Search

Learning representations with a high Probability of Necessary and Sufficient Causes (PNS) has been shown to enhance deep learning models' ability. This task involves identifying causal features that are both sufficient (guaranteeing the outcome) and necessary (without which the outcome cannot occur). However, current research predominantly focuses on unimodal data, and extending PNS learning to multimodal settings presents significant challenges. The challenges arise as the conditions for PNS identifiability, Exogeneity and Monotonicity, need to be reconsidered in a multimodal context, where sufficient and necessary causal features are distributed across different modalities. To address this, we first propose conceptualizing multimodal representations as comprising modality-invariant and modality-specific components. We then analyze PNS identifiability for each component, while ensuring non-trivial PNS estimation. Finally, we formulate tractable optimization objectives that enable multimodal models to learn high-PNS representations, thereby enhancing their predictive performance. Experiments demonstrate the effectiveness of our method on both synthetic and real-world data.

This study investigates the acoustic features of sarcasm and disentangles the interplay between the propensity of an utterance being used sarcastically and the presence of prosodic cues signaling sarcasm. Using a dataset of sarcastic utterances compiled from television shows, we analyze the prosodic features within utterances and key phrases belonging to three distinct sarcasm categories (embedded, propositional, and illocutionary), which vary in the degree of semantic cues present, and compare them to neutral expressions. Results show that in phrases where the sarcastic meaning is salient from the semantics, the prosodic cues are less relevant than when the sarcastic meaning is not evident from the semantics, suggesting a trade-off between prosodic and semantic cues of sarcasm at the phrase level. These findings highlight a lessened reliance on prosodic modulation in semantically dense sarcastic expressions and a nuanced interaction that shapes the communication of sarcastic intent., Comment: accepted at Interspeech 2024

We study the dynamics of the quantum battery capacity for the Bell-diagonal states under Markovian channels on the first subsystem. We show that the capacity increases for special Bell-diagonal states under amplitude damping channel. The sudden death of the capacity occurs under depolarizing channel. We also investigate the capacity evolution of Bell-diagonal states under Markovian channels on the first subsystem $n$ times. It is shown that the capacity under depolarizing channel decreases initially, then increases for small $n$ and tend to zero for large $n$. We find that under bit flip channel and amplitude damping channel, the quantum battery capacity of special Bell-diagonal states tends to a constant for large $n$, namely, the frozen capacity occurs. The dynamics of the capacity of the Bell-diagonal states under two independent same type local Markovian channels is also studied., Comment: 12 pages, 6 figures

To fill the gap of traditional GS compression method, in this paper, we first propose a simple and effective GS data compression anchor called Graph-based GS Compression (GGSC). GGSC is inspired by graph signal processing theory and uses two branches to compress the primitive center and attributes. We split the whole GS sample via KDTree and clip the high-frequency components after the graph Fourier transform. Followed by quantization, G-PCC and adaptive arithmetic coding are used to compress the primitive center and attribute residual matrix to generate the bitrate file. GGSS is the first work to explore traditional GS compression, with advantages that can reveal the GS distortion characteristics corresponding to typical compression operation, such as high-frequency clipping and quantization. Second, based on GGSC, we create a GS Quality Assessment dataset (GSQA) with 120 samples. A subjective experiment is conducted in a laboratory environment to collect subjective scores after rendering GS into Processed Video Sequences (PVS). We analyze the characteristics of different GS distortions based on Mean Opinion Scores (MOS), demonstrating the sensitivity of different attributes distortion to visual quality. The GGSC code and the dataset, including GS samples, MOS, and PVS, are made publicly available at https://github.com/Qi-Yangsjtu/GGSC.

In recent years, Neural Radiance Fields (NeRF) have demonstrated significant advantages in representing and synthesizing 3D scenes. Explicit NeRF models facilitate the practical NeRF applications with faster rendering speed, and also attract considerable attention in NeRF compression due to its huge storage cost. To address the challenge of the NeRF compression study, in this paper, we construct a new dataset, called Explicit-NeRF-QA. We use 22 3D objects with diverse geometries, textures, and material complexities to train four typical explicit NeRF models across five parameter levels. Lossy compression is introduced during the model generation, pivoting the selection of key parameters such as hash table size for InstantNGP and voxel grid resolution for Plenoxels. By rendering NeRF samples to processed video sequences (PVS), a large scale subjective experiment with lab environment is conducted to collect subjective scores from 21 viewers. The diversity of content, accuracy of mean opinion scores (MOS), and characteristics of NeRF distortion are comprehensively presented, establishing the heterogeneity of the proposed dataset. The state-of-the-art objective metrics are tested in the new dataset. Best Person correlation, which is around 0.85, is collected from the full-reference objective metric. All tested no-reference metrics report very poor results with 0.4 to 0.6 correlations, demonstrating the need for further development of more robust no-reference metrics. The dataset, including NeRF samples, source 3D objects, multiview images for NeRF generation, PVSs, MOS, is made publicly available at the following location: https://github.com/YukeXing/Explicit-NeRF-QA., Comment: 5 pages, 4 figures, 2 tables, conference

We study theoretical properties of a broad class of regularized algorithms with vector-valued output. These spectral algorithms include kernel ridge regression, kernel principal component regression, various implementations of gradient descent and many more. Our contributions are twofold. First, we rigorously confirm the so-called saturation effect for ridge regression with vector-valued output by deriving a novel lower bound on learning rates; this bound is shown to be suboptimal when the smoothness of the regression function exceeds a certain level. Second, we present the upper bound for the finite sample risk general vector-valued spectral algorithms, applicable to both well-specified and misspecified scenarios (where the true regression function lies outside of the hypothesis space) which is minimax optimal in various regimes. All of our results explicitly allow the case of infinite-dimensional output variables, proving consistency of recent practical applications.

