基于Kinect的虚拟视点生成技术

传统的多视点生成方法是基于多相机阵列系统的关键技术。现提出了基于Kinect的多视点成像计算方法。首先对Kinect的深度图使用三边滤波器进行平滑,根据修复好的深度图配合彩色图,利用DIBR技术生成多个存在空缺信息的彩色视点;最后结合彩色图的纹理结构信息和深度图的背景信息对有丢失信息的彩色图进行修复。实验结果表明,文中提出的深度修复方法能够有效地修补Kinect的深度图,生成的虚拟视点图在3DTV上效果明显,立体视觉效果显著。     

基于Kinect的实时深度提取与多视绘制算法

提出了一种基于Kinect的实时深度提取算法和单纹理+深度的多视绘制方法。在采集端,使用Kinect提取场景纹理和深度,并针对Kinect输出深度图的空洞提出一种快速修复算法。在显示端,针对单纹理+深度的基于深度图像的绘制(DIBR,depth image based rendering)绘制产生的大空洞,采用一种基于背景估计和前景分割的绘制方法。实验结果表明,本文方法可实时提取质量良好的深度图,并有效修复了DIBR绘制过程中产生的大空洞,得到质量较好的多路虚拟视点图像。以所提出的深度获取和绘制算法为核心,实现了一种基于深度的立体视频系统,最终的虚拟视点交织立体显示的立体效果良好,进一步验证了本文算法的有效性。本文系统可用于实景的多视点立体视频录制与播放。     

基于超像素分割的深度图像修复算法

为了提高Kinect相机获取的深度图质量,提出了一种基于超像素分割的图像修复算法。 首先对深度图和彩色图分别 进行双边滤波和超像素分割;其次,结合深度图像和彩色图像相似性,记录彩色分割块的位 置,并对应于 深度图中;最后,在每个分割块对应深度区域中,根据丢失像素点在分割块中所占比例,划 分为无空洞区 域、小空洞区域、大空洞区域和全空洞区域4类。采用快速行进算法对小空洞区域进行 修复,利用中 值填补算法进行大空洞区域修复,对全空洞区域利用邻域区间对应彩色图像相似性进行填充 。4种类型中 的无空洞区域无需修复。实验结果表明,本文方法与FMM、Shen和Scheming的方法相比, 平均均方根误差(RMSE) 分别降低了2.958、0.822和0.078,修复 的主观质量也有所提高。     

基于区域融合的单视点图像深度信息提取

将2D转换为3D是目前3D多媒体成功应用的重要解决方法之一.而在2D至3D转换过程中,单视点图像中深度信息提取是最具挑战的任务.提出一种基于区域融合的单视点图像深度信息提取方法,利用区域融合对单视点图像进行区域融合,用先验假设的深度梯度图对区域进行深度分配,得到基于区域融合的深度图.实验结果表明通过所提方法得到的深度图...     

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。     

基于纹理平滑度的视点合成失真优化快速算法

针对3D-HEVC中深度图编码采用的视点合成失真优化方法的高复杂度问题,提出一种基于纹理平滑度的快速算法。首先结合帧内DC预测特性和统计学方法分析平坦纹理图中像素规律并设定基于纹理图平坦度的跳过准则;然后在深度图编码采用视点合成失真优化方法时提前分离出纹理图平坦区域所对应的深度图区域,并终止该区域像素基于虚拟视点合成的视点合成失真计算过程。实验结果证明该算法的有效性,能在保持编码质量的同时减少大量编码时间。     

面向编码和绘制的多视点图像深度估计

针对自由视点三维电视系统中深度估计不准确将给后续多视点深度编码和虚拟视点绘制带来困难的问题,提出一种面向编码和绘制的多视点图像深度估计算法。首先对初始深度进行一致性检查,并采用自适应匹配误差策略删除不可靠的匹配以减小初始深度的误匹配。然后根据融合准则将多幅参考深度图合成为一幅深度图以提高深度图的精度。最后,采用多边滤波...     

基于图像分割的深度视频校正算法

在基于深度图的虚拟视点绘制过程中,由于通过深 度估计软件获取的深度视频存在大量的失真,从而导致绘制的虚拟视点中存在纹理失真和缺 失现象。本文围绕深度视频失真类型,提出一种基于分割的深度 视频校正算法。利用彩色深度一致性信息分区域校正深度失真,以解决由于深度块失真造成 的虚拟视点纹理 缺失问题。首先,提取彩色视频运动和边缘区域,得到彩色视频边缘和运动区域掩模图;其 次,在边缘和运 动信息的辅助下,对彩色图像进行Mean Shift聚类,并将不同类别区域赋以不同的标签;最 后,分别统计不 同类别连通区域对应的深度直方图,利用其峰值校正深度视频中深度彩色非一致区域。实验 结果表明,本文提 出的基于分割块的深度视频校正算法优于部分基于像素的滤波算法,可以有效地校正深度视 频块失真,解决 虚拟视点边缘失真和纹理缺失问题,同时虚拟视点质量平均提高了0.20dB。     

