Free Viewpoint Video Research Articles

An Artifact-Type Aware DIBR Method for View Synthesis

Depth-image-based rendering is a popular way to produce content for three-dimensional television and free viewpoint video, allowing the synthesis of numerous viewpoints using a single reference view and its depth map. Due to the synthesis process and nature of the input, artifacts and holes appear, and solving these problems becomes a challenge. In this letter, we propose solutions to remove those artifacts and apply different filling strategies depending on the nature of each hole. Cracks are identified and filled using very local neighborhood information. Regions classified as ghosts are projected to their correct place. The remaining holes are classified as disocclusions or out-of-field areas, and filled with an appropriate adaptation of a popular inpainting method. In both adaptations, patch matching explores the spatial locality concept, using dynamically adaptive patch sizes from the reference image. For disocclusions we propose a filling order using depth and background terms, and a searching process that considers only background patches. We show that our method outperforms several view synthesis methods in the quantitative evaluation, besides presenting consistent visual results for both large baselines and severely occluded scenes.

Combining Local and Global Measures for DIBR-Synthesized Image Quality Evaluation.

Depth-Image-Based-Rendering (DIBR) techniques are significant for three-dimensional (3D) video applications, e.g., 3D television and free viewpoint video (FVV). Unfortunately, the DIBR-synthesized image suffers from various distortions, which induce an annoying viewing experience for the entire FVV. Proposing a quality evaluator for DIBR-synthesized images is fundamental for the design of perceptual friendly FVV systems. Since the associated reference image is usually not accessible, full-reference (FR) methods cannot be directly applied for quality evaluation of the synthesized image. In addition, most traditional no-reference (NR) methods fail to effectively measure the specifically DIBR-related distortions. In this paper, we propose a novel NR quality evaluation method accounting for two categories of DIBR-related distortions, i.e., geometric distortions and sharpness. First, the disoccluded regions, as one of the most obvious geometric distortions, are captured by analyzing local similarity. Then, another typical geometric distortion (i.e., stretching) is detected and measured by calculating the similarity between it and its equal-size adjacent region. Second, considering the property of scale invariance, the global sharpness is measured as the distance between the distorted image and its downsampled version. Finally, the perceptual quality is estimated by linearly pooling the scores of two geometric distortions and sharpness together. Experimental results verify the superiority of the proposed method over the prevailing FR and NR metrics. More specifically, it is superior to all competing methods except APT in terms of effectiveness, but greatly outmatches APT in terms of implementation time.

Cross-View Multi-Lateral Filter for Compressed Multi-View Depth Video.

Multi-view depth is crucial for describing positioning information in 3D space for virtual reality, free viewpoint video, and other interaction- and remote-oriented applications. However, in cases of lossy compression for bandwidth limited remote applications, the quality of multi-view depth video suffers from quantization errors, leading to the generation of obvious artifacts in consequent virtual view rendering during interactions. Considerable efforts must be made to properly address these artifacts. In this paper, we propose a cross-view multi-lateral filtering scheme to improve the quality of compressed depth maps/videos within the framework of asymmetric multi-view video with depth compression. Through this scheme, a distorted depth map is enhanced via non-local candidates selected from current and neighboring viewpoints of different time-slots. Specifically, these candidates are clustered into a macro super pixel denoting the physical and semantic cross-relationships of the cross-view, spatial and temporal priors. The experimental results show that gains from static depth maps and dynamic depth videos can be obtained from PSNR and SSIM metrics, respectively. In subjective evaluations, even object contours are recovered from a compressed depth video. We also verify our method via several practical applications. For these verifications, artifacts on object contours are properly managed for the development of interactive video and discontinuous object surfaces are restored for 3D modeling. Our results suggest that the proposed filter outperforms state-of-the-art filters and is suitable for use in multi-view color plus depth-based interaction- and remote-oriented applications.

A Free-Viewpoint Television System for Horizontal Virtual Navigation

Free-viewpoint television (FTV) and virtual navigation appear to be hot research topics. In this paper, the authors study the practical development of free-viewpoint television systems that provide the functionality of virtual horizontal navigation around real scenes. The considerations are focused on practical systems that use purely optical depth estimation and might be employed in the next few years. The architectures of such systems are discussed in detail, including acquisition, preprocessing, depth estimation, compression, and presentation. In particular, the optimization of camera locations is discussed, and it is shown that video acquisition using camera pairs is advantageous for scenes with a substantial amount of occlusions. The theoretical considerations are supported by experimental results obtained for standard test multiview video sequences. Furthermore, the paper describes FTV video acquisition systems that consist of modules with pairs of cameras. The modules are sparsely located in arbitrary positions around a scene. Each camera module is equivalent to a video camera with a depth sensor. The hardware requirements, video processing algorithms, and experimental results are reported. In particular, for such systems, a compression technique is discussed that is more efficient than the new three-dimensional HEVC technology. The paper also describes new test video sequences that are obtained from the camera pairs sparsely distributed around scenes.