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. Herein, we propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. To ensure the compactness of Gaussian primitives, we devise a hybrid primitive structure that captures predictive relationships between each other. Then, we exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Moreover, we develop a rate-constrained optimization scheme to eliminate redundancies within such hybrid primitives, steering our CompGS towards an optimal trade-off between bitrate consumption and representation efficacy. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Our code will be released on GitHub for further research., Comment: Submitted to a conference

Low-light conditions and occluded scenarios impede object detection in real-world Internet of Things (IoT) applications like autonomous vehicles and security systems. While advanced machine learning models strive for accuracy, their computational demands clash with the limitations of resource-constrained devices, hampering real-time performance. In our current research, we tackle this challenge, by introducing ``YOLO Phantom", one of the smallest YOLO models ever conceived. YOLO Phantom utilizes the novel Phantom Convolution block, achieving comparable accuracy to the latest YOLOv8n model while simultaneously reducing both parameters and model size by 43\%, resulting in a significant 19\% reduction in Giga Floating-Point Operations (GFLOPs). YOLO Phantom leverages transfer learning on our multimodal RGB-infrared dataset to address low-light and occlusion issues, equipping it with robust vision under adverse conditions. Its real-world efficacy is demonstrated on an IoT platform with advanced low-light and RGB cameras, seamlessly connecting to an AWS-based notification endpoint for efficient real-time object detection. Benchmarks reveal a substantial boost of 17\% and 14\% in frames per second (FPS) for thermal and RGB detection, respectively, compared to the baseline YOLOv8n model. For community contribution, both the code and the multimodal dataset are available on GitHub., Comment: This paper has been accepted for publication at the IEEE International Conference on Image Processing (ICIP) 2024

Cells not only have self-motility by crawling but are also capable of other types of active motions like periodic contraction or pulsation. In this work, by using the Voronoi cell model, we show how this non-motility activity affects the structure, dynamic and density fluctuations of cellular monolayers. We find that random cell pulsation can fluidize solid epithelial tissues, resulting in hyperuniform fluids, while pulsation synchronization inhibits the fluidity and causes a reversed solidification. We prove this solidification is a BKT-type transition, characterized by strong density/dynamic heterogeneity arising from the birth of topological defects in the pulsating phase space. The magnitude and length scale of density heterogeneity diverge with the pulsating period, resulting in an opposite giant density fluctuation. We propose an unified fluctuating hydrodynamic theory to explain the two very different anomalous density fluctuations phenomena. Our findings can help understanding recent experimental observations in MDCK monolayers., Comment: 7pages, 3 figures

We present the first optimal rates for infinite-dimensional vector-valued ridge regression on a continuous scale of norms that interpolate between $L_2$ and the hypothesis space, which we consider as a vector-valued reproducing kernel Hilbert space. These rates allow to treat the misspecified case in which the true regression function is not contained in the hypothesis space. We combine standard assumptions on the capacity of the hypothesis space with a novel tensor product construction of vector-valued interpolation spaces in order to characterize the smoothness of the regression function. Our upper bound not only attains the same rate as real-valued kernel ridge regression, but also removes the assumption that the target regression function is bounded. For the lower bound, we reduce the problem to the scalar setting using a projection argument. We show that these rates are optimal in most cases and independent of the dimension of the output space. We illustrate our results for the special case of vector-valued Sobolev spaces., Comment: Published JMLR version. arXiv admin note: text overlap with arXiv:2208.01711

Since DARPA Grand Challenges (rural) in 2004/05 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications. Recently powered by large language models (LLMs), chat systems, such as chatGPT and PaLM, emerge and rapidly become a promising direction to achieve artificial general intelligence (AGI) in natural language processing (NLP). There comes a natural thinking that we could employ these abilities to reformulate autonomous driving. By combining LLM with foundation models, it is possible to utilize the human knowledge, commonsense and reasoning to rebuild autonomous driving systems from the current long-tailed AI dilemma. In this paper, we investigate the techniques of foundation models and LLMs applied for autonomous driving, categorized as simulation, world model, data annotation and planning or E2E solutions etc., Comment: 23 pages. A survey paper

Rain streaks bring complicated pixel intensity changes and additional gradients, greatly obstructing the extraction of image features from background. This causes serious performance degradation in feature-based applications. Thus, it is critical to remove rain streaks from a single rainy image to recover image features. Recently, many excellent image deraining methods have made remarkable progress. However, these human visual system-driven approaches mainly focus on improving image quality with pixel recovery as loss function, and neglect how to enhance image feature recovery ability. To address this issue, we propose a task-driven image deraining algorithm to strengthen image feature supply for subsequent feature-based applications. Due to the extensive use and strong practicability of Scale-Invariant Feature Transform (SIFT), we first propose two separate networks using distinct losses and modules to achieve two goals, respectively. One is difference of Gaussian (DoG) pyramid recovery network (DPRNet) for SIFT detection, and the other gradients of Gaussian images recovery network (GGIRNet) for SIFT description. Second, in the DPRNet we propose an alternative interest point loss that directly penalizes scale response extrema to recover the DoG pyramid. Third, we advance a gradient attention module in the GGIRNet to recover those gradients of Gaussian images. Finally, with the recovered DoG pyramid and gradients, we can regain SIFT key points. This divide-and-conquer scheme to set different objectives for SIFT detection and description leads to good robustness. Compared with state-of-the-art methods, experimental results demonstrate that our proposed algorithm achieves better performance in both the number of recovered SIFT key points and their accuracy., Comment: A direct DoG feature pyramid recovery from rainy pixels solution for SIFT detection, accepted by T-CSVT, 2023

Many recent theoretical works on meta-learning aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. Importantly, the main aim in theory works on the subject is to understand the extent to which convergence rates -- in learning a common representation -- may scale with the number $N$ of tasks (as well as the number of samples per task). First steps in this setting demonstrate this property when both the shared representation amongst tasks, and task-specific regression functions, are linear. This linear setting readily reveals the benefits of aggregating tasks, e.g., via averaging arguments. In practice, however, the representation is often highly nonlinear, introducing nontrivial biases in each task that cannot easily be averaged out as in the linear case. In the present work, we derive theoretical guarantees for meta-learning with nonlinear representations. In particular, assuming the shared nonlinearity maps to an infinite-dimensional RKHS, we show that additional biases can be mitigated with careful regularization that leverages the smoothness of task-specific regression functions

Originated from the work extraction in quantum systems coupled to a heat bath, quantum deficit is a kind of significant quantum correlations like quantum entanglement. It links quantum thermodynamics with quantum information. We analytically calculate the one-way deficit of the generalized $n$-qubit Werner state. We find that the one-way deficit increases as the mixing probability $p$ increases for any $n$. For fixed $p$, we observe that the one-way deficit increases as $n$ increases. For any $n$, the maximum of one-way deficit is attained at $p=1$. Furthermore, for large $n$ ($2^n \rightarrow \infty$), we prove that the curve of one-way deficit versus $p$ approaches to a straight line with slope $1$. We also calculate the Holevo quantity for the generalized $n$-qubit Werner state, and show that it is zero., Comment: 8 pages, 1 figure

