Search

This paper presents a new objective quality metric that was adapted to the complex characteristics of immersive video (IV) which is prone to errors caused by processing and compression of multiple input views and virtual view synthesis. The proposed metric, IV-PSNR, contains two techniques that allow for the evaluation of quality loss for typical immersive video distortions: corresponding pixel shift and global component difference. The performed experiments compared the proposal with 31 state-of-the-art quality metrics, showing their performance in the assessment of quality in immersive video coding and processing, and in other applications, using commonly used image quality assessment databases– TID2013 and CVIQ. As presented, IV-PSNR outperforms other metrics in immersive video applications and still can be efficiently used in the evaluation of different images and videos. Moreover, basing the metric on the calculation of PSNR allowed the computational complexity to remain low. Publicly available, efficient implementation of IV-PSNR software was provided by the authors of this paper and is used by ISO/IEC MPEG for evaluation and research on the upcoming MPEG Immersive video (MIV) coding standard. [ABSTRACT FROM AUTHOR]

In this paper, we find that the conventional convolution operation becomes the bottleneck for extremely efficient binary neural networks (BNNs). To address this issue, we open up a new direction by introducing a reshaped point-wise convolution (RPC) to replace the conventional one to build BNNs. Specifically, we conduct a point-wise convolution after rearranging the spatial information into depth, with which at least $2.25\times $ computation reduction can be achieved. Such an efficient RPC allows us to explore more powerful representational capacity of BNNs under a given computation complexity budget. Moreover, we propose to use a balanced activation (BA) to adjust the distribution of the scaled activations after binarization, which enables significant performance improvement of BNNs. After integrating RPC and BA, the proposed network, dubbed as RB-Net, strikes a good trade-off between accuracy and efficiency, achieving superior performance with lower computational cost against the state-of-the-art BNN methods. Specifically, our RB-Net achieves 66.8% Top-1 accuracy with ResNet-18 backbone on ImageNet, exceeding the state-of-the-art Real-to-Binary Net (65.4%) by 1.4% while achieving more than $3\times $ reduction (52M vs. 165M) in computational complexity. [ABSTRACT FROM AUTHOR]

Multi-view clustering has received widespread attention owing to its effectiveness by integrating multi-view data appropriately, but traditional algorithms have limited applicability to large-scale real-world data due to their high computational complexity and low robustness. Focusing on the aforementioned issues, we propose an efficient and robust multi-view clustering algorithm with anchor graph regularization (ERMC-AGR). In this work, a novel anchor graph regularization (ARG) is designed to improve the quality of the learned embedded anchor graph (EAG), and the obtained EAG is decomposed by nonnegative matrix factorization (NMF) under correntropy criterion to acquire clustering results directly. Different from the traditional graph regularization that needs to construct a large-scale Laplacian matrix pertaining to the all-sample graph, our lightweight AGR, constructed from the perspective of anchors, can reduce the computational complexity significantly while improving the EAG quality. Moreover, a factor matrix of NMF is constrained to be the cluster indicator matrix to omit additional k-means after optimization. Subsequently, correntropy is utilized to improve the effectiveness and robustness of ERMC-AGR owing to its promising performance to complex noises and outliers. Extensive experiments on real-world datasets and noisy datasets show that ERMC-ARG can improve the clustering efficiency and robustness while ensuring comparable or even better effectiveness. [ABSTRACT FROM AUTHOR]

In the three-dimensional video system, the depth image-based rendering is a key technique for generating synthesized views, which provides audiences with depth perception and interactivity. However, the inaccuracy of depth information leads to geometrical rendering position errors, and the compression distortion of texture and depth videos degrades the quality of the synthesized views. Although existing quality enhancement methods can eliminate the distortions in the synthesized views, their huge computational complexity hinders their applications in real-time multimedia systems. To this end, a residual distillation enhanced network (RDEN)-guided lightweight synthesized view quality enhancement (SVQE) method is proposed to minimize holes and compression distortions in the synthesized views while reducing the model complexity. First, a rethinking on the deep-learning-based SVQE methods is performed. Then, a feature distillation attention block is proposed to effectively reduce the distortions in the synthesized views and make the model fulfill more real-time tasks, which is a lightweight and flexible feature extraction block using an information distillation mechanism and a lightweight multi-scale spatial attention mechanism. Third, a residual feature fusion block is proposed to improve the enhancement performance by using the feature fusion mechanism, which efficiently improves the feature extraction capability without introducing any additional parameters. Experimental results prove that the proposed RDEN efficiently improves the SVQE performance while consuming few computational complexities compared with the state-of-the-art SVQE methods. [ABSTRACT FROM AUTHOR]