Hole Filling With Multiple Reference Views in DIBR View Synthesis

Depth-image-based rendering (DIBR) oriented view synthesis has been widely employed in the current depth-based 3D video systems by synthesizing a virtual view from an arbitrary viewpoint. However, holes may appear in the synthesized view due to disocclusion, thus significantly degrading the quality. Consequently, efforts have been made on developing effective and efficient hole filling algorithms. Current hole filling techniques generally extrapolate/interpolate the hole regions with the neighboring information based on an assumption that the texture pattern in the holes is similar to that of the neighboring background information. However, in many scenarios especially of complex texture, the assumption may not hold. In other words, hole filling techniques can only provide an estimation for a hole which may not be good enough or may even be erroneous considering a wide variety of complex scene of images. In this paper, we first examine the view interpolation with multiple reference views, demonstrating that the problem of emerging holes in a target virtual view can be greatly alleviated by making good use of other neighboring complementary views in addition to its two (commonly used) most neighboring primary views. The effects of using multiple views for view extrapolation in reducing holes are also investigated in this paper. In view of the 3D Video and ongoing free-viewpoint TV standardization, we propose a new view synthesis framework which employs multiple views to synthesize output virtual views. Furthermore, a scheme of selective warping of complementary views is developed by efficiently locating a small number of useful pixels in the complementary views for hole reduction, to avoid a full warping of additional complementary views thus lowering greatly the warping complexity.

Reliability-Based View Synthesis for Free Viewpoint Video

View synthesis is a crucial technique for free viewpoint video and multi-view video coding because of its capability to render an unlimited number of virtual viewpoints from adjacent captured texture images and corresponding depth maps. The accuracy of depth maps is very important to the rendering quality, since depth image–based rendering (DIBR) is the most widely used technology among synthesis algorithms. There are some issues due to the fact that stereo depth estimation is error-prone. In addition, filling occlusions is another challenge in producing desirable synthesized images. In this paper, we propose a reliability-based view synthesis framework. A depth refinement method is used to check the reliability of depth values and refine some of the unreliable pixels, and an adaptive background modeling algorithm is utilized to construct a background image aiming to fill the remaining empty regions after a proposed weighted blending process. Finally, the proposed approach is implemented and tested on test video sequences, and experimental results indicate objective and subjective improvements compared to previous view synthesis methods.

MonoPerfCap

We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows us to resolve the ambiguities of the monocular reconstruction problem based on a low-dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness, and scene complexity that can be handled.

Quality Assessment of DIBR-Synthesized Images by Measuring Local Geometric Distortions and Global Sharpness

Depth-image-based rendering (DIBR) is a fundamental technique in free viewpoint video, which is widely adopted to synthesize virtual viewpoints. The warping and rendering operations in DIBR generally introduce geometric distortions and sharpness change. The state-of-the-art quality indices are limited in dealing with such images since they are sensitive to geometric changes. In this paper, a new quality model for DIBR-synthesized view images is presented by measuring LOcal Geometric distortions in disoccluded regions and global Sharpness (LOGS). A disoccluded region detection method is first proposed using SIFT-flow-based warping. Then, the sizes and distortion strength of local disoccluded regions are combined to generate a score. Furthermore, a reblurring-based strategy is proposed to quantify the global sharpness. Finally, the overall quality score is calculated by pooling the scores of local disoccluded regions and global sharpness. Experiments on four public DIBR-synthesized image/video databases show the superiority of the proposed metric over the state-of-the-art quality models. The proposed method is further adopted for boosting the performances of existing quality metrics and benchmarking DIBR algorithms, both achieving very promising results.

