位置：立项数据库 > 立项详情页
高逼真度视听系统的理论与方法
  • 项目名称：高逼真度视听系统的理论与方法
  • 项目类别：创新研究群体科学基金
  • 批准号：61121002
  • 申请代码：F0205
  • 项目来源：国家自然科学基金
  • 研究期限：2012-01-01-2014-12-31
  • 项目负责人：高文
  • 负责人职称：教授
  • 依托单位：北京大学
  • 批准年度：2011
中文摘要：

音像完美或图像清晰的多媒体系统是家庭数字影院、数字电视、激光视盘、远程医疗等产业追求的理想目标。近年来视音频性能逐步演进，视频从标清到高清HDTV，进而到超高清UHDTV，以及三维视频；音频从单声道到立体声，进而5.1和7.1声道，甚至22.2声道。随着视音频质量的提升，数据量也在迅速增加，日本SHV系统的原始数据量甚至超过59Gbps，由此带来了很多新的技术挑战。例如，如何有效压缩音视频以便合理控制传输和存储成本。为了解决这些难题，课题组拟研究基于视觉特性和模型的高效编码理论与技术和主客观质量评价方法；研究基于计算机视觉理论的二维至三维视频转换与生成技术；研究基于统计学习的图像与视频表达模型与算法；研究复杂视听场景的虚实融合、三维呈现与交互所需的高效计算方法。课题组将参与下一代国家和国际视频编码标准制订，力争成为本领域国际上有影响的创新团队，为国家和行业的重大需求提供理论方法与核心技术

中文主题词： 图像处理；视频处理；三维视频；虚拟现实；音视频标准
英文摘要：

image processing；video processing；3D video；virtual reality；audio and video standards

英文主题词： image processing；video processing；3D video；virtual reality；audio and video standards
结论摘要：

高逼真度图像、音频与视频需求带来了若干理论和方法的挑战。在过去三年中，本创新研究群体重点开展了高逼真度视听信息表示与重构的理论与方法、高逼真度视听信息编码理论与方法、视听场景呈现与高效计算等方面的研究。本创新研究群体取得的主要进展包括（1）针对高逼真度视听信息表示与重构的理论与方法，在视觉基元熵、Mumford-Shah泛函正则化理论和硬件加速重建方法、超分辨重建方面取得进展；（2）针对高逼真度视频编码理论与方法，在非精确背景建模编码方面有显著进展；（3）针对高逼真度声音场景分析、音频编码理论与方法，在声音场景分析模型和多通道编码方面取得进展；（4）针对视听场景呈现与高效计算，在全局场景构建和虚实融合、场景特征抽取取得进展。在开展上述基础研究的同时，开发了系列原型工具与平台，并将研究成果应用于多项实际项目。本创新研究群体新增国家自然科学基金委“杰出青年基金”获得者1人和“优秀青年基金”获得者1人，中国科协“求是杰出青年奖成果转化奖” 获得者1人。在本项目基金支持下，基于本项目的研究成果，本创新研究群体构建了一个基于GPU集群的多屏拼接并行绘制系统和一套22.2声道的高逼真度、高临场感的环绕声播放系统，有利于进一步开展高逼真度视听系统的研究。经过3年的发展，本创新研究群体的合作研究不断深化和聚焦，重大科学问题日趋明确，国际化水平和国际竞争力不断提升，学术环境日益和谐，为进一步的研究工作奠定了良好基础。

成果综合统计
成果类型
数量
  • 期刊论文
  • 会议论文
  • 专利
  • 获奖
  • 著作
  • 88
  • 138
  • 0
  • 0
  • 0
期刊论文
Image Restoration Using Joint Statistical Modeling in a Space-Transform Domain
基于位置的多线索可视化显示
Difficulty Guided Image Retrieval Using Linear Multiple Feature Embedding
Low Complexity Adaptive View Synthesis Optimization in HEVC Based 3D Video Coding
X射线相位衬度层析成像的数学模型
<b>A Comparative Study on Selecting Acoustic Modeling Units in Deep Neural Networks based Larg
On the uniqueness and non-uniqueness of the positive Z-eigenvector for transition probability tensor
Differential phase-contrast interior tomography
Robust Simulation of Small-Scale Thin Features in SPH-based Free Surface Flows
String-averaging expectation-maximization for maximum likelihood estimation in emission tomography
结合用户交互行为和资源内容的资源推荐
Rate-adaptive Compact Fisher Codes for Mobile Visual Search
Recovering Missing Contours for Occluded Object Detection
X射线相位相位衬度层析成像的数学模型
Superiorization of EMAlgorithm and Its Application in Single-Photon Emission Computed Tomography(SPE
Transform invariant text extraction
Moment-based cosh-Hilbert Inversion and Its Applications in Single-photon Emission Computed Tomograp
Towards Mobile Document Retrieval for Digital Library
Background-Modeling Based Adaptive Prediction for Surveillance Video Coding
A Shape Reconstructability Measure of Object Part Importance with Applications to Object Detection a
<span>A Compact Representation for Compressing Converted Stereo Videos</span>
Solving Principal Component Pursuit in Linear Time via l1 Filtering
IEEE 1857 Standard Empowering Smart Video Surveillance Systems
Radiative transfer equation for media with spatially varying refractive index
Learning Markov random walks for robust subspace clustering&nbsp;and estimation<br />
A Regularized Approach for Geodesic-Based&nbsp;Semisupervised Multimanifold Learning<br />
Manifold regularized multitask learning for semi-supervised multi -label image classification
面向大语料库的语音合成方法研究
<em>Visibility studies in grating-based neutron phase contrast and dark-field imaging by parti
The Lasso under Poisson-like heteroscedasticity
Rate-GOP Based Rate Control for High Efficiency Video Coding
Mode Dependent Coding Tools for Video Coding
Temporally pre-presented lipreading cues release speech from informational masking
Disappearance of the unmasking effect of temporally pre-presented lipreading cues on speech recognit
Approximate Poisson disk sampling on mesh
Large-margin Multi-view Information Bottleneck
Superiorization of em algorithm and its application in single-photon emission computed tomography(sp
A Low Complexity Interest Point Detector
<em>A Hierarchical Bayesian Approach for Aerosol Retrieval Using MISR Data</em>