The depth video contains large smooth contents with sharp edges. Since the deep learning-based color video orientated intra prediction methods pay no attention to the characteristics of depth video, they are unsuitable for optimizing the coding efficiency of depth video. In this paper, a multiple resolution prediction method with deep up-sampling is proposed to promote the coding efficiency of depth video. To efficiently encode the depth blocks of different complexity, the depth block is selectively encoded at different resolutions, including $\times 1$ , $\times 1$ /2, and $\times 1$ /4 resolutions. If the block is encoded with a low-resolution (LR), the resolution of reconstructed LR depth block is recovered by an up-sampling network. To constrain the quality of both reconstructed high-resolution depth block and its synthesized view, a view synthesis distortion guidance mechanism is proposed for the up-sampling network. In addition, a distillation-based lightweight up-sampling network is proposed to reduce the computational complexity. Experimental results demonstrate that the proposed multiple resolution prediction method obtains an average of 10.84% BD-rate saving in comparison with 3D-HEVC. [ABSTRACT FROM AUTHOR]

Video compression is an important procedure for digital applications. A commonly used format for inputs to video coders is YUV420, which is a subsampled result from YUV444, that is transformed and demosaicked from a color filter array (CFA) format. The process of chroma subsampling is a crucial step for the reconstructed image quality. A state-of-the-art method utilizes the solution of a prior method to compute the starting point, and devises a search method to improve the results. However, the search method does not consider the optimality condition of the problem, and the overall computational complexity is high because of the execution of the prior method for the starting point. In the proposed work, the cost function of the optimization problem is analyzed and decomposed into 4 subchannels based on the CFA format. The optimal line of each subterm is studied in 3-dimensional space. The problem is then mathematically reduced to a 3-subchannel problem. Based on the combinations of the optimal lines, a triangle search area is formed and proved to contain the optimal solution. And because the derived triangle search area is small on average, the search for the optimal value can be considerably fast. Experimental results demonstrate that the proposed approach can produce reconstructed images with qualities that are exactly the same as those generated using the state-of-the-art method. Relative to the state-of-the-art method, the proposed approach can reduce the time complexity by 84.08%–84.91%, and reduce the number of search points by 40.24%–85.25%, for the image datasets Kodak and IMAX with different demosaicking methods. [ABSTRACT FROM AUTHOR]

The discrete cosine transform (DCT) is a relevant tool in signal processing applications, mainly known for its good decorrelation properties. Current image and video coding standards—such as JPEG and HEVC—adopt the DCT as a fundamental building block for compression. Recent works have introduced low-complexity approximations for the DCT, which become paramount in applications demanding real-time computation and low-power consumption. The design of DCT approximations involves a trade-off between computational complexity and performance. This paper introduces a new multiparametric transform class encompassing the round-off DCT (RDCT) and the modified RDCT (MRDCT), two relevant multiplierless 8-point approximate DCTs. The associated fast algorithm is provided. Four novel orthogonal low-complexity 8-point DCT approximations are obtained by solving a multicriteria optimization problem. The optimal 8-point transforms are scaled to lengths 16 and 32 while keeping the arithmetic complexity low. The proposed methods are assessed by proximity and coding measures with respect to the exact DCT. Image and video coding experiments and hardware realization are performed. The novel transforms perform close to or outperform the current state-of-the-art DCT approximations. [ABSTRACT FROM AUTHOR]

Edge-preserving image filtering is an essential task in computational photography and imaging. In this paper, we propose a simple yet effective global edge-preserving filter based on soft clustering, and we propose a novel soft clustering algorithm based on a restricted Gaussian mixture model. Given specified parameters, the soft clustering process is firstly performed on the image to derive the partition matrix, from which the affinity matrix is then constructed for filtering. The filtering output is calculated as the weighted average of the pixels in the local window, so the proposed filter could suppress the intensity shift artifacts that impede most global filters. Besides, the weights in the proposed filter are derived by clustering, which properly separates dissimilar pixels, so the proposed filter could handle the halo artifacts that haunt many local filters. Moreover, our filter provides flexible control over the amount of smoothing that is deficient in the deep learning-based filters. Besides the efficacy in smoothing, the proposed filter naturally has low computational complexity. Qualitative and quantitative results suggest that the proposed filter benefits various applications, including edge-preserving smoothing, image enhancing, flash/non-flash fusion, HDR tone mapping, and dehazing. [ABSTRACT FROM AUTHOR]

