Search

The paper proposes a method to effectively fuse multi-exposure inputs and generate high-quality high dynamic range (HDR) images with unpaired datasets. Deep learning-based HDR image generation methods rely heavily on paired datasets. The ground truth images play a leading role in generating reasonable HDR images. Datasets without ground truth are hard to be applied to train deep neural networks. Recently, Generative Adversarial Networks (GAN) have demonstrated their potentials of translating images from source domain $X$ to target domain $Y$ in the absence of paired examples. In this paper, we propose a GAN-based network for solving such problems while generating enjoyable HDR results, named UPHDR-GAN. The proposed method relaxes the constraint of the paired dataset and learns the mapping from the LDR domain to the HDR domain. Although the pair data are missing, UPHDR-GAN can properly handle the ghosting artifacts caused by moving objects or misalignments with the help of the modified GAN loss, the improved discriminator network and the useful initialization phase. The proposed method preserves the details of important regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against the representative methods demonstrate the superiority of the proposed UPHDR-GAN. [ABSTRACT FROM AUTHOR]

Faster-than-Nyquist signaling (FTNS) has already been shown to increase the communication capacity on certain channels such as additive white Gaussian noise and block flat multiple-input multiple-output (MIMO) Rayleigh fading channels. The following issues, however, remain unresolved: 1) whether FTNS enables a capacity increase in generalized MIMO Rayleigh fading channels that are selective in time, frequency, and space; and 2) how channel selectivities affect the capacity and if present, the FTN capacity gain. To address the issues, this paper firstly investigates the ergodic capacity of MIMO-FTN transmission over triply-selective fading channels. We derive a low-complexity approximate capacity formula and also show how it degenerates in other channel models, such as doubly-selective single-input single-output fading channels, which can be considered as the special cases of triply-selective fading channels. The capacity evaluation results obtained under different channel conditions show that: 1) MIMO-FTN outperforms MIMO-Nyquist in terms of capacity; 2) the FTN gains are nearly consistent, while the FTN gains obtained in the frequency-selective fading channels are slightly higher than those obtained in the flat fading channels. [ABSTRACT FROM AUTHOR]

The paper proposes a solution based on Generative Adversarial Network (GAN) for solving jigsaw puzzles. The problem assumes that an image is divided into equal square pieces, and asks to recover the image according to information provided by the pieces. Conventional jigsaw puzzle solvers often determine the relationships based on the boundaries of pieces, which ignore the important semantic information. In this paper, we propose JigsawGAN, a GAN-based auxiliary learning method for solving jigsaw puzzles with unpaired images (with no prior knowledge of the initial images). We design a multi-task pipeline that includes, (1) a classification branch to classify jigsaw permutations, and (2) a GAN branch to recover features to images in correct orders. The classification branch is constrained by the pseudo-labels generated according to the shuffled pieces. The GAN branch concentrates on the image semantic information, where the generator produces the natural images to fool the discriminator, while the discriminator distinguishes whether a given image belongs to the synthesized or the real target domain. These two branches are connected by a flow-based warp module that is applied to warp features to correct the order according to the classification results. The proposed method can solve jigsaw puzzles more efficiently by utilizing both semantic information and boundary information simultaneously. Qualitative and quantitative comparisons against several representative jigsaw puzzle solvers demonstrate the superiority of our method. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel point-to-surface representation for 3D point cloud learning. Unlike the previous methods that mainly adopt voxel, mesh, or point coordinates, we propose to tackle this problem from a new perspective: learn a set of quadratic terms based static and global reference surfaces to describe 3D shapes, such that the coordinates of a 3D point (x, y, z) can be extended to quadratic terms (xy, xz, yz, $\ldots $) and transformed to the relationship between the local point and the global reference surfaces. Then, the static surfaces are changed into dynamic surfaces by adaptive contribution weighting to improve the descriptive capability. Towards this end, we propose our point-to-surface representation, a new representation for 3D point cloud learning that has not been attempted before, which can assemble local and global geometric information effectively by building connections between the point cloud and the learned reference surfaces. Given 3D points, we show how the reference surfaces are constructed, and how they are inserted into the 3D learning pipeline for different tasks. The experimental results confirm the effectiveness of our new representation, which has outperformed the state-of-the-art methods on the tasks of 3D classification and segmentation. [ABSTRACT FROM AUTHOR]