Affordable content creation for free-viewpoint video and VR/AR applications

We present a scalable pipeline for Free-Viewpoint Video (FVV) content creation, considering also visualisation in Augmented Reality (AR) and Virtual Reality (VR). We support a range of scenarios where there may be a limited number of handheld consumer cameras, but also demonstrate how our method can be applied in professional multi-camera setups. Our novel pipeline extends many state-of-the-art techniques (such as structure-from-motion, shape-from-silhouette and multi-view stereo) and incorporates bio-mechanical constraints through 3D skeletal information as well as efficient camera pose estimation algorithms. We introduce multi-source shape-from-silhouette (MS-SfS) combined with fusion of different geometry data as crucial components for accurate reconstruction in sparse camera settings. Our approach is highly flexible and our results indicate suitability either for affordable content creation for VR/AR or for interactive FVV visualisation where a user can choose an arbitrary viewpoint or sweep between known views using view synthesis.

Virtual View Synthesis for Free Viewpoint Video and Multiview Video Compression using Gaussian Mixture Modelling.

High quality virtual views need to be synthesized from adjacent available views for free viewpoint video and multiview video coding (MVC) to provide users with a more realistic 3D viewing experience of a scene. View synthesis techniques suffer from poor rendering quality due to holes created by occlusion and rounding integer error through warping. To remove the holes in the virtual view, the existing techniques use spatial and temporal correlation in intra/inter-view images and depth maps. However, they still suffer quality degradation in the boundary region of foreground and background areas due to the low spatial correlation in texture images and low correspondence in inter-view depth maps. To overcome the above-mentioned limitations, we use a number of models in the Gaussian mixture modeling (GMM) to separate background and foreground pixels in our proposed technique. Here, the missing pixels introduced from the warping process are recovered by the adaptive weighted average of the pixel intensities from the corresponding GMM model(s) and warped image. The weights vary with time to accommodate the changes due to a dynamic background and the motions of the moving objects for view synthesis. We also introduce an adaptive strategy to reset the GMM modeling if the contributions of the pixel intensities drop significantly. Our experimental results indicate that the proposed approach provides 5.40-6.60-dB PSNR improvement compared with the relevant methods. To verify the effectiveness of the proposed view synthesis technique, we use it as an extra reference frame in the motion estimation for MVC. The experimental results confirm that the proposed view synthesis is able to improve PSNR by 3.15-5.13 dB compared with the conventional three reference frames.

Fast deformable model-based human performance capture and FVV using consumer-grade RGB-D sensors

In this paper, a novel end-to-end system for the fast reconstruction of human actor performances into 3D mesh sequences is proposed, using the input from a small set of consumer-grade RGB-Depth sensors. The proposed framework, by offline pre-reconstructing and employing a deformable actor’s 3D model to constrain the on-line reconstruction process, implicitly tracks the human motion. Handling non-rigid deformation of the 3D surface and applying appropriate texture mapping, it finally produces a dynamic sequence of temporally-coherent textured meshes, enabling realistic Free Viewpoint Video (FVV). Given the noisy input from a small set of low-cost sensors, the focus is on the fast (“quick-post”), robust and fully-automatic performance reconstruction. Apart from integrating existing ideas into a complete end-to-end system, which is itself a challenging task, several novel technical advances contribute to the speed, robustness and fidelity of the system, including a layered approach for model-based pose tracking, the definition and use of sophisticated energy functions, parallelizable on the GPU, as well as a new texture mapping scheme. The experimental results on a large number of challenging sequences, and comparisons with model-based and model-free approaches, demonstrate the efficiency of the proposed approach.

Efficient Multi-View 3D Video Multicast with Depth-Image-Based Rendering in LTE-Advanced Networks with Carrier Aggregation

With the recent emergence of naked-eye 3D mobile devices and various 3D-enabled laptops, service providers now afford the opportunity to provide mobile 3D video streaming in LTE-Advanced networks. Differing from traditional single-view 3D videos, multi-view 3D videos allow users to choose preferred view angles and thus are promising for new applications, such as free-viewpoint television (FTV). Nevertheless, enabling multi-view 3D video services may overwhelm the network resource when transmitting all views of every video. Fortunately, Depth-Image-Based Rendering (DIBR) allows each mobile client to synthesize the desired view from a nearby left view and right view, so that not all views of a video are necessarily transmitted. A new challenge with DIBR, however, is to carefully choose the transmitted views to limit the video distortion and minimize the bandwidth consumption. In this paper, therefore, we first formulate a new optimization problem, called View and MCS Selection (VMS) Problem, to minimize the bandwidth consumption for multi-view 3D video multicast in LTE networks. An algorithm, called View and MCS Aggregation (VMAG) is proposed to find the optimal solution to VMS. For Carrier Aggregation (CA) in LTE-Advanced networks, we formulate a new View, MCS and Carrier Selection (VMCS) Problem and prove that the problem is NP-Hard. We first design a dynamic programming algorithm, called the View Assignment with MCS and Carrier (VAMC) algorithm, to find the optimal solution for small instances. We then propose the View and MCS Aggregation with Carrier (VMAGC) algorithm based on VMAG to effectively find the near-optimal solution to VMCS. The simulation results show that bandwidth consumption can be effectively reduced by over 30 percent in VMS and VMCS.