The rising demand for high quality display has ensued active research in high dynamic range (HDR) imaging, which has the potential to replace the standard dynamic range imaging. This is due to HDR’s features like accurate reproducibility of a scene with its entire spectrum of visible lighting and color depth. But this capability comes with expensive capture, display, storage and distribution resource requirements. Also, display of HDR images/video content on an ordinary display device with limited dynamic range requires some form of adaptation. Many adaptation algorithms, widely known as tone mapping (TM) operators, have been studied and proposed in the last few decades. In this article, we present a comprehensive survey of 60 TM algorithms that have been implemented on hardware for acceleration and real-time performance. In this state-of-the-art survey, we will discuss those TM algorithms which have been implemented on GPU, FPGA, and ASIC in terms of their hardware specifications and performance. Output image quality is an important metric for TM algorithms. From our literature survey we found that, various objective quality metrics have been used to demonstrate the quality of those algorithms hardware implementation. We have compiled those metrics used in this survey, and analyzed the relationship between hardware cost, image quality and computational efficiency. Currently, machine learning-based (ML) algorithms have become an important tool to solve many image processing tasks, and this article concludes with a discussion on the future research directions to realize ML-based TM operators on hardware. [ABSTRACT FROM AUTHOR]

Light Field (LF) video technology is a step towards offering a better immersive experience through on-demand refocusing and perspective viewing. However, the significant increase in captured data makes the need for efficient compression of paramount importance. In this paper, we proposed two prediction structures and coding orders that efficiently compress LF video content using the existing HEVC standard. This is achieved by utilizing horizontal and vertical correlation among the views for better inter-view prediction. To assess the performance of the schemes, ten publicly available and widely used LF video sequences were used. Our first method is highly suitable for applications demanding high compression efficiency. It outperforms the best pseudo-sequence-based compression technique to date by up to 17% in bitrate reduction while being scalable in the number of views. The second method is proficient for low computational and random-access complexity to any arbitrary view in the light field video. It offers 10% faster decoding and 20% lower random-access complexity compared to the best existing technique. [ABSTRACT FROM AUTHOR]

In video-based dynamic point cloud compression (V-PCC), 3D point clouds are projected into patches, and then the patches are padded into 2D images suitable for the video compression framework. However, the patch projection-based method produces a large number of empty pixels; the far and near components are projected to generate different 2D images (video frames), respectively. As a result, the generated video is with high resolutions and double frame rates, so the V-PCC has huge computational complexity. This paper proposes an occupancy map guided fast V-PCC method. Firstly, the relationship between the prediction coding and block complexity is studied based on a local linear image gradient model. Secondly, according to the V-PCC strategies of patch projection and block generation, we investigate the differences of rate-distortion characteristics between different types of blocks, and the temporal correlations between the far and near layers. Finally, by taking advantage of the fact that occupancy maps can explicitly indicate the block types, we propose an occupancy map guided fast coding method, in which coding is performed on the different types of blocks. Experiments have tested typical dynamic point clouds, and shown that the proposed method achieves an average 43.66% time-saving at the cost of only 0.27% and 0.16% Bjontegaard Delta (BD) rate increment under the geometry Point-to-Point (D1) error and attribute Luma Peak-Signal-Noise-Ratio (PSNR), respectively. [ABSTRACT FROM AUTHOR]

Traditional clustering algorithms are widely used for building bag-of-words (BOW) models to aggregate spatio-temporal feature points extracted from a video for human activity recognition problems. Their performances are restricted by the computational complexity which limits the number of feature points being used. In contrast, deep clustering yields good clustering performance without the limit of the number of feature points. Therefore, this work proposes a dual stacked autoencoders features embedded clustering (DSAFEC) and a BOW construction method based on the DSAFEC (B-DSAFEC) to reduce the computational complexity and to remove the selection restriction. The DSAFEC first transforms feature points extracted from a video to a learned feature space and then probabilities of cluster assignment of feature points are predicted to build BOWs for human activity recognition. A soft clustering is used by assigning each feature point to multiple clusters yielding the largest probabilities instead of only one in hard clustering. Experimental results on three benchmark human activity datasets show that the B-DSAFEC yields better performance compared to five reference methods which are developed based on either traditional clustering methods or deep clustering methods. [ABSTRACT FROM AUTHOR]

Flexible optimization on video coding computational complexity is imperative to adapt to diverse terminals in video streaming, especially with high definition videos and increasingly comprehensive encoders. Until now, few efforts have been contributed to the encoder of multiview videos, which complicates its encoding structure with duplex frame display. To address this issue, we propose a flexible complexity optimization framework in this paper. In the first place, the proposed algorithm flexibly reduces the encoder complexity at different external-defined complexity constraints; furthermore, it is also committed to compression efficiency optimization at different complexity levels. The framework is achieved by a hybrid approach: complexity allocation, which allocates the external-defined complexity constraint to all views, hierarchical layers and frames based on linear programming; and complexity regulation, which dynamically adjusts local candidate partitions to fulfil the targeted local complexity constraint, with a probability-driven Alternate Partition Cost (APC) minimization. The overall algorithm is implemented on the popular multiview encoder, Multiview High Efficiency Video Coding (MV-HEVC), with promising Rate-Distortion (RD) performances at different complexity constraints, which are also superior to two recent complexity optimization algorithms. [ABSTRACT FROM AUTHOR]