Faster-than-Nyquist signaling (FTNS) has emerged as a promising technique to increase communication capacity in bandwidth-limited channels. However, the presence of FTN-induced inter-symbol interference (FTN-ISI) in the received observations, is detrimental to channel estimation (CE) and data detection in terms of computational complexity and performance. This paper copes with these problems by incorporating linear pre-equalization (LPE) and composite precoding formed by linear spectral precoding and Tomlinson-Harashima precoding (THP), into the FTNS. Specifically, LPE completely pre-equalizes the FTN-ISI, while spectral precoding resolves the LPE-caused signal spectral broadening by introducing proper artificial ISI, which is pre-equalized by THP. Channel-induced ISI, as the only ISI component in the observations, is estimated and equalized using the classical frequency-domain low-complexity schemes. We show that there are four advantages of the LPE-aided CE over the CE designed for the FTN transmissions without FTN-ISI pre-equalization, namely lower pilot overhead, simpler yet optimal pilot sequence design, lower mean-squared error of CE, and more robust against the FTN-ISI. Simulation results show that our scheme improves the performance of CE and detection, compared to existing FTN frequency-domain CE and equalization schemes. [ABSTRACT FROM AUTHOR]

Accurate intensity estimation of tropical cyclone (TC) is important and challenging. Currently, no standardized method is available for estimating the TC intensity, usually in terms of the maximum surface wind speed, using satellite remote sensing data. This article proposes a multifeature distribution learning (MFDL) model that uses satellite microwave brightness temperatures to estimate the TC intensity. The MFDL model uses the brightness temperatures of Advanced Technology Microwave Sounder (ATMS) to generate the synthetic temperature anomaly fields of TCs at different pressure levels. These 3-D temperature anomaly data are trained by MFDL to establish the relationship between anomaly fields and TC intensity. MFDL treats the TC intensity estimation as a probability distribution of wind speed, instead of as a regression problem as in the conventional TC intensity estimation methods. In this study, 964 TCs occurred in North Atlantic (NA) and North Pacific (NP) from 2012 to 2019 are used for training and testing. The simulation results suggest that estimation accuracy is greatly improved using the preprocessed 3-D TC anomaly data. The MFDL network achieves the average mean absolute errors (MAEs) of 4.37 m/s for NA TCs and 4.92 m/s for NP TCs in the years 2018 and 2019. The results show that the MFDL network and ATMS temperature-based anomaly can be a promising means for TC intensity estimation in operational weather forecast. [ABSTRACT FROM AUTHOR]

The state-of-the-art radio-frequency (RF) devices limit the deployment of extremely high-order quadrature amplitude modulation (QAM) formats (e.g., 16384-QAM) to meet the high-capacity demand on microwave backhaul links. This paper turns to faster-than-Nyquist (FTN) transmission using lower-order constellations and lower-cost RF devices as a solution to the demand. To realize low-complexity interference cancellation, we pre-equalize the FTN-induced inter-symbol interference at the transmitter by using Tomlinson-Harashima precoding (THP), while at the receiver suppressing the phase noise (PHN) generated by the RF local oscillators with pilot symbol assisted approaches. However, the THP may distort the pilots, which degrades the performance of PHN compensation. To resolve this problem, we propose two pilot designs that are distortion-free to precisely estimate the PHN samples. Moreover, we derive a closed-form expression of the symbol detection signal-to-noise ratio (SNR), in terms of the THP-FTN waveform parameters. With the SNR expression, a waveform optimization procedure is developed to maximize the SNR and enhance the achievable FTN capacity. The proposed scheme is validated in the simulated platform of 4096-QAM microwave link. The results demonstrate that the FTN signaling achieves the system capacity equivalent to that of the 16384-QAM Nyquist signaling with an SNR gain of 5.8 dB. [ABSTRACT FROM AUTHOR]

Over-the-air (OTA) measurement is mandatory for 5G mm-wave wireless devices. The compact antenna test range (CATR) is the baseline method in the current version of TR 38.810 in 3rd generation partnership project (3GPP) and cellular telecommunications industry association (CTIA) millimeter-wave (mm-Wave) test plan. For CATR, both amplitude and phase variations inside the quiet zone (QZ) could affect the final OTA results significantly and hence need to be characterized carefully. Especially in the phase validation of QZ, even slight misalignments between sampling plane and incident plane wavefront due to the limited precision of the positioner or tolerance in antenna fixture could result in large phase variations, which is not the true phase property of QZ. This letter presents a method to remove the effect of the angular error due to misalignment when measuring the phase variation inside QZ. By adopting the proposed method to the measured phase data, any angular error due to misalignment with respect to the incident plane wavefront will be eliminated mathematically, leaving the true phase variations of QZ only. In the meanwhile, the proposed method can alleviate the requirements of fixture manufacture and alignment precision and reduce the test cost. [ABSTRACT FROM AUTHOR]

