{Q}mathrm{P}, T_{pred}$ denotes the predicted texture complexity based on the neighboring reconstruction pixels, and parameters $delta, Q_{jnd}, Q_{thres}$ and Tthres are preseted on the encoder and decoder side. So no additional syntax need to be transmitted in the bitstream. Moreover, for the transformation-off non-pixel-wise prediction, the straightforward extension of the PWQ method is designed to divide the coding block into simple and complex areas based on the above reference pixels, and reduce the pixel QP in simple areas. Qualitative results in Fig. 1 show that, the PWQ method can significantly improve the subjective quality by reducing the distortions on simple pixels, especially in the flat areas near the object edge and between the words on the screen content, and realizes more fine-grained pixel-level quantization compared with the traditional block-level quantization.","PeriodicalId":209029,"journal":{"name":"2023 Data Compression Conference (DCC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126040771","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: 0

Learning-based Point Cloud Geometry Coding Rate Control 基于学习的点云几何编码速率控制

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00079

Manuela Ruivo, André F. R. Guarda, F. Pereira

{"title":"Learning-based Point Cloud Geometry Coding Rate Control","authors":"Manuela Ruivo, André F. R. Guarda, F. Pereira","doi":"10.1109/DCC55655.2023.00079","DOIUrl":"https://doi.org/10.1109/DCC55655.2023.00079","url":null,"abstract":"Multimedia applications have been evolving towards providing users with more immersive and realistic experiences. A common way to model the light available for the users’ eyes is the so-called plenoptic function – a powerful 7D representation of light. There are three main types of 3D representation models for the plenoptic function, capable of expressing the light information needed to offer 6-Degrees of Freedom (DoF) experiences, namely light fields, meshes, and Point Clouds (PCs). This paper focuses on PCs since they allow representing and processing objects directly in the 3D space, facilitating user interaction and navigation in a multitude of application domains. Since the illusion of real surfaces is provided by high-density point sets, a good quality of experience requires a rather large set of points to represent a single PC, thus originating huge amounts of data to be stored and/or transmitted. Consequently, PC Coding (PCC) with significant compression levels is a must to reduce the PC data to more manageable sizes and bring PC-based applications to practical deployment. The promising results for image coding led the Joint Photographic Experts Group (JPEG) to launch a standardization project especially targeting Deep Learning (DL)-based PCC, with a final Call for Proposals in January 2022. The best performing response to this call [1] became the JPEG Pleno Learning-based PCC Verification Model (VM), which is the seed codec for the final standard. In this codec, the rate may be controlled through a set of coding parameters, largely depending on the specific PC to code, notably its sparsity and homogeneity.","PeriodicalId":209029,"journal":{"name":"2023 Data Compression Conference (DCC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122749010","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: 0

Optimizing Compression Schemes for Parallel Sparse Tensor Algebra 并行稀疏张量代数的优化压缩方案

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00084

Helen Xu, T. Schardl, Michael Pellauer, J. Emer

引用次数: 0

Multiple Description Audio Coding for Wireless Low-Frequency Sound Zones 无线低频声区的多描述音频编码

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00022

Jan Østergaard, Christian Pedersen, Mo Zhou, N. D. Koeijer, M. Møller

引用次数: 0

Compressed unordered integer sequences with fast direct access 具有快速直接访问的压缩无序整数序列

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00053

I. Zavadskyi

引用次数: 0

CNN Quadtree Depth Decision Prediction for Block Partitioning in HEVC Intra-Mode 基于HEVC Intra-Mode的CNN四叉树深度决策预测

