加权SIFT流深度迁移的单幅图像2D转3D

2D视频转3D视频是解决3D片源不足的主要手段,而单幅图像的深度估计是其中的关键步骤.提出基于加权SIFT流深度迁移和能量模型优化的单幅图像深度提取方法.首先利用图像的全局描述符从深度图数据库中检索出近邻图像;其次通过SIFT流建立输入图像和近邻图像之间像素级稠密对应关系;再次由SIFT流误差计算迁移权重,将近邻图像对应像素点的深度乘以权重后迁移到输入图像上;然后利用均值滤波对迁移后的近邻图像深度进行融合;最后建立深度图优化能量模型,在尽量接近迁移后近邻图像深度的前提下,平滑梯度较小区域的深度.实验结果表明,该方法降低了估计深度图的平均相对误差,增强了深度图的均匀性.     

基于FTV的改进深度估计算法

深度估计是任意视点电视(Free View Television,FTV)系统的关键技术。为提高深度边缘的深度估计准确度,并解决视频序列中不同帧间同一深度物体深度估计值不一致问题,提出一种在深度图的时间一致性保持算法,以前一帧的深度图与当前视图的运动信息为约束条件估计当前帧的深度,使得相邻帧的深度图在时间上保持一致。     

面向三维高效视频编码的深度图错误隐藏

基于多视点视频序列视点内、视点间存在的相关性,并结合视点间运动矢量共享技术,该文提出一种面向3维高效视频编码中深度序列传输丢包的错误隐藏算法。首先,根据3D高效视频编码(3D-HEVC)的分层B帧预测(HBP)结构和深度图纹理特征,将深度图丢失块分成运动块和静止块;然后,对于受损运动块,使用结合纹理结构的外边界匹配准则来选择相对最优的运动/视差矢量进行基于位移矢量补偿的错误掩盖,而对受损静止块采用参考帧直接拷贝进行快速错误隐藏;最后,使用参考帧拆分重组来获取新的运动/视差补偿块对修复质量较差的重建块进行质量提升。实验结果表明:相较于近年提出的对比算法,该文算法隐藏后的深度帧平均峰值信噪比(PSNR)能提升0.25～2.03 dB,结构相似度测量值(SSIM)能提升0.001～0.006,且修复区域的主观视觉质量与原始深度图更接近。     

结合预处理的深度视频帧内快速编码算法

多视点彩色加深度(MVD)视频是三维(3D)视频的 主流格式。在3D高效视频编码中,深度视频帧内编码 具有较高的编码复杂度;深度估计软件获取的深度视频由于不够准确会使深度图平坦 区域纹理增加, 从而进一步增加帧内编码复杂度。针对以上问题,本文提出了一种联合深度处理的深度视频 帧内低复杂度 编码算法。首先,在编码前对深度视频进行预处理,减少由于深度图不准确而出现的纹理信 息;其次,运 用反向传播神经网络(BPNN,backpropagation neural network)预测最大编码单元 (LCU,la rgest coding unit)的最大划分深度;最后联合深度视频的边缘信 息及对应的彩色LCU最大划分深度进行CU提前终止划分和快速模式选取。实验结果表明, 本文算法在保证 虚拟视点质量的前提下,BDBR下降0.33% ,深度视频编码时间平均节省50.63%。     

时域注意力特征对齐的视频压缩感知重构网络

现有视频压缩感知神经网络重构算法采用的光流对齐和可变形卷积对齐的运动补偿方式存在误差积聚、信息感知范围有限等问题,极大地限制了其有效性和实用性.为了在不引入额外参数的条件下自适应提取参考帧的全局信息,本文提出了利用注意力机制实现视频压缩感知重构过程中运动估计/运动补偿的创新思想,并设计了时域注意力特征对齐网络（Temporal-Attention Feature Alignment Network,TAFA-Net）进行实现.在此基础上,提出了联合深度重构网络（Joint Deep Reconstruction Network Based on TAFA-Net,JDR-TAFA-Net）,实现非关键帧的高性能重构.先利用本文所提的TAFA-Net获得参考帧到当前帧的对齐帧;然后,利用基于自编码器架构的融合网络充分提取已有帧信息,增强非关键帧的重构质量.仿真结果表明,与最优的迭代优化算法SSIM-InterF-GSR相比,所提算法重构帧的峰值信噪比（Peak Signal to Noise Ratio,PSNR）最高提升了4.74 dB;与最优的深度学习算法STM-Net相比,所提算法...     