The Role of Structure and Textural Information in Image Utility and Quality Assessment Tasks

Abstract The perceptual process of images is hierarchical. Human tends to first perceive global structural information such as shapes of objects and further focus on local regional details such as texture. Furthermore, it is widely believed that structure information plays the most important role in task of utility assessment and quality assessment, especially in new scenarios like free-viewpoint television, where the synthesized views contain geometric distortion around objects. We thus hypothesize that the degradation of structural information in an image is more annoying for human observers than the one of the textures in certain application scenarios. In order to confirm our hypothesis, a bilateral filtering based model (BF-M) is proposed referring to a recent subjective perceptual test. In the proposed model, bilateral filters are first utilized to separate structure from the texture information in images. Afterward, features that capture object properties and features that reflect texture information were extracted from the response and the residual of bilateral filtering separately. A contour, a shape related and a texture based estimator are then proposed with the corresponding extracted features. Finally, the model is designed by leveraging the three estimators according to target tasks. With the task-based model, one can then investigate the role of structure/texture information in certain task by checking the correspondence optimized weights assigned to the estimators. In this paper, the hypothesis and the performance of the BF-M is verified on CU-Nantes database as utility estimator and on SynTEX, IRCCyN/IVC-DIBR databases as quality estimator. Experimental results show that (1) structure information does play greater role in several tasks; (2) the performance of the BF-M is comparable to the state-of-the art utility metrics as well as the quality metrics designed for texture synthesis and views synthesis. It is thus validated that the proposed model can also be applied as a task-based parametric image metric.

Depth Assisted Adaptive Workload Balancing for Parallel View Synthesis

Depth image-based rendering has been adopted by MPEG as the recommended view synthesis technique for free viewpoint TV applications. In this paper, a workload balancing algorithm is proposed for parallel view synthesis on multicore platforms. First, view synthesis workload is defined as the function of the number of hole-pixels in the warped images. Then, a novel depth assisted prediction method is proposed to predict the number of hole-pixels in the current frame by exploiting the depth differences between the neighboring frames, which reflects the movement of objects in video content. Feeding the predicted workload to the proposed cost function, each input frame is partitioned adaptively to balance the synthesis workload among the cores. The proposed workload prediction method outperforms the existing approaches both in terms of frame average prediction error and standard deviation in prediction error. Applying the proposed workload balancing method, the parallel view synthesis system provides higher acceleration ratio and better synchronization performance among the cores compared with other parallel processing systems without sacrificing the subjective and objective quality. It is also robust to different platforms, which shows high potential in being applied to mobile oriented applications.

Lidar-Based Gait Analysis and Activity Recognition in a 4D Surveillance System

This paper presents new approaches for gait and activity analysis based on data streams of a rotating multibeam (RMB) Lidar sensor. The proposed algorithms are embedded into an integrated 4D vision and visualization system, which is able to analyze and interactively display real scenarios in natural outdoor environments with walking pedestrians. The main focus of the investigations is gait-based person reidentification during tracking and recognition of specific activity patterns, such as bending, waving, making phone calls, and checking the time looking at wristwatches. The descriptors for training and recognition are observed and extracted from realistic outdoor surveillance scenarios, where multiple pedestrians are walking in the field of interest following possibly intersecting trajectories; thus, the observations might often be affected by occlusions or background noise. Since there is no public database available for such scenarios, we created and published a new Lidar-based outdoor gait and activity data set on our website that contains point cloud sequences of 28 different persons extracted and aggregated from 35-min-long measurements. The presented results confirm that both efficient gait-based identification and activity recognition are achievable in the sparse point clouds of a single RMB Lidar sensor. After extracting the people trajectories, we synthesized a free-viewpoint video, in which moving avatar models follow the trajectories of the observed pedestrians in real time, ensuring that the leg movements of the animated avatars are synchronized with the real gait cycles observed in the Lidar stream.

