2010 IEEE International Workshop on Multimedia Signal Processing最新文献_第5页

Depth-aided image inpainting for novel view synthesis 用于新型视图合成的深度辅助图像绘制

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662013

Ismaël Daribo, B. Pesquet-Popescu

引用次数: 151

Multistage compressed-sensing reconstruction of multiview images 多视角图像的多级压缩感知重构

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662003

M. Trocan, Thomas Maugey, Eric W. Tramel, J. Fowler, B. Pesquet-Popescu

引用次数: 19

Robust foreground segmentation for GPU architecture in an immersive 3D videoconferencing system 沉浸式3D视频会议系统中GPU架构的鲁棒前景分割

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5661997

J. Civit, Ò. Escoda

{"title":"Robust foreground segmentation for GPU architecture in an immersive 3D videoconferencing system","authors":"J. Civit, Ò. Escoda","doi":"10.1109/MMSP.2010.5661997","DOIUrl":"https://doi.org/10.1109/MMSP.2010.5661997","url":null,"abstract":"Current telepresence systems, while being a great step forward in videoconferencing, still have important points to improve in what eye-contact, gaze and gesture awareness concerns. Many-to-many communications are going to greatly benefit from mature auto-stereoscopic 3D technology; allowing people to engage more natural remote meetings, with proper eye-contact and better spatiality feeling. For this purpose, proper real-time multi-perspective 3D video capture is necessary (often based on one or more View+Depth data sets). Given current state of the art, some sort of foreground segmentation is often necessary at the acquisition in order to generate 3D depth maps with hight enough resolution and accurate object boundaries. For this, one needs flicker-less foreground segmentations, accurate to borders, resilient to noise and foreground shade changes, and able to operate in real-time on performing architectures such as GPGPUs. This paper introduces a robust Foreground Segmentation approach used within the experimental immersive 3D Telepresence system from EU-FP7 3DPresence project. The proposed algorithm is based on a costs minimization using Hierarchical Believe Propagation and outliers reduction by regularization on oversegmented regions. The iterative nature of the approach makes it scalable in complexity, allowing it to increase accuracy and picture size capacity as GPGPUs become faster. In this work, particular care in the design of foreground and background cost models has also been taken in order to overcome limitations of previous work proposed in the literature.","PeriodicalId":105774,"journal":{"name":"2010 IEEE International Workshop on Multimedia Signal Processing","volume":"43 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131751620","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

Depth consistency testing for improved view interpolation 深度一致性测试改进的视图插值

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662051

P. Rana, M. Flierl

引用次数: 16

Optimizing the free distance of Error-Correcting Variable-Length Codes 纠错变长码自由距离的优化

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662027

A. Diallo, C. Weidmann, M. Kieffer

引用次数: 4

Scalable-to-lossless transform domain distributed video coding 可缩放到无损变换域分布式视频编码

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662041

Xin Huang, Anna Ukhanova, A. Veselov, Søren Forchhammer, M. Gilmutdinov

引用次数: 0

Error concealment considering error propagation inside a frame 考虑帧内错误传播的错误隐藏

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662053

Jun Wang, Yichun Tang, Hao Sun, S. Goto

{"title":"Error concealment considering error propagation inside a frame","authors":"Jun Wang, Yichun Tang, Hao Sun, S. Goto","doi":"10.1109/MMSP.2010.5662053","DOIUrl":"https://doi.org/10.1109/MMSP.2010.5662053","url":null,"abstract":"Transmission of compressed video over error prone channels may result in packet losses or errors, which can significantly degrade the image quality. Such degradation even becomes worse in 1Seg video broadcasting, which is widely used in Japan and Brazil for mobile phone TV service recently, where errors are drastically increased and lost areas are contiguous. Therefore the errors in earlier concealed MBs (macro blocks) may propagate to the MBs later to be concealed inside the same frame (spatial domain). The error concealment (EC) is used to recover the lost data by the redundancy in videos. Aiming at spatial error propagation (SEP) reduction, this paper proposes a SEP reduction based EC (SEPEC). In SEPEC, besides the mismatch distortion in current MB, the potential propagated mismatch distortion in the following to be concealed MBs is also minimized. Also, 2 extensions of SEPEC, that SEPEC with refined search and SEPEC with multiple layer match are discussed. Compared with previous work, the experiments show SEPEC achieves much better performance of video recovery and excellent trade-off between quality and computation in 1Seg broadcasting in terms of computation cost.","PeriodicalId":105774,"journal":{"name":"2010 IEEE International Workshop on Multimedia Signal Processing","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117040068","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: 1

Optimized decomposition basis using Lanczos filters for lossless compression of biomedical images 利用Lanczos滤波器优化分解基础，对生物医学图像进行无损压缩

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662005

Jonathan Taquet, C. Labit

引用次数: 10

Motion vector forecast and mapping (MV-FMap) method for entropy coding based video coders 基于熵编码的视频编码器的运动矢量预测和映射(MV-FMap)方法

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5662020

J. L. Tanou, Jean-Marc Thiesse, Joël Jung, M. Antonini

引用次数: 0

A comparative study between different pre-whitening decorrelation based acoustic feedback cancellers 基于预白化去相关的不同声反馈消除器的比较研究

2010 IEEE International Workshop on Multimedia Signal Processing Pub Date : 2010-12-10 DOI: 10.1109/MMSP.2010.5661984

K. Essafi, S. B. Jebara

引用次数: 1