新一代基于HEVC的3D视频编码技术

HEVC标准出台后,新一代基于HEVC的多视点加深度编码也将正式推出。基于HEVC的3D视频编码作为HEVC标准的扩展部分,主要面向立体电视和自由立体视频。从该编码方式的基本结构出发,较全面地介绍了视频编码方式、深度图编码方式和对深度图的编码控制三个方面的关键技术,包括视点间运动预测、深度图建模模式和视点合成优化等技术。     

对象引导的单幅散焦图像深度提取方法

2D图像转3D图像是解决3D影视内容缺乏的主要手段之一,而深度提取是其中的关键步骤.考虑到影视作品中存在大量散焦图像,提出单幅散焦图像深度估计的方法:首先通过高斯卷积将散焦图像转换成两幅模糊程度不同的图像;其次计算这两幅图像在边缘处的梯度幅值比例,进而根据阶跃信号与镜头的卷积模型得到边缘处的模糊度;再次将边缘处的模糊度转换成图像的稀疏深度并利用拉普拉斯矩阵插值得到稠密深度图;最后通过图像的视觉显著度提取前景对象,建立对象引导的深度图优化能量模型,使前景的深度趋于一致并平滑梯度较小区域的深度.该方法利用对象引导的深度优化,剔除了拉普拉斯矩阵插值引入深度图的纹理信息.模拟图像的峰值信噪比和真实图像的视觉对比均表明该算法比现有方法有较大改善.     

深度图时域一致性增强

在自由视点电视(FTV)系统的发送端,数据由多摄 像机采集的纹理图和其相应的深度信息组成;在接收端,虚拟视点由视点纹理序列和估计的 深度信息经过3D变换绘制。因此,获取高质量的深度信息是FTV系统的一个重 要部分。由于当前非交互方式深度估计方法是逐帧进行的,所得到的深度图序列往往缺乏时 域一致性。理 想情况下相邻帧静止区域的深度值应该相同,但是对这些区域深度值的估计结果往往不同, 这将严重影 响编码效率和绘制质量。由于深度图表征的是纹理图中相应场景离摄像机的距离,所以可以 通过对纹理图 的有效分析,判断出错误的深度值。通过对深度值可靠性和当前区域运动属性的判断,提出 一种基于 自适应时域加权的深度图一致性增强等。实验表明,本文算法能有效抑制静止区域深度值 不连续的错误,产生 更加稳定的深度图序列,使虚拟视点的时域绘制质量得到增强,同时编码效率得到提高。     

深度图时域一致性增强

在自由视点电视(FTV)系统的发送端,数据由多摄像机采集的纹理图和其相应的深度信息组成;在接收端,虚拟视点由视点纹理序列和估计的深度信息经过3D变换绘制。因此,获取高质量的深度信息是FTV系统的一个重要部分。由于当前非交互方式深度估计方法是逐帧进行的,所得到的深度图序列往往缺乏时域一致性。理想情况下相邻帧静止区域的深度值应该相同,但是对这些区域深度值的估计结果往往不同,这将严重影响编码效率和绘制质量。由于深度图表征的是纹理图中相应场景离摄像机的距离,所以可以通过对纹理图的有效分析,判断出错误的深度值。通过对深度值可靠性和当前区域运动属性的判断,提出一种基于自适应时域加权的深度图一致性增强等。实验表明,本文算法能有效抑制静止区域深度值不连续的错误,产生更加稳定的深度图序列,使虚拟视点的时域绘制质量得到增强,同时编码效率得到提高。     

基于模板匹配的视频对象分割

视频对象分割是MPEG-4标准关键技术.本文结合模板匹配和基于运动估值和补偿的对象跟踪方法,提出了一种可以从复杂场景中分割出MPEG-4视频对象的新方法.在使用运动估值和补偿得到分割掩膜后,以初始帧对象颜色为模板,在当前帧的轮廓边界区域通过模板匹配检测对象,使轮廓精确化.本文方法在一定范围内有效解决了遮挡问题,并能够以初始帧跟踪任意长序列中的对象.     

Semi-automatic 2D-to-3D video conversion based on background sprite generation

This paper presents a technique for semi-automatic 2D-to-3D stereo video conversion, which is known to provide user intervention in assigning foreground/background depths for key frames and then get depth maps for non-key frames via automatic depth propagation. Our algorithm treats foreground and background separately. For foregrounds, kernel pixels are identified and then used as the seeds for graph-cut segmentation for each non-key frame independently, resulting in results not limited by objects’ motion activity. For backgrounds, all video frames, after foregrounds being removed, are integrated into a common background sprite model (BSM) based on a relay-frame-based image registration algorithm. Users can then draw background depths for BSM in an integrated manner, thus reducing human efforts significantly. Experimental results show that our method is capable of retaining more faithful foreground depth boundaries (by 1.6–2.7 dB) and smoother background depths than prior works. This advantage is helpful for 3D display and 3D perception.     

Texture aided depth frame interpolation

Recent development of depth acquiring technique has accelerated the progress of 3D video in the market. Utilizing the acquired depth, arbitrary view frames can be generated based on depth image based rendering (DIBR) technique in free viewpoint video system. Different from texture video, depth sequence is mainly utilized for virtual view generation rather than viewing. Inspired by this, a depth frame interpolation scheme using texture information is proposed in this paper. The proposed scheme consists of a texture aided motion estimation (TAME) and texture aided motion compensation (TAMC) to fully explore the correlation between depth and the accompanying textures. The optimal motion vectors in TAME and the best interpolation weights in TAMC are respectively selected taking the geometric mapping relationship between depth and the accompanying texture frames into consideration. The proposed scheme is able to not only maintain the temporal consistency among interpolated depth sequence but also improve the quality of virtual frames generated by interpolated depth. Besides, it can be easily applied to arbitrary motion compensation based frame interpolation scheme. Experimental results demonstrate that the proposed depth frame interpolation scheme is able to improve the quality of virtual view texture frames in both subjective and objective criterions compared with existing schemes.     

