Automated Video Generation of Moving Digits from Text Using Deep Deconvolutional Generative Adversarial Network

Generating realistic and synthetic video from text is a highly challenging task due to the multitude of issues involved,including digit deformation,noise interference between frames,blurred output,and the need for temporal coherence across frames.In this paper,we propose a novel approach for generating coherent videos of moving digits from textual input using a Deep Deconvolutional Generative Adversarial Network(DD-GAN).The DDGAN comprises a Deep Deconvolutional Neural Network(DDNN)as a Generator(G)and a modified Deep Convolutional Neural Network(DCNN)as a Discriminator(D)to ensure temporal coherence between adjacent frames.The proposed research involves several steps.First,the input text is fed into a Long Short Term Memory(LSTM)based text encoder and then smoothed using Conditioning Augmentation(CA)techniques to enhance the effectiveness of the Generator(G).Next,using a DDNN to generate video frames by incorporating enhanced text and random noise and modifying a DCNN to act as a Discriminator(D),effectively distinguishing between generated and real videos.This research evaluates the quality of the generated videos using standard metrics like Inception Score(IS),Fréchet Inception Distance(FID),Fréchet Inception Distance for video(FID2vid),and Generative Adversarial Metric(GAM),along with a human study based on realism,coherence,and relevance.By conducting experiments on Single-Digit Bouncing MNIST GIFs(SBMG),Two-Digit Bouncing MNIST GIFs(TBMG),and a custom dataset of essential mathematics videos with related text,this research demonstrates significant improvements in both metrics and human study results,confirming the effectiveness of DD-GAN.This research also took the exciting challenge of generating preschool math videos from text,handling complex structures,digits,and symbols,and achieving successful results.The proposed research demonstrates promising results for generating coherent videos from textual input.

基于聚焦变换解卷积的宽带稳健波束形成

In the field of array signal processing,uniform linear arrays(ULAs)are widely used to detect/separate a weak target and estimate its direction of arrival from interference and noise.Conventional beamforming(CBF)is robust but restricted by a wide mainlobe and high sidelobe level.Covariance-matrix-inversed beamforming techniques,such as the minimum variance distortionless response and multiple signal classification,are sensitive to signal mismatch and data snapshots and exhibit high-resolution performance because of the narrow mainlobe and low sidelobe level.Therefore,compared with the wideband CBF,this study proposes a robust focused-and-deconvolved conventional beamforming(RFD-CBF),utilizing the Richardson–Lucy(R-L)iterative algorithm to deconvolve the focused conventional beam power of a half-wavelength spaced ULA.Then,the focused-and-deconvolved beam power achieves a narrower mainlobe and lower sidelobe level while retaining the robustness of wideband CBF.Moreover,compared with the wideband CBF,RFD-CBF can obtain a higher output signal-to-noise ratio(SNR).Finally,the performance of RFD-CBF is evaluated through numerical simulation and verified by sea trial data processing.

Study of inter-well interference in shale gas reservoirs by a robust production data analysis method based on deconvolution

In order to overcome the defects that the analysis of multi-well typical curves of shale gas reservoirs is rarely applied to engineering,this study proposes a robust production data analysis method based on deconvolution,which is used for multi-well inter-well interference research.In this study,a multi-well conceptual trilinear seepage model for multi-stage fractured horizontal wells was established,and its Laplace solutions under two different outer boundary conditions were obtained.Then,an improved pressure deconvolution algorithm was used to normalize the scattered production data.Furthermore,the typical curve fitting was carried out using the production data and the seepage model solution.Finally,some reservoir parameters and fracturing parameters were interpreted,and the intensity of inter-well interference was compared.The effectiveness of the method was verified by analyzing the production dynamic data of six shale gas wells in Duvernay area.The results showed that the fitting effect of typical curves was greatly improved due to the mutual restriction between deconvolution calculation parameter debugging and seepage model parameter debugging.Besides,by using the morphological characteristics of the log-log typical curves and the time corresponding to the intersection point of the log-log typical curves of two models under different outer boundary conditions,the strength of the interference between wells on the same well platform was well judged.This work can provide a reference for the optimization of well spacing and hydraulic fracturing measures for shale gas wells.