Orthogonal time frequency space (OTFS) has shown to be a promising modulation technology that achieves the robust wireless transmission in high-mobility environments. The high mobility incurred Doppler effect in OTFS system, is represented as a continuous and relatively large band in the Doppler frequency. It yields the equivalent channel responses (ECRs) in the system change significantly within one symbol block, posing a challenge to channel estimation (CE) or tracking. In order to tackle this issue, in this paper, a set of transform-domain basis functions is designed to span a low-dimensional subspace for modeling the OTFS channel. Then, the CE can be performed by estimating a few projection coefficients of ECRs in the developed subspace, with training pilots. According to the individual transmission characteristic of OTFS signal, we propose a corner-inserted pilot pattern, which targets the low pilot overhead and satisfactory CE performance. Moreover, an OTFS signal detector, leveraging the time-domain channel equalization, linear-complexity interference cancellation and delay-Doppler domain maximal ratio combining detection, is developed to retrieve the transmitted data symbols. The simulations show the precisely estimated ECRs enable the detector to ideally demodulate 256-ary quadrature amplitude modulation signaling, under a velocity of 550 km/h at 5.9 GHz carrier frequency. [ABSTRACT FROM AUTHOR]

The paper proposes a solution to effectively handle salient regions for style transfer between unpaired datasets. Recently, Generative Adversarial Networks (GAN) have demonstrated their potentials of translating images from source domain ${X}$ to target domain ${Y}$ in the absence of paired examples. However, such a translation cannot guarantee to generate high perceptual quality results. Existing style transfer methods work well with relatively uniform content, they often fail to capture geometric or structural patterns that always belong to salient regions. Detail losses in structured regions and undesired artifacts in smooth regions are unavoidable even if each individual region is correctly transferred into the target style. In this paper, we propose SDP-GAN, a GAN-based network for solving such problems while generating enjoyable style transfer results. We introduce a saliency network, which is trained with the generator simultaneously. The saliency network has two functions: (1) providing constraints for content loss to increase punishment for salient regions, and (2) supplying saliency features to generator to produce coherent results. Moreover, two novel losses are proposed to optimize the generator and saliency networks. The proposed method preserves the details on important salient regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against several leading prior methods demonstrates the superiority of our method. [ABSTRACT FROM AUTHOR]

Accurate cloud detection using infrared (IR) data is very challenging due to the limitations and uncertainties from many aspects in the satellite IR remote sensing. This article proposes an end-to-end cloud detection method for the Cross-track IR Sounder (CrIS) using machine learning (ML) techniques. The brightness temperatures from paired CrIS channels in the longwave and midwave water vapor bands and the longwave and shortwave CO2 bands are used. After obtaining the linear regression coefficients for each of the selected channel pairs, a complete set of CrIS full spectral resolution (FSR) cloud detection index (FCDI) is derived from the temperature difference between the regression and observation for each channel pair. It is shown that FCDI captures cloud location and structure well by comparing with the cloud products (CPs) from the Visible IR Imaging Radiometer Suite (VIIRS). After collocating FCDI with VIIRS CP, ML techniques such as the extreme learning machine, support vector machine, and multilayer perceptron are used to train the collocated FCDIs for cloud detection. Simulation results show that the accuracy of FCDI cloud detection is slightly above 80%. Moreover, the results encourage the use of water vapor bands in FCDI, in addition to CO2 bands. [ABSTRACT FROM AUTHOR]

Orthogonal time frequency space (OTFS) is a two-dimensional modulation scheme realized in the delay-Doppler domain, which targets the robust wireless transmissions in high-mobility environments. In such scenarios, OTFS signal suffers from multipath channel with continuous Doppler spread, which results in significant inter-symbol interference and inter-Doppler interference (IDI). In this article, we analyze the interference generation mechanism, and compare statistical distributions of the IDI in two typical cases, i.e., limited-Doppler-shift channel and continuous-Doppler-spread channel (CoDSC). Focusing on the OTFS signal transmission over the CoDSC, our study firstly indicates that the widespread IDI incurs a computational burden for the element-wise detector like the message passing in the state-of-the-art works. Addressing this challenge, we propose a block-wise OTFS receiver by exploiting the structure and characteristics of the OTFS transmission matrix. In the receiver, we deliberately design an iteration strategy among the least squares minimum residual based channel equalizer, reliability-based symbol detector and interference eliminator, which can realize fast convergence by leveraging the sparsity of channel matrix. The simulations demonstrate that, in the CoDSC, the proposed scheme achieves much less detection error, and meanwhile reduces the computational complexity by an order of magnitude, compared with the state-of-the-art OTFS receivers. [ABSTRACT FROM AUTHOR]