Disparity field and depth map coding for multiview 3D image generation

In the present paper techniques are examined for the coding of the depth map and disparity fields for stereo or multiview image communication applications. It is assumed that both the left and right channels of the multiview image sequence are coded using block- or object-based methods. A dynamic programming algorithm is used to estimate a disparity field between each stereo image pair. Depth is then estimated and occlusions are optionally detected, based on the estimated disparity fields. Spatial interpolation techniques are examined based on the disparity/depth information and the detection of occluded regions using either stereoscopic or trinocular camera configurations. It is seen that the presence of a third camera at the transmitter site improves the estimation of disparities, the detection of occlusions and the accuracy of the resulting spatial interpolation at the receiver. Various disparity field and depth map coding techniques are then proposed and evaluated, with emphasis given to the quality of the resulting intermediate images at the receiver site. Block-based and wireframe modeling techniques are examined for the coding of isolated depth or disparity map information. Further, 2D and 3D motion compensation techniques are evaluated for the coding of sequences of depth or disparity maps. The motion fields needed may be available as a byproduct of block-based or object-based coding of the intensity images. Experimental results are given for the evaluation of the performance of the proposed coding and spatial interpolation methods.     

Reconstruction of lost depth data in multiview video-plus-depth communications using geometric transforms

This paper addresses depth data recovery in multiview video-plus-depth communications affected by transmission errors and/or packet loss. The novel aspects of the proposed method rely on the use of geometric transforms and warping vectors, capable of capturing complex motion and view-dependent deformations, which are not efficiently handled by traditional motion and/or disparity compensation methods. By exploiting the geometric nature of depth information, a region matching approach combined with depth contour reconstruction is devised to achieve accurate interpolation of arbitrary shapes within lost regions of depth maps. The simulation results show that, for different packet loss rates, up to 20%, the depth maps recovered by the proposed method produce virtual views with better quality than existing methods based on motion information and spatial interpolation. An average PSNR gain of 1.48 dB is obtained in virtual views synthesised from depth maps using the proposed method.     

用于多视视频加深度的错误隐藏算法

提出了一种针对多视视频加深度(MVD)的错误隐藏( EC)算法。算法充分利用MVD特有的深度 信息及当前丢失宏块周围正确解码的宏块信息,将丢失宏块分为3类不同属性的宏块。针对3类宏块的特 点,分别提出了基于候选运动矢量修正(CMVR)、基于深度的外边界匹配(DOBMA)以及自适应 权 值的EC(AWEC)等模式。实验表明,本文提出的算法在保证相同的视频主客观质量情况下, 能够快速有效地实现EC。     

A new method for inpainting of depth maps from time-of-flight sensors based on a modified closing by reconstruction algorithm

Time-of-Flight (ToF) sensors are popular devices that extract 3D information from a scene but result to be susceptible to noise and loss of data creating holes and gaps in the boundaries of the objects. The most common approaches to tackling this problem are supported by color images with good results, however, not all ToF devices produce color information. Mathematical morphology provides operators that can manage the problem of noise in single depth frames. In this paper, a new method for the filtering of single depth maps, when no color image is available, is presented, based on a modification to the morphological closing by reconstruction algorithm. The proposed method eliminates noise, emphasizing a high contour preservation, and it is compared, both qualitative and quantitatively, with other state-of-the-art filters. The proposed method represents an improvement to the closing by reconstruction algorithm that can be applied for filter depth maps of ToF devices.     

基于运动变化信息熵的视频序列时域亚采样技术

视频序列的时域亚采样对于低比特率信道上的视频传输和存储空间受限条件下的视频存储具有十分重要的意义。目前普遍采用的时域等间隔亚采样方法有时会造成视频序列中重要的运动变化信息的丢失。针对这一情况,本文提出了基于运动变化信息熵的视频序列时域亚采样技术,通过帧间运动场分析,利用运动场总体能量和运动补偿后的残差能量综合描述视频序列的运动变化信息,并根据信息熵最大化准则确定各个时域亚采样时刻点。大量的对比实验证明该方法明显优于时域等间隔亚采样方法,它较完整地反映了序列图像的运动变化过程,更有利于对视频内容的理解。     

基于模糊聚类的运动对象分割算法研究

为了从视频序列中分割出完整的、一致的运动视频对象,该文使用基于模糊聚类的分割算法获得组成对象边界的像素,从而提取对象。该算法首先使用了当前帧以及之前一些帧的图像信息计算其在小波域中不同子带的运动特征,并根据这些运动特征构造了低分辨率图像的运动特征矢量集;然后,使用模糊C-均值聚类算法分离出图像中发生显著变化的像素,以此代替帧间差图像,并利用传统的变化检测方法获得对象变化检测模型,从而提取对象;同时,使用相继两帧之间的平均绝对差值大小确定计算当前帧运动特征所需帧的数量,保证提取视频对象的精确性。实验结果证明该方法对于分割各种图像序列中的视频对象是有效的。