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00054

Iris Linck, A. T. Gómez, G. Alaghband

{"title":"CNN Quadtree Depth Decision Prediction for Block Partitioning in HEVC Intra-Mode","authors":"Iris Linck, A. T. Gómez, G. Alaghband","doi":"10.1109/DCC55655.2023.00054","DOIUrl":"https://doi.org/10.1109/DCC55655.2023.00054","url":null,"abstract":"High Efficiency Video Coding. (HEVC) reflects the new international standardization for digital video coding technology. HEVC achieves higher compression compared to its antecessor at the expense of dramatically increasing coding complexity due to the use of a recursive quadtree to partition every frame to various block sizes, a process called prediction mode. We propose three CNNs based on VGGNet, one CNN for each CU size of 64x64, 32x32, and 16x16, as shown in Figure 1, to predict the quadtree levels for the CU blocks of HEVC reducing its code complexity. The new CNNs simplify the original VGGNet in terms of number of convolutional layers while maintaining the original 3x3 filters. As our model is designed to recognize the quadtree structure of a block of pixels instead of image categories, a shallow version of the VGGNet combined with our CU partition datasets will provide fast and accurate results. The accuracy of the model can be further improved because the input CU size is consistent with the size of CU encoded by HEVC, that avoids losses in the CU texture features. Our CNN models learn from three customized datasets of CU blocks encoded in the specific QP of 32. In this way there is no need to introduce QP as a parameter in the loss function used in other works, and further increase accuracy. Given the success of this idea, in the future models will have separate training for each QP of 22, 27 and 37, respectively.","PeriodicalId":209029,"journal":{"name":"2023 Data Compression Conference (DCC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114824041","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: 0

Mixed-precision Deep Neural Network Quantization With Multiple Compression Rates 多重压缩率的混合精度深度神经网络量化

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00075

Xuanda Wang, Wen Fei, Wenrui Dai, Chenglin Li, Junni Zou, H. Xiong

引用次数: 0

Semantically Adaptive JND Modeling with Object-wise Feature Characterization and Cross-object Interaction 基于对象特征表征和跨对象交互的语义自适应JND建模

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00072

Xia Wang, Haibing Yin, Tingyu Hu, Qing-hua Sheng

引用次数: 0

Permutation coding using divide-and-conquer strategy 采用分治策略的排列编码

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00046

Kun Tu, D. Puchala

{"title":"Permutation coding using divide-and-conquer strategy","authors":"Kun Tu, D. Puchala","doi":"10.1109/DCC55655.2023.00046","DOIUrl":"https://doi.org/10.1109/DCC55655.2023.00046","url":null,"abstract":"In computer science permutations are used, e.g., in the tasks of pattern searching, duplicate documents detection and data compression [1], [2]. For this reason the reduction of redundancy leading to succinct representation of permutations is of great importance. In this paper, we introduce a novel method for succinct representation of permutations where the average number of bits per element required to encode permutations is $log_{2}n-1.269$, which is close to the theoretic limit. Furthermore, it is possible to formulate precise expressions for the average value, lower, and upper bounds to the number of bits required by the method. Let n be an integer power of 2. Then the proposed method can be described as follows: (i) the method follows the ‘‘divide-and-conquer’’ strategy and at each stage a considered permutation is divided into two equal halves (bins), (ii) binary encoding is used to describe elements-to-bins assignment (’ 0’-first, ‘l’-second bin), (iii) depending on a permutation some bits can be omitted, which leads to succinct representation. For instance, let $pi_{2}=(0,2,1,3,7,6,4,5)$. We start with the identity permutation $pi_{1}=(0,1,2,3,4,5,6,7)$. At the first stage $pi_{1}$ is split between two bins in relation to $pi_{2}$ as $pi_{1}=(0,1,2,3|4,5,6,7)$ which is encoded with bits ‘0000’. At the second stage we repeat the same operations leading to $pi_{1}=(0,2|1,3|6,7|4,5)$, and formulate the coding bits ‘01011’ Finally, at the last stage, we get $pi_{1}=pi_{2}=(0|2|1|3|7|6|4|5)$ encoded as ‘0010’. The concatenated bits give the unique code $C=0000010110010$ for $pi_{2}$. The lower and upper bounds for the length of codes $displaystyle frac{1}{n}|C|$ are $G^{min}(n)=displaystyle frac{1}{2}log_{2}n$ and $G^{max}left(nright)=displaystyle log_{2}n-left(1-frac{1}{n}right)$. The average number of bits per element required to encode permutations can be calculated as:","PeriodicalId":209029,"journal":{"name":"2023 Data Compression Conference (DCC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131719652","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: 0

Point Cloud Geometry Compression via Density-Constrained Adaptive Graph Convolution 基于密度约束的自适应图卷积的点云几何压缩

2023 Data Compression Conference (DCC) Pub Date : 2023-03-01 DOI: 10.1109/DCC55655.2023.00076

Dan Wang, Jin Wang, Yunhui Shi, Nam Ling, Baocai Yin

引用次数: 0