Recent learned image coding has emerged with superior efficiency to conventional methods. It, however, is criticized for its complexity-exhaustive deep neural network (DNN) architectures, especially on resource-constrained mobile platforms. Thus we devise a two-stage approach: first, a range pre-processing is applied to constrain the dynamic range of feature map activation by leveraging its sparsity nature with densely clustered distribution, then a layer-wise range-adaptive quantization for convolutional parameter (e.g., weight, bias), and simple yet efficient linear scaling and range-dependent normalization for activation are executed, leading to a fully fixed-point inference architecture. All arithmetic operations and associated data tensors are processed using low-bit-width fixed-point numbers, yielding significant reductions of the computational complexity, memory space, and the elimination of platform-dependent inconsistency induced by floating-point operations. We first exemplify such fixed-point inference in a DNN-based image decoder, showing the comparable coding efficiency with its native floating-point model, against the same anchor using the High-Efficiency Video Coding (HEVC)-based intra image coder. We also extend proposed approach to the super-resolution network for learned resolution scaling-based video streaming, and VGG network-based classification tasks, both of which present negligible performance loss. These evidence the generalization of our approach for efficient DNN processing of various tasks. All materials are made publicly accessible at http://njuvision.github.io/fixed-point/. [ABSTRACT FROM AUTHOR]

The classical chroma subsampling involves downsampling chrominance components (U and V) while maintaining the luminance component (Y). Recently, a study has attempted to change Y for the chroma-subsampling process, and improved results in the reconstructed image quality are obtained. However, computational complexity remains an issue because the study examines all the candidates in the determined range for minimal pixel distortion for the modified Y; the complexity can be high if the range is large. In this study, we reduced the candidate number to seven at most, which is mathematically optimized. Boundary points for in-the-range red, green, and blue (RGB) values are first decided, followed by the determination of the intervals that concatenate the entire curve (at most seven intervals). Each interval belongs to one of the seven sub-cases of different linear combinations of individual curves. The optimal solution (modified Y) for each sub-case is derived, which is in highly efficient form. Compared with the existing method, the proposed fast method ensures that the image quality is preserved, while the number of search candidates is reduced by 61.30%–69.19% on average, and the computational time of the process is reduced by 31.39%–58.97%, thereby demonstrating an efficient performance. [ABSTRACT FROM AUTHOR]

This paper presents an overview of the decoder-side motion vector refinement (DMVR) algorithm in the Versatile Video Coding (VVC) standard. The proposed DMVR algorithm aims to increase the prediction accuracy of the blocks coded in merge mode using the bilateral matching-based refinement method. Compared with previous decoder-side motion vector derivation approaches, the proposed method significantly increases the coding efficiency without signaling additional side information. Furthermore, the hardware implementation considerations of the DMVR design are particularly focused in this study. This paper details and analyzes the novel features of DMVR contributing to the increase in coding efficiency and the reduction in computational complexity and implementation difficulty. Experimental results based on the VVC test model version 8.0 demonstrate that average Bjøntegaard Delta rate savings of 0.80 % and 2.81 % are achieved for the “tool-off” and “tool-on” test configurations, respectively. Moreover, 4 % additional decoding time and negligible additional external memory bandwidth requirements of DMVR based on the common test conditions for VVC are reported. [ABSTRACT FROM AUTHOR]

Motion-compensated prediction adopts fractional-pixel interpolation to obtain the best motion vector. Traditional fixed interpolation filters cannot handle various content and structures well, and existing convolutional neural network based methods cannot fully exploit the distortion characteristics for fractional interpolation. Therefore, this paper proposes a distortion-aware multi-task learning framework (DA-MLF) to perform fractional interpolation. First, a multi-task training framework is proposed to provide the distortion characteristics as complementary information for improving the performance of subsequent interpolation. Then, a uniform interpolation sub-network is proposed to accomplish fractional interpolation, which utilizes the feature fusion module to fuse abundant local features, and the distortion awareness module to capture the multi-scale information of compression artifacts. Furthermore, DA-MLF is integrated into High Efficiency Video Coding (HEVC) test model, and multiple experiments are performed to evaluate the effectiveness of our method. On HEVC testing sequences, DA-MLF achieves 5.0%, 4.0% and 1.7% BD-rate reduction on average compared to the HEVC baseline, under low-delay P, low-delay B and random-access configurations, respectively. The experimental results validate that our framework not only achieves the best interpolation performance but also has the lowest computational complexity compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]