易错网络中面向虚拟视点绘制的宏块模型

为了降低传输失真对自由视点视频虚拟视点质量 的影响,提出了一种同时适用于彩色图及深度 图的宏块区分模型。模型主要包括两部分:首先结合立体视频时空域的相关性,在 考虑错误扩散 的基础上,提出一个递归形式的宏块级传输失真模型;之后分别讨论彩色图失真和深度图失 真对虚拟视点 质量的影响,进而提出了一个低复杂度的基于绘制失真分析的重要性模型。实验结果表明, 与随机丢包相比, 本文算法能在不改变丢包率(PLR)的情况下大幅提高虚拟视 点的客观 质量,在PLR为20%时,平均峰值信噪 比(PSNR)最大能提 高15.65dB,且主观质量接近零传输失真情况。     

Generation of high-quality depth maps using hybrid camera system for 3-D video

In this paper, we present a hybrid camera system combining one time-of-flight depth camera and multiple video cameras to generate multi-view video sequences and their corresponding depth maps. In order to obtain the multi-view video-plus-depth data using the hybrid camera system, we capture multi-view videos using multiple video cameras and a single view depth video with the depth camera. After performing a three-dimensional (3-D) warping operation to obtain an initial depth map at each viewpoint, we refine the initial depth map using segment-based stereo matching. To reduce mismatched depth values along object boundaries, we detect the moving objects using color difference between frames and extract occlusion and disocclusion areas with the initial depth information. Finally, we recompute the depth value of each pixel in each segment using pairwise stereo matching with a proposed cost function. Experimental results show that the proposed hybrid camera system produces multi-view video sequences with more accurate depth maps, especially along the boundary of objects. In addition, it is suitable for generating more natural 3-D views for 3-D TV than previous works..     

Depth map misalignment correction and dilation for DIBR view synthesis

The quality of the synthesized views by Depth Image Based Rendering (DIBR) highly depends on the accuracy of the depth map, especially the alignment of object boundaries of texture image. In practice, the misalignment of sharp depth map edges is the major cause of the annoying artifacts at the disoccluded regions of the synthesized views. Conventional smooth filter approach blurs the depth map to reduce the disoccluded regions. The drawbacks are the degradation of 3D perception of the reconstructed 3D videos and the destruction of the texture in background regions. Conventional edge preserving filter utilizes the color image information in order to align the depth edges with color edges. Unfortunately, the characteristics of color edges and depth edges are very different which causes annoying boundaries artifacts in the synthesized virtual views. Recent solution of reliability-based approach uses reliable warping information from other views to fill the holes. However, it is not suitable for the view synthesis in video-plus-depth based DIBR applications. In this paper, a new depth map preprocessing approach is proposed. It utilizes Watershed color segmentation method to correct the depth map misalignment and then the depth map object boundaries are extended to cover the transitional edge regions of color image. This approach can handle the sharp depth map edges lying inside or outside the object boundaries in 2D sense. The quality of the disoccluded regions of the synthesized views can be significantly improved and unknown depth values can also be estimated. Experimental results show that the proposed method achieves superior performance for view synthesis by DIBR especially for generating large baseline virtual views.     

Adaptive depth truncation filter for MVC based compressed depth image

In multiview video plus depth (MVD) format, virtual views are generated from decoded texture videos with corresponding decoded depth images through depth image based rendering (DIBR). 3DV-ATM is a reference model for the H.264/AVC based multiview video coding (MVC) and aims at achieving high coding efficiency for 3D video in MVD format. Depth images are first downsampled then coded by 3DV-ATM. However, sharp object boundary characteristic of depth images does not well match with the transform coding based nature of H.264/AVC in 3DV-ATM. Depth boundaries are often blurred with ringing artifacts in the decoded depth images that result in noticeable artifacts in synthesized virtual views. This paper presents a low complexity adaptive depth truncation filter to recover the sharp object boundaries of the depth images using adaptive block repositioning and expansion for increasing the depth values refinement accuracy. This new approach is very efficient and can avoid false depth boundary refinement when block boundaries lie around the depth edge regions and ensure sufficient information within the processing block for depth layers classification. Experimental results demonstrate that the sharp depth edges can be recovered using the proposed filter and boundary artifacts in the synthesized views can be removed. The proposed method can provide improvement up to 3.25 dB in the depth map enhancement and bitrate reduction of 3.06% in the synthesized views.     