3D dynamic point cloud (DPC) compression relies on mining its temporal context, which faces significant challenges due to DPC's sparsity and non-uniform structure. Existing methods are limited in capturing sufficient temporal dependencies. Therefore, this paper proposes a learning-based DPC compression framework via hierarchical block-matching-based inter-prediction module to compensate and compress the DPC geometry in latent space. Specifically, we propose a hierarchical motion estimation and motion compensation (Hie-ME/MC) framework for flexible inter-prediction, which dynamically selects the granularity of optical flow to encapsulate the motion information accurately. To improve the motion estimation efficiency of the proposed inter-prediction module, we further design a KNN-attention block matching (KABM) network that determines the impact of potential corresponding points based on the geometry and feature correlation. Finally, we compress the residual and the multi-scale optical flow with a fully-factorized deep entropy model. The experiment result on the MPEG-specified Owlii Dynamic Human Dynamic Point Cloud (Owlii) dataset shows that our framework outperforms the previous state-of-the-art methods and the MPEG standard V-PCC v18 in inter-frame low-delay mode., Comment: 9 pages for the main body, 3 pages for the supplemental after References

In this work, we first analyze the correlations among different nuclear matter parameters which are obtained by the 119 effective Skyrme interaction sets. The values of the correlation coefficients illustrate that the magnitude of the effective mass splitting is crucial for the tight constraints of the symmetry energy via HICs. Thus, the main object of this work is to investigate the impacts of the effective mass splitting on the heavy ion collisions observables. The $^{86}$Kr+$^{208}$Pb system at the beam energy ranging from 25A MeV to 200A MeV are simulated within the framework of the improved quantum molecular dynamics model (ImQMD-Sky) for this goal. Our calculations show that the slopes of the spectra of $\ln$[Y(n)/Y(p)] and $\ln$[Y(t)/Y($^3$He)], which are the logarithms of the neutron to proton yield ratios and triton to Helium-3 yield ratios, are directly related to the effective mass splitting and can be used to probe the effective mass splitting., Comment: 9 pages, 4 figures

Realizing both ultra-low breakdown voltage and ultra-high gain has been one of the major challenges in the development of high-performance avalanche photodetector. Here, we report that an ultra-high avalanche gain of 3*10^5 can be realized in the graphite/InSe Schottky photodetector at a breakdown voltage down to 5.5 V. Remarkably, the threshold breakdown voltage can be further reduced down to 1.8 V by raising the operating temperature, approaching the theoretical limit of 1.5E_g/e with E_g the band gap of semiconductor. We develop a two-dimensional impact ionization model and uncover that observation of high gain at low breakdown voltage arises from reduced dimensionality of electron-phonon (e-ph) scattering in the layered InSe flake. Our findings open up a promising avenue for developing novel weak-light detectors with low energy consumption and high sensitivity.

The non-uniform distribution and extremely sparse nature of the LiDAR point cloud (LPC) bring significant challenges to its high-efficient compression. This paper proposes a novel end-to-end, fully-factorized deep framework that encodes the original LPC into an octree structure and hierarchically decomposes the octree entropy model in layers. The proposed framework utilizes a hierarchical latent variable as side information to encapsulate the sibling and ancestor dependence, which provides sufficient context information for the modelling of point cloud distribution while enabling the parallel encoding and decoding of octree nodes in the same layer. Besides, we propose a residual coding framework for the compression of the latent variable, which explores the spatial correlation of each layer by progressive downsampling, and model the corresponding residual with a fully-factorized entropy model. Furthermore, we propose soft addition and subtraction for residual coding to improve network flexibility. The comprehensive experiment results on the LiDAR benchmark SemanticKITTI and MPEG-specified dataset Ford demonstrates that our proposed framework achieves state-of-the-art performance among all the previous LPC frameworks. Besides, our end-to-end, fully-factorized framework is proved by experiment to be high-parallelized and time-efficient and saves more than 99.8% of decoding time compared to previous state-of-the-art methods on LPC compression.

We address the consistency of a kernel ridge regression estimate of the conditional mean embedding (CME), which is an embedding of the conditional distribution of $Y$ given $X$ into a target reproducing kernel Hilbert space $\mathcal{H}_Y$. The CME allows us to take conditional expectations of target RKHS functions, and has been employed in nonparametric causal and Bayesian inference. We address the misspecified setting, where the target CME is in the space of Hilbert-Schmidt operators acting from an input interpolation space between $\mathcal{H}_X$ and $L_2$, to $\mathcal{H}_Y$. This space of operators is shown to be isomorphic to a newly defined vector-valued interpolation space. Using this isomorphism, we derive a novel and adaptive statistical learning rate for the empirical CME estimator under the misspecified setting. Our analysis reveals that our rates match the optimal $O(\log n / n)$ rates without assuming $\mathcal{H}_Y$ to be finite dimensional. We further establish a lower bound on the learning rate, which shows that the obtained upper bound is optimal., Comment: Typos & revised argument for the Gaussian kernel. Results unchanged

Efficient point cloud compression is essential for applications like virtual and mixed reality, autonomous driving, and cultural heritage. This paper proposes a deep learning-based inter-frame encoding scheme for dynamic point cloud geometry compression. We propose a lossy geometry compression scheme that predicts the latent representation of the current frame using the previous frame by employing a novel feature space inter-prediction network. The proposed network utilizes sparse convolutions with hierarchical multiscale 3D feature learning to encode the current frame using the previous frame. The proposed method introduces a novel predictor network for motion compensation in the feature domain to map the latent representation of the previous frame to the coordinates of the current frame to predict the current frame's feature embedding. The framework transmits the residual of the predicted features and the actual features by compressing them using a learned probabilistic factorized entropy model. At the receiver, the decoder hierarchically reconstructs the current frame by progressively rescaling the feature embedding. The proposed framework is compared to the state-of-the-art Video-based Point Cloud Compression (V-PCC) and Geometry-based Point Cloud Compression (G-PCC) schemes standardized by the Moving Picture Experts Group (MPEG). The proposed method achieves more than 88% BD-Rate (Bjontegaard Delta Rate) reduction against G-PCCv20 Octree, more than 56% BD-Rate savings against G-PCCv20 Trisoup, more than 62% BD-Rate reduction against V-PCC intra-frame encoding mode, and more than 52% BD-Rate savings against V-PCC P-frame-based inter-frame encoding mode using HEVC. These significant performance gains are cross-checked and verified in the MPEG working group.