Distributed Dynamic Load in Structural Dynamics by the Impulse-Based Force Estimation Algorithm

This paper proposes a novel approach for identifying distributed dynamic loads in the time domain.Using polynomial andmodal analysis,the load is transformed intomodal space for coefficient identification.This allows the distributed dynamic load with a two-dimensional form in terms of time and space to be simultaneously identified in the form of modal force,thereby achieving dimensionality reduction.The Impulse-based Force Estimation Algorithm is proposed to identify dynamic loads in the time domain.Firstly,the algorithm establishes a recursion scheme based on convolution integral,enabling it to identify loads with a long history and rapidly changing forms over time.Secondly,the algorithm introduces moving mean and polynomial fitting to detrend,enhancing its applicability in load estimation.The aforementioned methodology successfully accomplishes the reconstruction of distributed,instead of centralized,dynamic loads on the continuum in the time domain by utilizing acceleration response.To validate the effectiveness of the method,computational and experimental verification were conducted.

Cryo-EM combined with image deconvolution to determine ZIF-8 crystal structure

Metal–organic frameworks(MOFs) are crystalline porous materials with tunable properties, exhibiting great potential in gas adsorption, separation and catalysis.[1,2]It is challenging to visualize MOFs with transmission electron microscopy(TEM) due to their inherent instability under electron beam irradiation. Here, we employ cryo-electron microscopy(cryoEM) to capture images of MOF ZIF-8, revealing inverted-space structural information at a resolution of up to about 1.7A and enhancing its critical electron dose to around 20 e^(-)/A^(2). In addition, it is confirmed by electron-beam irradiation experiments that the high voltage could effectively mitigate the radiolysis, and the structure of ZIF-8 is more stable along the [100] direction under electron beam irradiation. Meanwhile, since the high-resolution electron microscope images are modulated by contrast transfer function(CTF) and it is difficult to determine the positions corresponding to the atomic columns directly from the images. We employ image deconvolution to eliminate the impact of CTF and obtain the structural images of ZIF-8. As a result, the heavy atom Zn and the organic imidazole ring within the organic framework can be distinguished from structural images.

Research on a deconvolution algorithm for laser-induced fluorescence diagnosis based on the maximum entropy principle

Laser-induced fluorescence(LIF)spectroscopy is employed for plasma diagnosis,necessitating the utilization of deconvolution algorithms to isolate the Doppler effect from the raw spectral signal.However,direct deconvolution becomes invalid in the presence of noise as it leads to infinite amplification of high-frequency noise components.To address this issue,we propose a deconvolution algorithm based on the maximum entropy principle.We validate the effectiveness of the proposed algorithm by utilizing simulated LIF spectra at various noise levels(signal-to-noise ratio,SNR=20–80 d B)and measured LIF spectra with Xe as the working fluid.In the typical measured spectrum(SNR=26.23 d B)experiment,compared with the Gaussian filter and the Richardson–Lucy(R-L)algorithm,the proposed algorithm demonstrates an increase in SNR of 1.39 d B and 4.66 d B,respectively,along with a reduction in the root-meansquare error(RMSE)of 35%and 64%,respectively.Additionally,there is a decrease in the spectral angle(SA)of 0.05 and 0.11,respectively.In the high-quality spectrum(SNR=43.96 d B)experiment,the results show that the running time of the proposed algorithm is reduced by about98%compared with the R-L iterative algorithm.Moreover,the maximum entropy algorithm avoids parameter optimization settings and is more suitable for automatic implementation.In conclusion,the proposed algorithm can accurately resolve Doppler spectrum details while effectively suppressing noise,thus highlighting its advantage in LIF spectral deconvolution applications.