融合粗糙深度信息的低纹理物体偏振三维重建

对于表面光滑、低纹理的目标,传统基于多视几何重建的算法难以获得理想的结果,利用偏振信息来重建这类物体是便捷有效的方法之一.然而单纯利用偏振信息进行三维重建存在歧义性等问题,难以获得理想的结果.以粗糙深度图作为先验信息可解决歧义性问题.先对偏振相机与深度相机标定并配准图像,由粗糙深度图获得的法向量辅助纠正偏振方位角歧义,再利用纠正的法向量与粗糙深度图积分融合,从而获得较高精度的物体三维表面.     

Sum-of-gradient based fast intra coding in 3D-HEVC for depth map sequence (SOG-FDIC)

As the latest video coding standard for multi-view plus depth video, 3D-HEVC yields high coding efficiency but at the cost of heavy computational complexity. To reduce the computational complexity, a fast intra coding algorithm based on sum-of-gradient criterion for depth map coding in 3D-HEVC, named SOG-FDIC, is proposed in this paper. Based on the observation that DMM modes and smaller partitioning sizes are rarely used in flat region, sum of gradient is presented to determine whether the current block belongs to the flat region so as to skip unnecessary checking of DMMs and smaller partitioning sizes. Experimental results show that the proposed algorithm can save about 21.8% coding time while keeping almost the same coding efficiency and the reconstructed video quality of depth maps and synthesized views, compared with the original 3D-HEVC. Moreover, it has been verified that the proposed method outperforms the state-of-the-art methods.     

Adaptive Learning Based View Synthesis Prediction for Multi-View Video Coding

In the applications of Free View TV, pre-estimated depth information is available to synthesize the intermediate views as well as to assist multi-view video coding. Existing view synthesis prediction schemes generate virtual view picture only from interview pictures. However, there are many types of signal mismatches caused by depth errors, camera heterogeneity or illumination difference across views and these mismatches decrease the prediction capability of virtual view picture. In this paper, we propose an adaptive learning based view synthesis prediction algorithm to enhance the prediction capability of virtual view picture. This algorithm integrates least square prediction with backward warping to synthesize the virtual view picture, which not only utilizes the adjacent views information but also the temporal decoded information to adaptively learn the prediction coefficients. Experiments show that the proposed method reduces the bitrates by up to 18 % relative to the multi-view video coding standard, and about 11 % relative to the conventional view synthesis prediction method.     

A novel multi-view image coding scheme based on view-warping and 3D-DCT

Efficient compression of multi-view images and videos is an open and interesting research issue that has been attracting the attention of both academic and industrial world during the last years. The considerable amount of information produced by multi-camera acquisition systems requires effective coding algorithms in order to reduce the transmitted data while granting good visual quality in the reconstructed sequence. The classical approach of multi-view coding is based on an extension of the H.264/AVC standard, still based on motion prediction techniques. In this paper we present a novel approach that tries to fully exploit the redundancy between different views of the same scene considering both texture and geometry information. The proposed scheme replaces the motion prediction stage with a 3D warping procedure based on depth information. After the warping step, a joint 3D-DCT encoding of all the warped views is provided, taking advantage of the strong correlation among them. Finally, the transformed coefficients are conveniently quantized and entropy coded. Occluded regions are also taken into account with ad-hoc interpolation and coding strategies. Experimental results performed with a preliminary version of the proposed approach show that at low bitrates it outperforms the H.264 MVC coding scheme on both real and synthetic datasets. Performance at high bitrates are also satisfactory provided that accurate depth information is available.     

Segment-based view synthesis optimization scheme in 3D-HEVC

The 3D extension of high efficiency video coding (3D-HEVC) adopts a view synthesis optimization (VSO) technique to improve the quality of synthesized views for depth map coding. The exact synthesized view distortion change (SVDC) is calculated in VSO which in turn brings huge coding complexity to the 3D-HEVC encoder due to the real view synthesis process. This work presents a scheme aimed at reducing coding complexity of the SVDC calculating process in the 3D-HEVC encoder. It skips line segments of pixels with variable lengths based on information from both of the textures and depth maps in the SVDC calculation. Experimental results demonstrate that the proposed scheme can reduce the coding complexity without any significant loss in rate distortion performance for the synthesized views.     

多视点纹理加深度编码的联合码率控制方法

码率控制技术是多视点视频编码和传输中一个关键的问题。为了提高三维(3D)视频的整体显示质量,包括虚拟视点质量和编码视点质量,提出一种多视点纹理加深度编码的联合码率控制方法。该算法研究了纹理和深度的关系,采用基于模型方法确定最优的纹理和深度之间的码率比例。根据各个视点编码结果的统计规律,不同的视频序列采用不同的视点间比特分配比例。实验结果表明,与目前流行的多视点码率控制算法相比,该算法在计算复杂度基本保持不变的情况下,平均码率控制误差在0.6%以内,客观质量PSNR最高可提高0.65 dB。