FTV (Free-viewpoint Television) and its International Standardization

Free-viewpoint television (FTV) is the ultimate three-dimensional TV (3DTV) with an infinite number of views, and it ranks at the top of visual media. FTV enables users to view a 3D scene by freely changing the viewpoint, as we do naturally in the real world. FTV is a natural interface between humans and the environment. It is also an immersive medium that enables a realistic virtual reality (VR) experience and revolutionizes 3D viewing. FTV was realized by developing novel ray capture, processing, and display technologies and is based on ray-space representation. The international standardization of FTV has been conducted by the Moving Picture Experts Group (MPEG). The first phase of FTV is multiview video coding (MVC), and the second phase is 3D video (3DV). The third phase of FTV is MPEG-FTV, which targets revolutionized viewing of 3D scenes via super multiview, free navigation, and 360-degree 3D. After the success of Exploration Experiments and Call for Evidence, MPEG-FTV moved MPEG Immersive project (MPEG-I), and has been in charge of its video part as MPEG-I Visual. MPEG-I will create standards for immersive services based on the stages of immersion. In this paper, FTV and its international standardization are reviewed.

Reduced-reference quality assessment of DIBR-synthesized images based on multi-scale edge intensity similarity

Depth-image-based-rendering (DIBR) plays an important role in view synthesis for free-viewpoint videos. The warping process in DIBR causes geometric displacement, which distributes intensively around edges, and the subsequent rendering process results in the impairment of edges. Traditional 2D image quality metrics are limited in the quality evaluation of DIBR-synthesized images. In this paper, we present a reduced-reference quality metric for DIBR-synthesized images by only extracting several feature values, namely multi-scale Edge Intensity Similarity (EIS). The original and synthesized images are first downsampled to generate images with different resolutions. Then an edge detection process is conducted on each scale and the edge intensity is calculated. The similarity of the edge intensity between each downsampled original image and the corresponding synthesized image is computed. Finally, the average similarity is calculated as the quality score of the DIBR-synthesized image. Experiments conducted on IRCCyN/IVC DIBR image and video databases demonstrate that the proposed method overall outperforms traditional 2D and existing DIBR-targeted quality metrics.

Free-viewpoint Video Synthesis Technology for a New Video Viewing Experience

Free-viewpoint Video Synthesis Technology for a New Video Viewing Experience

Evaluating virtual image quality using the side-views information fusion and depth maps

Three Dimensional (3D) image quality assessment is a challenging problem as compared to 2D images due to their different nature of acquisition, representation, coding, and display. The additional dimension of depth in multiview video plus depth (MVD) format is exploited to obtain images at novel intermediate viewpoints using depth image based rendering (DIBR) techniques, enabling 3D television and free-viewpoint television (FTV) applications. Depth maps introduce various quality artifacts in the DIBR-synthesized (virtual) images. In this paper, we propose a novel methodology to evaluate the quality of synthesized views in absence of the corresponding original reference views. It computes the statistical characteristics of the side views from whom the virtual view is generated, and fuses this information to estimate the statistical characteristics of the cyclopean image which are compared to those of the synthesized image to evaluate its quality. In addition to texture images, the proposed algorithm also considers the depth maps in evaluating the quality of the synthesized images. The algorithm blends two quality metrics, one estimating the texture distortion in the synthesized texture image induced by compression, transmission, 3D warping, or other causes and the second one determining the distortion of the depth maps. The two metrics are combined to obtain an overall quality assessment of the synthesized image. The proposed Synthesized Image Quality Metric (SIQM) is tested on the challenging MCL-3D and SIAT-3D datasets. The evaluation results show that the proposed metric significantly improves over state-of-the-art 3D image quality assessment algorithms.

Virtual-view PSNR prediction based on a depth distortion tolerance model and support vector machine.

Quality prediction of virtual-views is important for free viewpoint video systems, and can be used as feedback to improve the performance of depth video coding and virtual-view rendering. In this paper, an efficient virtual-view peak signal to noise ratio (PSNR) prediction method is proposed. First, the effect of depth distortion on virtual-view quality is analyzed in detail, and a depth distortion tolerance (DDT) model that determines the DDT range is presented. Next, the DDT model is used to predict the virtual-view quality. Finally, a support vector machine (SVM) is utilized to train and obtain the virtual-view quality prediction model. Experimental results show that the Spearman's rank correlation coefficient and root mean square error between the actual PSNR and the predicted PSNR by DDT model are 0.8750 and 0.6137 on average, and by the SVM prediction model are 0.9109 and 0.5831. The computational complexity of the SVM method is lower than the DDT model and the state-of-the-art methods.