With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize adversarially altered samples to fool the victim model to misclassify the adversarial sample. While such attacks claim to be or are expected to be stealthy, i.e., imperceptible to human eyes, such claims are rarely evaluated. In this paper, we present the first large-scale study on the stealthiness of adversarial samples used in the attacks against deep learning. We have implemented 20 representative adversarial ML attacks on six popular benchmarking datasets. We evaluate the stealthiness of the attack samples using two complementary approaches: (1) a numerical study that adopts 24 metrics for image similarity or quality assessment; and (2) a user study of 3 sets of questionnaires that has collected 20,000+ annotations from 1,000+ responses. Our results show that the majority of the existing attacks introduce nonnegligible perturbations that are not stealthy to human eyes. We further analyze the factors that contribute to attack stealthiness. We further examine the correlation between the numerical analysis and the user studies, and demonstrate that some image quality metrics may provide useful guidance in attack designs, while there is still a significant gap between assessed image quality and visual stealthiness of attacks., Comment: To appear in European Symposium on Research in Computer Security (ESORICS) 2022

The non-uniformly distributed nature of the 3D dynamic point cloud (DPC) brings significant challenges to its high-efficient inter-frame compression. This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space. In the proposed D-DPCC network, we design a {\it Multi-scale Motion Fusion} (MMF) module to accurately estimate the 3D optical flow between the feature representations of adjacent point cloud frames. Specifically, we utilize a 3D sparse convolution-based encoder to obtain the latent representation for motion estimation in the feature space and introduce the proposed MMF module for fused 3D motion embedding. Besides, for motion compensation, we propose a 3D {\it Adaptively Weighted Interpolation} (3DAWI) algorithm with a penalty coefficient to adaptively decrease the impact of distant neighbors. We compress the motion embedding and the residual with a lossy autoencoder-based network. To our knowledge, this paper is the first work proposing an end-to-end deep dynamic point cloud compression framework. The experimental result shows that the proposed D-DPCC framework achieves an average 76\% BD-Rate (Bjontegaard Delta Rate) gains against state-of-the-art Video-based Point Cloud Compression (V-PCC) v13 in inter mode.

Transport models are the main method to obtain physics information from low to relativistic-energy heavy-ion collisions. The Transport Model Evaluation Project (TMEP) has been pursued to test the robustness of transport model predictions in reaching consistent conclusions from the same type of physical model. Calculations under controlled conditions of physical input and set-up were performed with various participating codes. These included both calculations of nuclear matter in a box with periodic boundary conditions, and more realistic calculations of heavy-ion collisions. In this intermediate review, we summarize and discuss the present status of the project. We also provide condensed descriptions of the 26 participating codes, which contributed to some part of the project. These include the major codes in use today. We review the main results of the studies completed so far. They show, that in box calculations the differences between the codes can be well understood and a convergence of the results can be reached. These studies also highlight the systematic differences between the two families of transport codes, known as BUU and QMD type codes. However, when the codes were compared in full heavy-ion collisions using different physical models, as recently for pion production, they still yielded substantially different results. This calls for further comparisons of heavy-ion collisions with controlled models and of box comparisons of important ingredients, like momentum-dependent fields, which are currently underway. We often indicate improved strategies in performing transport simulations and thus provide guidance to code developers. Results of transport simulations of heavy-ion collisions from a given code will have more significance if the code can be validated against benchmark calculations such as the ones summarized in this review., Comment: 114 pages, 14 figures, 479 references, accepted for publication in Progress of Particle and Nuclear Phsics

The Holevo quantity and the $SU(2)$-invariant states have particular importance in quantum information processing. We calculate analytically the Holevo quantity for bipartite systems composed of spin-$j$ and spin-$\frac{1}{2}$ subsystems with $SU(2)$ symmetry, when the projective measurements are performed on the spin-$\frac{1}{2}$ subsystem. The relations among the Holevo quantity, the maximal values of the Holevo quantity and the states are analyzed in detail. In particular, we show that the Holevo quantity increases in the parameter region $FF_d$ when $j$ increases, where $F$ is function of temperature in thermal equilibrium and $F_d=j/(2j+1)$, and the maximum value of the Holevo quantity is attained at $F=1$ for all $j$. Moreover, when the dimension of system increases, the maximal value of the Holevo quantity decreases., Comment: 8 pages, 2 figures

Interfacial superconductivity has manifested itself in various types of heterostructures: band insulator-band insulator, band insulator-Mott insulator, and Mott insulator-metal. We report the observation of high-temperature superconductivity (HTS) in a complementary and long expected type of heterostructures, which consists of two Mott insulators, La2CuO4 (LCO) and PrBa2Cu3O7 (PBCO). By carefully controlling oxidization condition and selectively doping CuO2 planes with Fe atoms, which suppress superconductivity, we found that the superconductivity arises at the LCO side and is confined within no more than two unit cells (about 2.6 nm) near the interface. A phenomenon of overcome the Fe barrier will show up if excess oxygen is present during growth. Some possible mechanisms for the interfacial HTS have been discussed, and we attribute it to the redistribution of oxygen., Comment: 11 pages, 4 figures; and Supplementary Materials

This study develops a unified Point Cloud Geometry (PCG) compression method through the processing of multiscale sparse tensor-based voxelized PCG. We call this compression method SparsePCGC. The proposed SparsePCGC is a low complexity solution because it only performs the convolutions on sparsely-distributed Most-Probable Positively-Occupied Voxels (MP-POV). The multiscale representation also allows us to compress scale-wise MP-POVs by exploiting cross-scale and same-scale correlations extensively and flexibly. The overall compression efficiency highly depends on the accuracy of estimated occupancy probability for each MP-POV. Thus, we first design the Sparse Convolution-based Neural Network (SparseCNN) which stacks sparse convolutions and voxel sampling to best characterize and embed spatial correlations. We then develop the SparseCNN-based Occupancy Probability Approximation (SOPA) model to estimate the occupancy probability either in a single-stage manner only using the cross-scale correlation, or in a multi-stage manner by exploiting stage-wise correlation among same-scale neighbors. Besides, we also suggest the SparseCNN based Local Neighborhood Embedding (SLNE) to aggregate local variations as spatial priors in feature attribute to improve the SOPA. Our unified approach not only shows state-of-the-art performance in both lossless and lossy compression modes across a variety of datasets including the dense object PCGs (8iVFB, Owlii, MUVB) and sparse LiDAR PCGs (KITTI, Ford) when compared with standardized MPEG G-PCC and other prevalent learning-based schemes, but also has low complexity which is attractive to practical applications., Comment: 17 pages, 15 figures

Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high-fidelity speech data, and for unseen texts, the prosody of synthesized speech is relatively unnatural. To address these issues, we propose to combine a fine-tuned BERT-based front-end with a pre-trained FastSpeech2-based acoustic model to improve prosody modeling. The pre-trained BERT is fine-tuned on the polyphone disambiguation task, the joint Chinese word segmentation (CWS) and part-of-speech (POS) tagging task, and the prosody structure prediction (PSP) task in a multi-task learning framework. FastSpeech 2 is pre-trained on large-scale external data that are noisy but easier to obtain. Experimental results show that both the fine-tuned BERT model and the pre-trained FastSpeech 2 can improve prosody, especially for those structurally complex sentences.