Enhancing the vertical resolution of lunar penetrating radar data using predictive deconvolution

The Yutu-2 rover onboard the Chang’E-4 mission performed the first lunar penetrating radar detection on the farside of the Moon.The high-frequency channel presented us with many unprecedented details of the subsurface structures within a depth of approximately 50 m.However,it was still difficult to identify finer layers from the cluttered reflections and scattering waves.We applied deconvolution to improve the vertical resolution of the radar profile by extending the limited bandwidth associated with the emissive radar pulse.To overcome the challenges arising from the mixed-phase wavelets and the problematic amplification of noise,we performed predictive deconvolution to remove the minimum-phase components from the Chang’E-4 dataset,followed by a comprehensive phase rotation to rectify phase anomalies in the radar image.Subsequently,we implemented irreversible migration filtering to mitigate the noise and diminutive clutter echoes amplified by deconvolution.The processed data showed evident enhancement of the vertical resolution with a widened bandwidth in the frequency domain and better signal clarity in the time domain,providing us with more undisputed details of subsurface structures near the Chang’E-4 landing site.

Solar image reconstruction method under atmospheric turbulence at Fuxian Lake Solar Observatory

Strong atmospheric turbulence reduces astronomical seeing,causing speckle images acquired by ground-based solar telescopes to become blurred and distorted.Severe distortion in speckle images impedes image phase deviation in the speckle masking reconstruction method,leading to the appearance of spurious imaging artifacts.Relying only on linear image degradation principles to reconstruct solar images is insufficient.To solve this problem,we propose the multiframe blind deconvolution combined with non-rigid alignment(MFBD-CNRA)method for solar image reconstruction.We consider image distortion caused by atmospheric turbulence and use non-rigid alignment to correct pixel-level distortion,thereby achieving nonlinear constraints to complement image intensity changes.After creating the corrected speckle image,we use the linear method to solve the wavefront phase,obtaining the target image.We verify the effectiveness of our method results,compared with others,using solar observation data from the 1 m new vacuum solar telescope(NVST).This new method successfully reconstructs high-resolution images of solar observations with a Fried parameter r0 of approximately 10 cm,and enhances images at high frequency.When r0 is approximately 5 cm,the new method is even more effective.It reconstructs the edges of solar graining and sunspots,and is greatly enhanced at mid and high frequency compared with other methods.Comparisons confirm the effectiveness of this method,with respect to both nonlinear and linear constraints in solar image reconstruction.This provides a suitable solution for image reconstruction in ground-based solar observations under strong atmospheric turbulence.

Deblurring,artifact-free optical coherence tomography with deconvolution-random phase modulation

Deconvolution is a commonly employed technique for enhancing image quality in optical imaging methods.Unfortu-nately,its application in optical coherence tomography(OCT)is often hindered by sensitivity to noise,which leads to ad-ditive ringing artifacts.These artifacts considerably degrade the quality of deconvolved images,thereby limiting its effect-iveness in OCT imaging.In this study,we propose a framework that integrates numerical random phase masks into the deconvolution process,effectively eliminating these artifacts and enhancing image clarity.The optimized joint operation of an iterative Richardson-Lucy deconvolution and numerical synthesis of random phase masks(RPM),termed as De-conv-RPM,enables a 2.5-fold reduction in full width at half-maximum(FWHM).We demonstrate that the Deconv-RPM method significantly enhances image clarity,allowing for the discernment of previously unresolved cellular-level details in nonkeratinized epithelial cells ex vivo and moving blood cells in vivo.