Faster-than-Nyquist signaling (FTNS) is capable of improving the spectral efficiency (SE) of communication systems. However, for conventional single-carrier FTNS (SC-FTNS) in which only symbol interval is reduced, the increase of SE is very limited due to the presence of inter-symbol interference (ISI) introduced by the FTNS. To deal with this problem, this paper proposes a new time-frequency compressed SC-FTNS (TFC-SC-FTNS) scheme that includes the conventional FTNS as a special case, to improve the SE via two dimensions simultaneously: time dimension by stacking symbols closer; frequency dimension by precoding to make the FTN signal spectrum more compact. Further, an optimization subject to a spectral mask constraint is performed on the precoder to suppress the ISI, according to a mean-square-error criterion, but the optimization problem is non-convex. A nontrivial contribution in the new scheme is that the non-convex problem is transformed into a convex one by a change of variable and an addition of admissibility constraint. Simulation results demonstrate that the proposed scheme significantly outperforms the conventional FTNS in terms of achievable SE or, equivalently, reception performance at a given SE. Further, with larger constellations applied, the gains of the TFC-FTNS increase. [ABSTRACT FROM AUTHOR]

Similar to orthogonal frequency division multiplexing receiver, the frequency-domain (FD) channel estimation (CE) and equalization are indispensable parts in the coherent single carrier frequency division multiplexing (SC-FDM) receiver. When the channel varies slowly, the FD processing is cost effective. For the applications with high mobility, the traditional implementation of the SC-FDM receiver causes significant performance degradation. In this paper, we propose to estimate time-varying pieces of channel taps for pilot symbols based on basis expansion model (BEM), and subsequently to reconstruct time-domain (TD) channel response for data symbols by utilizing the Slepian sequences-based piece-wise interpolation. Furthermore, two simplified schemes, i.e., the Slepian sequences-based multiple-point interpolation and the segmented BEM, are developed to reduce the computational complexity of the TD-CE. The Cramer-Rao lower bound (CRLB) of channel impulse response (CIR) estimation is also analyzed. In the light of the sparsity of TD channel gain matrix, we design an iterative least-squares QR decomposition algorithm to equalize the SC-FDM symbols. In the simulated SC-FDM system, when considering the carrier frequency of 5.9 GHz and the velocity of about 510 km/h, we observe that the traditional FD methods cause the demodulation failure, while the proposed TD processing schemes achieve ideal error-probability performance and preserve a relatively low complexity. [ABSTRACT FROM AUTHOR]

When orthogonal frequency-division multiplexing (OFDM) is used in high-speed mobile scenarios, the traditional implementation of the OFDM receiver causes significant performance degradation. This letter proposes a subband superposed oversampled OFDM (SS-OOFDM) scheme for accommodating the diverse scenarios, including the scenarios with high mobility. To track the fast-varying mobile channel, a time-domain channel estimation method is developed to first obtain the channel impulse response (CIR) values at pilots by means of the basis expansion model. Subsequently, by utilizing Slepian sequences-based interpolation, the CIR values at data symbols are reconstructed. Furthermore, we design a subband decision feedback and feedforward equalizer for exploiting the Doppler and multipath diversity gains. Simulation results show that the SS-OOFDM, especially in high-speed mobile channels, outperforms the traditional OFDM receiver in terms of the bit-error-rate performance. [ABSTRACT FROM AUTHOR]

In this paper, the properties and operation of the virtual-space-vector pulse-width modulation (PWM) for a three-level neutral-point-clamped inverter with unbalanced dc-links are studied. By quantitatively analyzing the characteristics of the revised space-vector diagram (SVD) with unbalanced dc-links, the defined virtual SVD (VSVD) for the unbalanced case is theoretically proven identical to the VSVD of the conventional virtual-space-vector PWM (VSVPWM) strategy with balanced dc-links. The well-developed and fast-processing methods to calculate the durations of the nearest three virtual vectors for the conventional VSVPWM can be directly utilized. In addition, a control strategy to realize the asymmetric control of the dc-link voltages with VSVPWM is also studied, and this method can adjust the unbalancing degree with a high accuracy for any modulation indexes and load power factors. Simulated and experimental results are given to validate the effectiveness. [ABSTRACT FROM PUBLISHER]