28. Some variational principles for Z-eigenvalues of nonnegative tensors
Linearized Alternating Direction Method with Adaptive Penalty and Warm Starts for Fast Solving Trans
Regularizing properties of the Mumford-Shah functional for imaging applications
The order of convergence for Landweber Scheme with α,β –rule
Representing Visual Objects in HEVC Coding Loop, IEEE Journal on Emerging and Selected Topics in Cir
A Comparison of Typical lp Minimization Algorithms
2-D shape completion with shape priors
A Distributed 2D-to-3D Video Conversion System
Multiple Hypotheses Bayesian Frame Rate Up-conversion by Adaptive Fusion of Motion-compensated Inter
Local Poisson SPH For Viscous Incompressibility Fluids
近场结构化头相关传输函数的测量与分析
Bases Sorting: Generalizing the Concept of Frequency for Over-complete Dictionaries
How slow is Shannon's reconstruction for bandlimited&nbsp;signals?<br />
Perceptual Video Coding Based on SSIM-Inspired Divisive Normalization
Convergence Results of Landweber Iterations for Linear Systems
VARIATIONAL ITERATIVE ALGORITHMS IN PHOTOACOUSTIC TOMOGRAPHY WITH VARIABLE SOUND SPEED
Editing Vector Graphics in the Virtual Simulation Environment
A survey on the spectral theory of nonnegative tensors
Cosh-Hilbert变换反演的矩方法及其在单光子发射计算机断层成像中的应用
一种基于变换系数拉普拉斯分布的HEVC码率控制算法
用于视觉词语生成的概率预测器
会议论文
G-CAST: Gradient Based Image SoftCast for Perception-Friendly Wireless Visual Communication
Robust Low-Rank Regularized Regression for Face Recognition with Occlusion
On the interoperability of local descriptors compression
Robust fisher codes for large scale image retrieval
Query-Based Composition for Large-Scale Language Model in LVCSR
Jigsaw: Indoor Floor Plan Reconstruction via Mobile Crowdsensing
Single Underwater Image Enhancement with an Improved Optical Model
A Background Proportion Adaptive Lagrange Multiple Selection Method for Surveillance Video on High E
Overview of the IEEE 1857 Surveillance Groups
Correntropy Induced L2 Graph for Robust Subspace Clustering
Correlation Adaptive Subspace Segmentation by Trace Lasso
A Counterexample for the Validity of Using Nuclear Norm as a Convex Surrogate of Rank
纹理属性保持的三维网格模型简化算法
Multi layer based rate control algorithm for HEVC
Prosodic Modeling with Rich Syntactic Context in HMM-based Mandarin Speech Synthesis
Towards compact topical descriptors
Exploiting visual word co-occurrence for image retrieval
Hybrid Silhouette and Key-point Driven 3D-2D Registration
Reducing Blocking Artifacts in Compressed Images via Transformdomain Non-local Coefficients Estimati
Performance analysis of transform in uncoded wireless visual communication
3D texture mapping in multi-view reconstruction
Simplified AMVP for High Efficiency Video Coding
Content adaptive in-loop depth map filter for HEVC based 3DV coding
Smooth Representation Clustering
Background-Foreground Division based Search for Motion Estimation in Surveillance Video Coding
Surveillance Video Coding with Quadtree Partition Based ROI Extraction
Exploiting image local and nonlocal consistency for mixed Gaussian-impulse noise removal
Zero-Synthesis View Difference Aware View Synthesis Optimization For Hevc Based 3d Video Compression
Adaptive Rate control for High Efficiency video Coding
An Improved Color Image Demosaicking Algorithm
A Method of Perceptual-based Shape Decomposition
Low Complexity Rate Distortion Optimization for HEVC
Vector-valued Multi-view Semi-supervised Learning for Multi-label Image Classification
Online learning of COM trajectory for humanoid robot locomotion
Low Rank Global Geometric Consistency for Partial-Duplicate Image Search
FPGA Acceleration for Simultaneous Medical Image Reconstruction and Segmentation
Adaptive figure-ground classification
Overview of SHRC-Ginkgo speech synthesis system for Blizzard Challenge 2013
Deep Neural Networks for Syllable based Acoustic Modeling in Chinese Speech Recognition
Transform domain energy modeling of natural images for wireless SoftCast optimization
High Quality Image Reconstruction via Non-Local Collaborative Estimation for Wireless Image/Video So
Stereoscopic Video Quality Assessment Based on Stereo Just-Noticeable Difference Model