It is proposed that ratios of the sixth order to the second order cumulant ($C_6/C_2$) of conserved quantities are sensitive to the chiral crossover transition. Recently, the negative $C_6/C_2$ was obtained both in theoretical Lattice QCD and experiments at $\sqrt{s_{NN}} = $ 200 GeV. In this study, we investigate the behavior of net-proton $C_6/C_2$ in statistical Binomial distribution (BD) at $\sqrt{s_{NN}} = $ 200 GeV in Au + Au collisions. With the BD parameters extracted from RHIC/STAR, it is found that $C_6/C_2$ can be negative. Furthermore, the obtained $C_6/C_2$ becomes smaller when applying the same magnitude of experimental statistics and calculation method to simulations. In 0-10\% centrality, there is a significant difference between the simulated result and theoretical expectation. Based on the extracted parameters and experimentally collected statistics, the baseline of net-proton $C_6/C_2$ in BD is presented., Comment: 8 pages, 6 figures

We study the theoretical properties of random Fourier features classification with Lipschitz continuous loss functions such as support vector machine and logistic regression. Utilizing the regularity condition, we show for the first time that random Fourier features classification can achieve $O(1/\sqrt{n})$ learning rate with only $\Omega(\sqrt{n} \log n)$ features, as opposed to $\Omega(n)$ features suggested by previous results. Our study covers the standard feature sampling method for which we reduce the number of features required, as well as a problem-dependent sampling method which further reduces the number of features while still keeping the optimal generalization property. Moreover, we prove that the random Fourier features classification can obtain a fast $O(1/n)$ learning rate for both sampling schemes under Massart's low noise assumption. Our results demonstrate the potential effectiveness of random Fourier features approximation in reducing the computational complexity (roughly from $O(n^3)$ in time and $O(n^2)$ in space to $O(n^2)$ and $O(n\sqrt{n})$ respectively) without having to trade-off the statistical prediction accuracy. In addition, the achieved trade-off in our analysis is at least the same as the optimal results in the literature under the worst case scenario and significantly improves the optimal results under benign regularity conditions.

TianQin is a planned space-based gravitational wave (GW) observatory consisting of three earth orbiting satellites with an orbital radius of about $10^5~{\rm km}$. The satellites will form a equilateral triangle constellation the plane of which is nearly perpendicular to the ecliptic plane. TianQin aims to detect GWs between $10^{-4}~{\rm Hz}$ and $1~{\rm Hz}$ that can be generated by a wide variety of important astrophysical and cosmological sources, including the inspiral of Galactic ultra-compact binaries, the inspiral of stellar-mass black hole binaries, extreme mass ratio inspirals, the merger of massive black hole binaries, and possibly the energetic processes in the very early universe or exotic sources such as cosmic strings. In order to start science operations around 2035, a roadmap called the 0123 plan is being used to bring the key technologies of TianQin to maturity, supported by the construction of a series of research facilities on the ground. Two major projects of the 0123 plan are being carried out. In this process, the team has created a new generation $17~{\rm cm}$ single-body hollow corner-cube retro-reflector which has been launched with the QueQiao satellite on 21 May 2018; a new laser ranging station equipped with a $1.2~{\rm m}$ telescope has been constructed and the station has successfully ranged to all the five retro-reflectors on the Moon; and the TianQin-1 experimental satellite has been launched on 20 December 2019 and the first round result shows that the satellite has exceeded all of its mission requirements., Comment: 16 pages, 1 figure, invited article to a special section in PTEP

The TianQin-1 satellite (TQ-1), which is the first technology demonstration satellite for the TianQin project, was launched on 20 December 2019. The first round of experiment had been carried out from 21 December 2019 until 1 April 2020. The residual acceleration of the satellite is found to be about $1\times10^{-10}~{\rm m}/{\rm s}^{2}/{\rm Hz}^{1/2}$ at $0.1~{\rm Hz}\,$ and about $5\times10^{-11}~{\rm m}/{\rm s}^{2}/{\rm Hz}^{1/2}$ at $0.05~{\rm Hz}\,$, measured by an inertial sensor with a sensitivity of $5\times10^{-12}~{\rm m}/{\rm s}^{2}/{\rm Hz}^{1/2}$ at $0.1~{\rm Hz}\,$. The micro-Newton thrusters has demonstrated a thrust resolution of $0.1~\mu{\rm N}$ and a thrust noise of $0.3~\mu{\rm N}/{\rm Hz}^{1/2}$ at $0.1~{\rm Hz}$. The residual noise of the satellite with drag-free control is $3\times10^{-9}~{\rm m}/{\rm s}^{2}/{\rm Hz}^{1/2}$ at $0.1~{\rm Hz}\,$. The noise level of the optical readout system is about $30~{\rm pm}/{\rm Hz}^{1/2}$ at $0.1~{\rm Hz}\,$. The temperature stability at temperature monitoring position is controlled to be about $\pm3~{\rm mK}$ per orbit, and the mismatch between the center-of-mass of the satellite and that of the test mass is measured with a precision of better than $0.1~{\rm mm}$., Comment: 17 pages, 11 figures

In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination. The proposed quality assessment framework is grounded on the prior models of natural image statistical behaviors and rooted in the view that the perceptually meaningful features could be well exploited to characterize the visual quality. Herein, the PR features from the distorted images are learned by a mutual learning scheme with the pristine reference as the supervision, and the discriminative characteristics of PR features are further ensured with the triplet constraints. Given a distorted image for quality inference, the feature level disentanglement is performed with an invertible neural layer for final quality prediction, leading to the PR and the corresponding distortion features for comparison. The effectiveness of our proposed method is demonstrated on four popular IQA databases, and superior performance on cross-database evaluation also reveals the high generalization capability of our method. The implementation of our method is publicly available on https://github.com/Baoliang93/FPR.