胰腺局灶性实性病变CT灌注参数特征及不同算法的比较

目的总结胰腺局灶性实性病变CT灌注参数的特征,评估Deconvolution和Maximum slope+Patlak方法所测得的灌注参数之间的一致性及两种测量方法之间是否可相互替换。方法 2015年12月至2016年11月在北京协和医院行全胰腺CT灌注检查、经术后及穿刺病理证实为胰腺癌(PAC)患者22例和胰腺神经内分泌瘤(p NET)患者22例(共37个病灶),全胰腺CT灌注检查采用管电压80kV、管电流100m A,进行28次连续动态体积扫描,静脉注射45ml碘普罗胺,速率5ml/s,随后追加40ml盐水,速率5ml/s。由1名经验丰富的放射科医师在西门子后处理工作站上分别用Maximum slope+Patlak及Deconvolution method方法进行数据分析,测量并记录其灌注参数。结果 Wilcoxon非参配对秩和检验结果显示,PAC(BFM比BFD,Z=-3.263,P=0.001;BVD比BVP,Z=-3.978,P=0.000)和p NET(BFM比BFD,Z=-5.212,P=0.000;BVD比BVP,Z=-2.633,P=0.008)两种方法所测得的灌注参数之间差异均有统计学意义。Spearman’s相关系数分析结果显示,PAC(BFM与BFD,r=0.845,P=0.000;BVD与BVP,r=0.964,P=0.000)和p NET(BFM与BFD,r=0.759,P=0.000;BVD比BVP,r=0.683,P=0.000)两种方法所测得的灌注参数间均有显著相关性。PAC的BFM/BFD和BVD/BVP几何均数及其95%一致性界限(LOA)分别为0.77(0.61~0.99)和1.42(1.13~1.79),p NET的BFM/BFD和BVD/BVP几何均数及其95%LOA分别为0.66(0.51~0.86)和1.15(0.88~1.50)。结论无论在PAC还是p NET中由Deconvolution和Maximum slope+Patlak方法所测得的灌注参数BF、BV存在显著性差异,两种测量方法之间具有显著相关性,并且两者之间的转换范围较窄,所以两种测量方法之间可以相互替换。

气相色谱-质谱数据的后处理

气相色谱-质谱(gas chromatography/mass spectrometry)以其优异的分离定性特点,被广泛地应用于分析复杂混合物中的挥发性组分.然而,其质谱图会包含一些来自于离子源污染物、柱流失物、基质干扰物所产生的离子,导致定性准确性降低.……

Prestack nonstationary deconvolution based on variable-step sampling in the radial trace domain

The conventional nonstationary convolutional model assumes that the seismic signal is recorded at normal incidence. Raw shot gathers are far from this assumption because of the effects of offsets. Because of such problems, we propose a novel prestack nonstationary deconvolution approach. We introduce the radial trace （RT） transform to the nonstationary deconvolution, we estimate the nonstationary deconvolution factor with hyperbolic smoothing based on variable-step sampling （VSS） in the RT domain, and we obtain the high-resolution prestack nonstationary deconvolution data. The RT transform maps the shot record from the offset and traveltime coordinates to those of apparent velocity and traveltime. The ray paths of the traces in the RT better satisfy the assumptions of the convolutional model. The proposed method combines the advantages of stationary deconvolution and inverse Q filtering, without prior information for Q. The nonstationary deconvolution in the RT domain is more suitable than that in the space-time （XT） domain for prestack data because it is the generalized extension of normal incidence. Tests with synthetic and real data demonstrate that the proposed method is more effective in compensating for large-offset and deep data.

Nonstationary sparsity-constrained seismic deconvolution

The Robinson convolution model is mainly restricted by three inappropriate assumptions, i.e., statistically white reflectivity, minimum-phase wavelet, and stationarity. Modern reflectivity inversion methods（e.g., sparsity-constrained deconvolution） generally attempt to suppress the problems associated with the first two assumptions but often ignore that seismic traces are nonstationary signals, which undermines the basic assumption of unchanging wavelet in reflectivity inversion. Through tests on reflectivity series, we confirm the effects of nonstationarity on reflectivity estimation and the loss of significant information, especially in deep layers. To overcome the problems caused by nonstationarity, we propose a nonstationary convolutional model, and then use the attenuation curve in log spectra to detect and correct the influences of nonstationarity. We use Gabor deconvolution to handle nonstationarity and sparsity-constrained deconvolution to separating reflectivity and wavelet. The combination of the two deconvolution methods effectively handles nonstationarity and greatly reduces the problems associated with the unreasonable assumptions regarding reflectivity and wavelet. Using marine seismic data, we show that correcting nonstationarity helps recover subtle reflectivity information and enhances the characterization of details with respect to the geological record.