改进贝叶斯分类的智能短信分类方法
Large-margin Weakly Supervised Dimensionality Reduction
Reducing Blocking Artifacts in Compressed Images via Transform-Domain Non-local Coefficients Estimat
Transform domain energy modeling of natural images for wireless SoftCast optimization
High Quality Image Reconstruction via Non-Local Collaborative Estimation for Wireless Image/Video So
Stereoscopic Video Quality Assessment Based on Stereo Just-Noticeable Difference Model
High Quality Image Reconstruction via Non-Local Collaborative Estimation for Wireless Image/Video So
Stereoscopic Video Quality Assessment Based on Stereo Just-Noticeable Difference Model
Tensor LRR Based Subspace Clustering
Generalized Nonconvex Nonsmooth Low-Rank Minimization
An Improved Vertex-Clustering-Based Progressive Mesh Encoder
Compressing Material and Texture Attributes For Triangular Meshes
An Improved Vertex-Clustering-Based Progressive Mesh Encoder
Compressing Material and Texture Attributes For Triangular Meshes
改进贝叶斯分类的智能短信分类方法
Large-margin Weakly Supervised Dimensionality Reduction
Reducing Blocking Artifacts in Compressed Images via Transform-Domain Non-local Coefficients Estimat
Transform domain energy modeling of natural images for wireless SoftCast optimization
Layered Image/Video Softcast with Hybrid Digital-Analog Transmission for Robust Wireless Visual Comm
Gradient Based Image Transmission and Reconstruction using Non-Local Gradient Sparsity Regularizatio
HybridCast: A Wireless Image/Video SoftCast Scheme using Layered Representation and Hybrid Digital-A
Artifact Reduction of Compressed Video via Three-Dimensional Adaptive Estimation of Transform Coeffi
Tensor LRR Based Subspace Clustering
Generalized Nonconvex Nonsmooth Low-Rank Minimization
Efficient Generalized Fused Lasso with Application to the Diagnosis of Alzheimer’s Disease
Robust Subspace Segmentation with Block-diagonal Prior
Quality Assessment for Comparing Image Enhancement Algorithms
PUMS: the Architecture of the interactive System of Shape Design and Simulation
基于分布式虚拟现实环境的社会信息组织与分发系统
A Highly Effective Error Concealment Method for Whole Frame Loss
An Approach to Pose-based Action Recognition
Audio lossless coding/decoding method using basis pursuit algorithm
Discriminative apprenticeship learning with both preference and non-preference behavior
Indexing billions of images for sketch-based retrieval
A Novel Pair-wise Image Matching Strategy with Compact Descriptors
Labeling Unsegmented Sequence Data with DNN-HMM and Its Application for Speech Recognition
A New Method on Foot Rolling Trajectory Generation for Human-Like Bipedal Walking
Improved Disparity Vector Derivation in 3D-HEVC
Overview of IEEE 1857 Video Coding Standard
Parallelizing video transcoding with load balancing on cloud computing
基于移动终端的地形场景可视化数据调度算法
Robust Estimation of 3D Human Poses from Single Images
Fast Multi Reference Frame Motion Estimation For High Efficienty Video Coding
Wavelet Inpainting Driven Image Compression via Collaborative Sparsity Low Bitrates
<span class="title2">Multi-stage vector quantization towards low bit rate visual sea
Wavelet Inpainting Driven Image Compression via Collaborative Sparsity at Low Bit Rates
Intermediate View Synthesis based on Edge Detecting
Fast Multi Reference Frame Motion Estimation for High Efficiency Video Coding
LAPLACE DISTRIBUTION BASED CTU LEVEL RATE CONTROL FOR HEVC
<b>Decision tree based state tying for speech recognition using DNN derived embeddings</b&g
<b>Error Feedback Based Lexical Entity Extraction for Chinese Language Modeling</b>
<b>Head-Related Transfer Function Measurement</b>
Spatio-Temporal SSIM Index for Video Quality Assessment
Entropy of Primitive: A Top-Down Methodology for Evaluating the Perceptual Visual Information
Perceived elevation cued by images rotating in horizontal planes
The Effect of Part-of-speech on Mandarin Speech Recognition
Power-Distortion Optimization for Wireless Image/Video SoftCast by Transform Coefficients Energy Mod
Pre-trained Multi-view Word Embedding using Two-side Neural Network
An interactive system of stereoscopic video conversion
A Local Shape Descriptor for Mobile Linedrawing Retrieval.