Photo-realistic point cloud capture and transmission are the fundamental enablers for immersive visual communication. The coding process of dynamic point clouds, especially video-based point cloud compression (V-PCC) developed by the MPEG standardization group, is now delivering state-of-the-art performance in compression efficiency. V-PCC is based on the projection of the point cloud patches to 2D planes and encoding the sequence as 2D texture and geometry patch sequences. However, the resulting quantization errors from coding can introduce compression artifacts, which can be very unpleasant for the quality of experience (QoE). In this work, we developed a novel out-of-the-loop point cloud geometry artifact removal solution that can significantly improve reconstruction quality without additional bandwidth cost. Our novel framework consists of a point cloud sampling scheme, an artifact removal network, and an aggregation scheme. The point cloud sampling scheme employs a cube-based neighborhood patch extraction to divide the point cloud into patches. The geometry artifact removal network then processes these patches to obtain artifact-removed patches. The artifact-removed patches are then merged together using an aggregation scheme to obtain the final artifact-removed point cloud. We employ 3D deep convolutional feature learning for geometry artifact removal that jointly recovers both the quantization direction and the quantization noise level by exploiting projection and quantization prior. The simulation results demonstrate that the proposed method is highly effective and can considerably improve the quality of the reconstructed point cloud., Comment: Accepted in IEEE Transactions on Multimedia, 2021

Within the transport model evaluation project (TMEP) of simulations for heavy-ion collisions, the mean-field response is examined here. Specifically, zero-sound propagation is considered for neutron-proton symmetric matter enclosed in a periodic box, at zero temperature and around normal density. The results of several transport codes belonging to two families (BUU-like and QMD-like) are compared among each other and to exact calculations. For BUU-like codes, employing the test particle method, the results depend on the combination of the number of test particles and the spread of the profile functions that weight integration over space. These parameters can be properly adapted to give a good reproduction of the analytical zero-sound features. QMD-like codes, using molecular dynamics methods, are characterized by large damping effects, attributable to the fluctuations inherent in their phase-space representation. Moreover, for a given nuclear effective interaction, they generally lead to slower density oscillations, as compared to BUU-like codes. The latter problem is mitigated in the more recent lattice formulation of some of the QMD codes. The significance of these results for the description of real heavy-ion collisions is discussed.

In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem. The core of our technique is a layer selection strategy, named ReLU-Based Feature Fusion (RBFF), that extracts feature maps from a pretrained CNN-based single-object image classification model, namely MobileNetV2, and constructs a model for the aerial scene classification task. RBFF stacks features extracted from the batch normalization layer of a few selected blocks of MobileNetV2, where the candidate blocks are selected based on the characteristics of the ReLU activation layers present in those blocks. The feature vector is then compressed into a low-dimensional feature space using dimension reduction algorithms on which we train a low-cost SVM classifier for the classification of the aerial images. We validate our choice of selected features based on the significance of the extracted features with respect to our classification pipeline. RBFF remarkably does not involve any training of the base CNN model except for a few parameters for the classifier, which makes the technique very cost-effective for practical deployments. The constructed model despite being lightweight outperforms several recently proposed models in terms of accuracy for a number of aerial scene datasets., Comment: To be presented in IEEE ICIP'21

Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory. We examine how these benign overfitting phenomena occur in a two-layer neural network setting where sample covariates are corrupted with noise. We address the high dimensional regime, where the data dimension $d$ grows with the number $n$ of data points. Our analysis combines an upper bound on the bias with matching upper and lower bounds on the variance of the interpolator (an estimator that interpolates the data). These results indicate that the excess learning risk of the interpolator decays under mild conditions. We further show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate, which to our knowledge is the first generalization result for such networks. Finally, our theory predicts that the excess learning risk starts to increase once the number of parameters $s$ grows beyond $O(n^2)$, matching recent empirical findings.

Quark-antiquark pair (or dijet) production at the electron-ion collider (EIC) has been argued to be one of most important processes that allowing to access the Weizs\"acker-Williams (WW) gluon distributions at small $x$ limit. Within the framework of Color Glass Condensate (CGC) effective field theory (EFT), we calculated the dijet cross sections and the azimuthal correlations by including the Sudakov resummations, numerical results shown that the back-to-back correlations are significantly suppressed when the Sudakov resummations are taken into account. In addition, by using the solutions of running-coupling Balitsky-Kovchegov (rcBK) equation, the unpolarized and linearly polarized WW gluon distributions both in coordinate and momentum space are presented., Comment: A few typos corrected, some references added

Recent years have witnessed the growth of point cloud based applications because of its realistic and fine-grained representation of 3D objects and scenes. However, it is a challenging problem to compress sparse, unstructured, and high-precision 3D points for efficient communication. In this paper, leveraging the sparsity nature of point cloud, we propose a multiscale end-to-end learning framework which hierarchically reconstructs the 3D Point Cloud Geometry (PCG) via progressive re-sampling. The framework is developed on top of a sparse convolution based autoencoder for point cloud compression and reconstruction. For the input PCG which has only the binary occupancy attribute, our framework translates it to a downscaled point cloud at the bottleneck layer which possesses both geometry and associated feature attributes. Then, the geometric occupancy is losslessly compressed using an octree codec and the feature attributes are lossy compressed using a learned probabilistic context model.Compared to state-of-the-art Video-based Point Cloud Compression (V-PCC) and Geometry-based PCC (G-PCC) schemes standardized by the Moving Picture Experts Group (MPEG), our method achieves more than 40% and 70% BD-Rate (Bjontegaard Delta Rate) reduction, respectively. Its encoding runtime is comparable to that of G-PCC, which is only 1.5% of V-PCC.