Improved Euler method for the interpretation of potential data based on the ratio of the vertical fi rst derivative to analytic signal

We propose a new automatic method for the interpretation of potential fi eld data, called the RDAS–Euler method, which is based on Euler＇s deconvolution and analytic signal methods. The proposed method can estimate the horizontal and vertical extent of geophysical anomalies without prior information of the nature of the anomalies（structural index）. It also avoids inversion errors because of the erroneous choice of the structural index N in the conventional Euler deconvolution method. The method was tested using model gravity anomalies. In all cases, the misfi t between theoretical values and inversion results is less than 10%. Relative to the conventional Euler deconvolution method, the RDAS–Euler method produces inversion results that are more stable and accurate. Finally, we demonstrate the practicability of the method by applying it to Hulin Basin in Heilongjiang province, where the proposed method produced more accurate data regarding the distribution of faults.

Blind Deconvolution Method Based on Precondition Conjugate Gradients

In seismic data processing, blind deconvolution is a key technology. Introduced in this paper is a flow of one kind of blind deconvolution. The optimal precondition conjugate gradients (PCG) in Kyrlov subspace is also used to improve the stability of the algorithm. The computation amount is greatly decreased.

Research on 3D marine electromagnetic interferometry with synthetic sources for suppressing the airwave interference

In order to suppress the airwave noise in marine controlled-source electromagnetic （CSEM） data, we propose a 3D deconvolution （3DD） interferometry method with a synthetic aperture source and obtain the relative anomaly coefficient （RAC） of the EM field reflection responses to show the degree for suppressing the airwave. We analyze the potential of the proposed method for suppressing the airwave, and compare the proposed method with traditional methods in their effectiveness. A method to select synthetic source length is derived and the effect of the water depth on RAC is examined via numerical simulations. The results suggest that 3DD interferometry method with a synthetic source can effectively suppress the airwave and enhance the potential of marine CSEM to hydrocarbon exploration.

Experimental analysis and application of sparsity constrained deconvolution

Sparsity constrained deconvolution can improve the resolution of band-limited seismic data compared to conventional deconvolution. However, such deconvolution methods result in nonunique solutions and suppress weak reflections. The Cauchy function, modified Cauchy function, and Huber function are commonly used constraint criteria in sparse deconvolution. We used numerical experiments to analyze the ability of sparsity constrained deconvolution to restore reflectivity sequences and protect weak reflections under different constraint criteria. The experimental results demonstrate that the performance of sparsity constrained deconvolution depends on the agreement between the constraint criteria and the probability distribution of the reflectivity sequences; furthermore, the modified Cauchy- constrained criterion protects the weak reflections better than the other criteria. Based on the model experiments, the probability distribution of the reflectivity sequences of carbonate and clastic formations is statistically analyzed by using well-logging data and then the modified Cauchy-constrained deconvolution is applied to real seismic data much improving the resolution.

An improved predictive deconvolution based on maximization of non-Gaussianity

The predictive deconvolution algorithm （PD）, which is based on second-order statistics, assumes that the primaries and the multiples are implicitly orthogonal. However, the seismic data usually do not satisfy this assumption in practice. Since the seismic data （primaries and multiples） have a non-Gaussian distribution, in this paper we present an improved predictive deconvolution algorithm （IPD） by maximizing the non-Gaussianity of the recovered primaries. Applications of the IPD method on synthetic and real seismic datasets show that the proposed method obtains promising results.

Fast alternating direction method of multipliers for total-variation-based image restoration

A novel algorithm, i.e. the fast alternating direction method of multipliers （ADMM）, is applied to solve the classical total-variation （ TV ）-based model for image reconstruction. First, the TV-based model is reformulated as a linear equality constrained problem where the objective function is separable. Then, by introducing the augmented Lagrangian function, the two variables are alternatively minimized by the Gauss-Seidel idea. Finally, the dual variable is updated. Because the approach makes full use of the special structure of the problem and decomposes the original problem into several low-dimensional sub-problems, the per iteration computational complexity of the approach is dominated by two fast Fourier transforms. Elementary experimental results indicate that the proposed approach is more stable and efficient compared with some state-of-the-art algorithms.

BLIND ADAPTIVE XPIC BASED ON HOS

This paper presents a new blind XPIC and a new adaptive blind deconvolutional algorithm based on HOS processing, which separates and equalizes the signals in real time. The simulation results demonstrate that the performance of the proposed adaptive blind algorithm,compared with the conventional algorithms, is outstanding with the feature of feasibility, stability and fast convergence rate.