Quadratic &rho;-domain based rate control algorithm for HEVC
Multi-speaker Prosodic Instance Selection for HMM-based Speech Synthesis
Non-local extension of total variation regularization for image restoration
Physical material editing with structure embedding for animated solid
Hierarchical-and-Adaptive Bit-allocation with Selective Background Prediction for High Efficiency Vi
Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable C
Large-margin Weakly Supervised Dimensionality Reduction
Reducing Blocking Artifacts in Compressed Images via Transform-Domain Non-local Coefficients Estimat
High order total variation method for interior tomography
Segmentation-aided Local Stereo Matching
Rectification of Optical Characters as Transform Invariant Low-rank Textures
Progressive Motion Vector Resolution for HEVC
Adaptive Partial Differential Equation Learning for Visual Saliency Detection
Tensor LRR Based Subspace Clustering
Generalized Nonconvex Nonsmooth Low-Rank Minimization
An Improved Vertex-Clustering-Based Progressive Mesh Encoder
Compressing Material and Texture Attributes For Triangular Meshes
改进贝叶斯分类的智能短信分类方法
Large-margin Weakly Supervised Dimensionality Reduction
Reducing Blocking Artifacts in Compressed Images via Transform-Domain Non-local Coefficients Estimat
Transform domain energy modeling of natural images for wireless SoftCast optimization
High Quality Image Reconstruction via Non-Local Collaborative Estimation for Wireless Image/Video So
Stereoscopic Video Quality Assessment Based on Stereo Just-Noticeable Difference Model
A Coding Unit Classification Based AVC-to-HEVC Transcoding with Background Modeling for Surveillance
Computable Relation Graph Based Calibration Pattern Extraction Algorithm on Multiple Calibration Boa
Tensor LRR Based Subspace Clustering
Generalized Nonconvex Nonsmooth Low-Rank Minimization
An Improved Vertex-Clustering-Based Progressive Mesh Encoder
Compressing Material and Texture Attributes For Triangular Meshes
改进贝叶斯分类的智能短信分类方法
L1-Norm Global Geometric Consistency for Partial-Duplicate Image Retrieval
Proximal Iteratively Reweighted Algorithm with Multiple Splitting for Noncovex Sparsity Optimization
Parallel Amvp Candidate List Construction For Hevc
Error-Driven Pronunciation Dictionary Construction for Mandarin Speech Recognition
Distribution and rendering of real-time scene based on the virtual reality system
Robust and Accurate Calibration Point Extraction with Multi-scale Chess-board Feature Detector
相关项目
岩爆孕育过程中的应力迁移及其微震活动性
期刊论文 53 会议论文 7
作物根系三维形态原位测量方法的研究
期刊论文 11 会议论文 4
电子晶体学图像处理
期刊论文 9
基于运动库检索和视频分析的三维人体运动重构
期刊论文 22 会议论文 18
气动触觉和力觉反馈手套的基础研究
期刊论文 9 会议论文 3
喷射成形中柱状近终形沉积坯几何特征检测及智能控制的研究
期刊论文 10 专利 3
基于对象识别与挖掘技术的视频水墨风格化算法研究
期刊论文 13 会议论文 1
虚拟耳显微手术关键技术的研究与实现
期刊论文 12 会议论文 7
沥青路面微观形貌对抗滑性能影响机理研究
期刊论文 9 会议论文 4 专利 1
高文的项目
　基于视觉特性的视频编码理论与方法研究
期刊论文 3
基于视觉特性的高效视频编码研究
期刊论文 22 会议论文 47 著作 1
大地电磁数据信噪比提高研究
2009 ACM国际多媒体技术大会
融合3D视频与移动终端的增强现实系统
期刊论文 7