Gait recognition has proven to be effective for long-distance human recognition. But view variance of gait features would change human appearance greatly and reduce its performance. Most existing gait datasets usually collect data with a dozen different angles, or even more few. Limited view angles would prevent learning better view invariant feature. It can further improve robustness of gait recognition if we collect data with various angles at 1 degree interval. But it is time consuming and labor consuming to collect this kind of dataset. In this paper, we, therefore, introduce a Dense-View GEIs Set (DV-GEIs) to deal with the challenge of limited view angles. This set can cover the whole view space, view angle from 0 degree to 180 degree with 1 degree interval. In addition, Dense-View GAN (DV-GAN) is proposed to synthesize this dense view set. DV-GAN consists of Generator, Discriminator and Monitor, where Monitor is designed to preserve human identification and view information. The proposed method is evaluated on the CASIA-B and OU-ISIR dataset. The experimental results show that DV-GEIs synthesized by DV-GAN is an effective way to learn better view invariant feature. We believe the idea of dense view generated samples will further improve the development of gait recognition., Comment: Accepted for presentation at IJCB'2020

Generally, adaptive bitrates for variable Internet bandwidths can be obtained through multi-pass coding. Referenceless prediction-based methods show practical benefits compared with multi-pass coding to avoid excessive computational resource consumption, especially in low-latency circumstances. However, most of them fail to predict precisely due to the complex inner structure of modern codecs. Therefore, to improve the fidelity of prediction, we propose a referenceless prediction-based R-QP modeling (PmR-QP) method to estimate bitrate by leveraging a deep learning algorithm with only one-pass coding. It refines the global rate-control paradigm in modern codecs on flexibility and applicability with few adjustments as possible. By exploring the potentials of bitstream and pixel features from the prerequisite of one-pass coding, it can reach the expectation of bitrate estimation in terms of precision. To be more specific, we first describe the R-QP relationship curve as a robust quadratic R-QP modeling function derived from the Cauchy-based distribution. Second, we simplify the modeling function by fastening one operational point of the relationship curve received from the coding process. Third, we learn the model parameters from bitstream and pixel features, named them hybrid referenceless features, comprising texture information, hierarchical coding structure, and selected modes in intra-prediction. Extensive experiments demonstrate the proposed method significantly decreases the proportion of samples' bitrate estimation error within 10% by 24.60% on average over the state-of-the-art.

Modern machine learning often operates in the regime where the number of parameters is much higher than the number of data points, with zero training loss and yet good generalization, thereby contradicting the classical bias-variance trade-off. This \textit{benign overfitting} phenomenon has recently been characterized using so called \textit{double descent} curves where the risk undergoes another descent (in addition to the classical U-shaped learning curve when the number of parameters is small) as we increase the number of parameters beyond a certain threshold. In this paper, we examine the conditions under which \textit{Benign Overfitting} occurs in the random feature (RF) models, i.e. in a two-layer neural network with fixed first layer weights. We adopt a new view of random feature and show that \textit{benign overfitting} arises due to the noise which resides in such features (the noise may already be present in the data and propagate to the features or it may be added by the user to the features directly) and plays an important implicit regularization role in the phenomenon.

With the advantages of both classical and quantum secret sharing, many practical hybrid quantum secret sharing have been proposed. In this paper, we propose a hybrid quantum secret sharing scheme based on mutually unbiased bases and monotone span program. First, the dealer sends the shares in the linear secret sharing to the participants in the authorization set via a secure channel. Then, the dealer and participants perform unitary transformation on a d-dimensional quantum state sequentially, and the dealer publishes the measurement result confidentially to the participants in the authorization set to recover the secret. The verifiability of the scheme is guaranteed by the Hash function. Next, the correctness and security of the scheme are proved and our scheme is secure against the general eavesdropper attacks. Finally, a specific example is employed to further clarify the exibility of the scheme and the detailed comparison of similar quantum secret sharing schemes also shows the superiority of our proposed scheme., Comment: 13 pages, 2 figures

We propose the GraphSIM -- an objective metric to accurately predict the subjective quality of point cloud with superimposed geometry and color impairments. Motivated by the facts that human vision system is more sensitive to the high spatial-frequency components (e.g., contours, edges), and weighs more to the local structural variations rather individual point intensity, we first extract geometric keypoints by resampling the reference point cloud geometry information to form the object skeleton; we then construct local graphs centered at these keypoints for both reference and distorted point clouds, followed by collectively aggregating color gradient moments (e.g., zeroth, first, and second) that are derived between all other points and centered keypoint in the same local graph for significant feature similarity (a.k.a., local significance) measurement; Final similarity index is obtained by pooling the local graph significance across all color channels and by averaging across all graphs. Our GraphSIM is validated using two large and independent point cloud assessment datasets that involve a wide range of impairments (e.g., re-sampling, compression, additive noise), reliably demonstrating the state-of-the-art performance for all distortions with noticeable gains in predicting the subjective mean opinion score (MOS), compared with those point-wise distance-based metrics adopted in standardization reference software. Ablation studies have further shown that GraphSIM is generalized to various scenarios with consistent performance by examining its key modules and parameters., Comment: This paper has been accepted by TPAMI, 21, Decemebr, 2020

Convolutional neural networks (CNNs) have been widely used for hyperspectral image classification. As a common process, small cubes are firstly cropped from the hyperspectral image and then fed into CNNs to extract spectral and spatial features. It is well known that different spectral bands and spatial positions in the cubes have different discriminative abilities. If fully explored, this prior information will help improve the learning capacity of CNNs. Along this direction, we propose an attention aided CNN model for spectral-spatial classification of hyperspectral images. Specifically, a spectral attention sub-network and a spatial attention sub-network are proposed for spectral and spatial classification, respectively. Both of them are based on the traditional CNN model, and incorporate attention modules to aid networks focus on more discriminative channels or positions. In the final classification phase, the spectral classification result and the spatial classification result are combined together via an adaptively weighted summation method. To evaluate the effectiveness of the proposed model, we conduct experiments on three standard hyperspectral datasets. The experimental results show that the proposed model can achieve superior performance compared to several state-of-the-art CNN-related models.

Video Object Segmentation (VOS) is typically formulated in a semi-supervised setting. Given the ground-truth segmentation mask on the first frame, the task of VOS is to track and segment the single or multiple objects of interests in the rest frames of the video at the pixel level. One of the fundamental challenges in VOS is how to make the most use of the temporal information to boost the performance. We present an end-to-end network which stores short- and long-term video sequence information preceding the current frame as the temporal memories to address the temporal modeling in VOS. Our network consists of two temporal sub-networks including a short-term memory sub-network and a long-term memory sub-network. The short-term memory sub-network models the fine-grained spatial-temporal interactions between local regions across neighboring frames in video via a graph-based learning framework, which can well preserve the visual consistency of local regions over time. The long-term memory sub-network models the long-range evolution of object via a Simplified-Gated Recurrent Unit (S-GRU), making the segmentation be robust against occlusions and drift errors. In our experiments, we show that our proposed method achieves a favorable and competitive performance on three frequently-used VOS datasets, including DAVIS 2016, DAVIS 2017 and Youtube-VOS in terms of both speed and accuracy., Comment: 10 pages, 5 figures

In this paper, we propose an efficient and effective framework to fuse hyperspectral and Light Detection And Ranging (LiDAR) data using two coupled convolutional neural networks (CNNs). One CNN is designed to learn spectral-spatial features from hyperspectral data, and the other one is used to capture the elevation information from LiDAR data. Both of them consist of three convolutional layers, and the last two convolutional layers are coupled together via a parameter sharing strategy. In the fusion phase, feature-level and decision-level fusion methods are simultaneously used to integrate these heterogeneous features sufficiently. For the feature-level fusion, three different fusion strategies are evaluated, including the concatenation strategy, the maximization strategy, and the summation strategy. For the decision-level fusion, a weighted summation strategy is adopted, where the weights are determined by the classification accuracy of each output. The proposed model is evaluated on an urban data set acquired over Houston, USA, and a rural one captured over Trento, Italy. On the Houston data, our model can achieve a new record overall accuracy of 96.03%. On the Trento data, it achieves an overall accuracy of 99.12%. These results sufficiently certify the effectiveness of our proposed model.

The physical mechanism driving the $\gamma$-$\alpha$ phase transition of face-centre-cubic (fcc) cerium (Ce) remains controversial until now. In this work, high quality single crystalline fcc-Ce thin films were grown on Graphene/6$H$-SiC(0001) substrate, and explored by XRD and ARPES measurement. XRD spectra showed a clear $\gamma$-$\alpha$ phase transition at $T_{\gamma-\alpha}\approx$ 50 K, which is retarded by strain effect from substrate comparing with $T_{\gamma-\alpha}$ (about 140 K) of the bulk Ce metal. However, APRES spectra did not show any signature of $\alpha$-phase emerging in the surface-layer from 300 K to 17 K, which implied that $\alpha$-phase might form at the bulk-layer of our Ce thin films. Besides, an evident Kondo dip near Fermi energy was observed in the APRES spectrum at 80 K, indicting the formation of Kondo singlet states in $\gamma$-Ce. Furthermore, the DFT+DMFT calculations were performed to simulate the electronic structures and the theoretical spectral functions agreed well with the experimental ARPES spectra. In $\gamma$-Ce, the behavior of the self-energy's imaginary part at low frequency not only confirmed that the Kondo singlet states emerged at $T_{\rm KS} \geq 80$ K, but also implied that they became coherent states at a lower characteristic temperature ($T_{\rm coh}\sim 40$ K) due to the indirect RKKY interaction among $f$-$f$ electrons. Besides, $T_{\rm coh}$ from the theoretical simulation was close to $T_{\gamma-\alpha}$ from the XRD spectra. These issues suggested that the Kondo scenario might play an important role in the $\gamma$-$\alpha$ phase transition of cerium thin films.

Current adoption of machine learning in industrial, societal and economical activities has raised concerns about the fairness, equity and ethics of automated decisions. Predictive models are often developed using biased datasets and thus retain or even exacerbate biases in their decisions and recommendations. Removing the sensitive covariates, such as gender or race, is insufficient to remedy this issue since the biases may be retained due to other related covariates. We present a regularization approach to this problem that trades off predictive accuracy of the learned models (with respect to biased labels) for the fairness in terms of statistical parity, i.e. independence of the decisions from the sensitive covariates. In particular, we consider a general framework of regularized empirical risk minimization over reproducing kernel Hilbert spaces and impose an additional regularizer of dependence between predictors and sensitive covariates using kernel-based measures of dependence, namely the Hilbert-Schmidt Independence Criterion (HSIC) and its normalized version. This approach leads to a closed-form solution in the case of squared loss, i.e. ridge regression. Moreover, we show that the dependence regularizer has an interpretation as modifying the corresponding Gaussian process (GP) prior. As a consequence, a GP model with a prior that encourages fairness to sensitive variables can be derived, allowing principled hyperparameter selection and studying of the relative relevance of covariates under fairness constraints. Experimental results in synthetic examples and in real problems of income and crime prediction illustrate the potential of the approach to improve fairness of automated decisions.

The plenoptic point cloud that has multiple colors from various directions, is a more complete representation than the general point cloud that usually has only one color. It is more realistic but also brings a larger volume of data that needs to be compressed efficiently. The state-of-the-art method to compress the plenoptic point cloud is an extension of the region-based adaptive hierarchical transform (RAHT). As far as we can see, in addition to RAHT, the video-based point cloud compression (V-PCC) is also an efficient point cloud compression method. However, to the best of our knowledge, no works have used a video-based solution to compress the plenoptic point cloud yet. In this paper, we first extend the V-PCC to support the plenoptic point cloud compression by generating multiple attribute videos. Then based on the observation that these videos from multiple views have very high correlations, we propose encoding them using multiview high efficiency video coding. We further propose a block-based padding method that unifies the unoccupied attribute pixels from different views to reduce their bit cost. The proposed algorithms are implemented in the V-PCC reference software. The experimental results show that the proposed algorithms can bring significant bitrate savings compared with the state-of-the-art method for plenoptic point cloud compression., Comment: 10 pages, 4 figures

The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc. To compensate for those artifacts, extensive filtering techniques were proposed in the loop of video codecs, which are capable of boosting the subjective and objective qualities of reconstructed videos. Recently, neural network based filters were presented with the power of deep learning from a large magnitude of data. Though the coding efficiency has been improved from traditional methods in High-Efficiency Video Coding (HEVC), the rich features and information generated by the compression pipeline has not been fully utilized in the design of neural networks. Therefore, in this paper, we propose the Residual-Reconstruction-based Convolutional Neural Network (RRNet) to further improve the coding efficiency to its full extent, where the compression features induced from bitstream in form of prediction residual is fed into the network as an additional input to the reconstructed frame. In essence, the residual signal can provide valuable information about block partitions and can aid reconstruction of edge and texture regions in a picture. Thus, more adaptive parameters can be trained to handle different texture characteristics. The experimental results show that our proposed RRNet approach presents significant BD-rate savings compared to HEVC and the state-of-the-art CNN-based schemes, indicating that residual signal plays a significant role in enhancing video frame reconstruction.