PSNR Research Articles

A novel parabolic model driven by double phase flux operator with variable exponents: Application to image decomposition and denoising

This work tackles a novel parabolic equation driven by a nonlinear operator with double variable exponents, aiming to decompose and denoise images. Our primary approach involves enhancing classical models based on variable exponent operators by considering a novel nonlinear operator having a double-phase flux with unbalanced growth. We begin initially by analyzing the theoretical solvability of our model. Employing the Musielak-Orlicz space, we establish a suitable functional framework for investigating the proposed model. Subsequently, we use the Faedo-Galerkin approach to establish the existence and uniqueness of a weak solution for our problem. Furthermore, we provide a demonstration showcasing how our model preserves solution positivity, emphasizing this as a consistent feature of the proposed model. To evaluate our theoretical results, we present various numerical simulations on some grayscale and medical images (Magnetic Resonance Images (MRI)). These simulations covered aspects like decomposition, robustness and behavior sensitivity of model parameters with visual and quantitative comparisons. The obtained numerical results strongly support the efficiency of the proposed model in preserving features, reducing artifacts and deleting noise in comparison to some well-known existing state-of-the-art models. Furthermore, the proposed model quantitatively surpasses the competitive models in terms of several well-known criteria, namely the Peak Signal-to-Noise Ratio (PSNR), the Structural Similarity Index (SSIM) and the Mean-Square Error (MSE).

A Comparative Study of Mean Square Error, Dimensions, Signal to Noise Ratio of Colored and Non-Colored Clustered Original Images Along with Compressed Version After the Image Segmentation and Filtering Method

Primarily author has already done one fundamental paper work on image clustering and segmentation but here in this paper author has continued that same type of work on clustered and segmented images as a mode of comparative study for author has chosen three different parameters like mean square error, peak SNR and dimensions of images (length, width, height). The author has all three parametric methods on one particular to justify the comparison. So this paper is a cumulative case of a comparative study for which author has chosen the above mentioned parameters to justify the best results of the clustered and segmented images.

Deep learning approaches for image restoration in invasive coronary angiography

Abstract Background Despite being the gold standard for diagnosing coronary artery disease and guiding percutaneous coronary interventions (PCI), image restoration during invasive coronary angiography (ICA) has rarely been explored. Generative adversarial network (GAN), a deep learning model, has demonstrated its effectiveness in image restoration. Our hypothesis was that we could restore ICA images, damaged or deleted to varying degrees, using the inpainting GAN method, and we undertook efforts to test this hypothesis. Methods We extracted 22,659 ICA patch images (128 × 128 size) from 60 patients, focusing on sparse vessels for model training. To assess our inpainting GAN model, we degraded the extracted images to varying degrees: minimal, mild, moderate, severe, and completely blocked. The performance was quantitatively analyzed using metrics such as the peak signal-to-noise ratio (PSNR), structured similarity indexing methods (SSIM), and mean squared error (MSE). Results The inpainting GAN method significantly improved the image quality in all degraded images. For the blocked images, PSNR and SSIM were enhanced by 161.9% and 14.3%, respectively, with a 98% MSE reduction. In severely, moderately, mildly, and minimally damaged images, PSNR and SSIM increased by 14.9% and 14.8%, 15.7% and 14.7%, 19.3% and 15.6%, and 12.7% and 5.3%, respectively, with MSE reductions of 61.5%, 64.1%, 72.7%, and 33.9%, respectively. Conclusions Inpainting GAN can restore ICA images with varying damage levels, including deletions. Our deep-learning model can instantaneously improve ICA image quality, potentially aiding in emergency or chronic total occlusion PCI.Table 2.Quantitative Analysis of ImageFigure 1.Sample Cases Pre and Post-Rest

Multiple description image coding using Schur transform

A novel obvious and robust image Multiple Description Coding (MDC) using Schur transform (ST)is presented in this work. To overcome the inherent drawbacks in the discrete wavelet transform (DWT)which are the hardware implementation and computational complexityIn the MDC approach, two or more correlated descriptions of the same data aregenerated, which can be independently decoded, and yield mutually refinable information. Therefore, the quality of the recovered signal is dependent only on the number of received descriptions, and not on the specific loss pattern. The new techniquewas analyzed and compared to the conventional approach in the case of four descriptions by using multiple grayscale test images having different spectral characteristics.Theexperimental results of Schur transform (ST) compared to discrete wavelet transform (DWT)show that our method achievesbetter performance in terms of delivered peaksignal to noise ratio (PSNR) and visual image quality reconstruction.The proposed MDC has a low redundancy and outperforms the conventionalscheme for image transmission over error-prone networks.Therefore, the proposed approach provides an easier practical implementation and a better redundancy performancethan the classical approach.

WiTUnet: A U-shaped architecture integrating CNN and Transformer for improved feature alignment and local information fusion

Low-dose computed tomography (LDCT) has emerged as the preferred technology for diagnostic medical imaging due to the potential health risks associated with X-ray radiation and conventional computed tomography (CT) techniques. While LDCT utilizes a lower radiation dose compared to standard CT, it results in increased image noise, which can impair the accuracy of diagnoses. To mitigate this issue, advanced deep learning-based LDCT denoising algorithms have been developed. These primarily utilize Convolutional Neural Networks (CNNs) or Transformer Networks and often employ the Unet architecture, which enhances image detail by integrating feature maps from the encoder and decoder via skip connections. However, existing methods focus excessively on the optimization of the encoder and decoder structures while overlooking potential enhancements to the Unet architecture itself. This oversight can be problematic due to significant differences in feature map characteristics between the encoder and decoder, where simple fusion strategies may hinder effective image reconstruction. In this paper, we introduce WiTUnet, a novel LDCT image denoising method that utilizes nested, dense skip pathway in place of traditional skip connections to improve feature integration. Additionally, to address the high computational demands of conventional Transformers on large images, WiTUnet incorporates a windowed Transformer structure that processes images in smaller, non-overlapping segments, significantly reducing computational load. Moreover, our approach includes a Local Image Perception Enhancement (LiPe) module within both the encoder and decoder to replace the standard multi-layer perceptron (MLP) in Transformers, thereby improving the capture and representation of local image features. Through extensive experimental comparisons, WiTUnet has demonstrated superior performance over existing methods in critical metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Root Mean Square Error (RMSE), significantly enhancing noise removal and image quality. The code is available on github https://github.com/woldier/WiTUNet.

Image Denoising Using Deblur Generative Adversarial Network Denoising U-Net

Convolutional neural networks (CNNs) are becoming increasingly popular for image denoising. U-Nets, a type of CNN architecture, have been shown to be effective for this task. However, the impact of shallow layers on deeper layers decreases as the depth of the network increases. To address this issue, the authors propose a new image denoising method called DGANDU-Net. DGANDU-Net combines the DeblurGAN design with a U-Net architecture. This combination allows DGANDU-Net to effectively remove noise from images while preserving fine details. The authors also propose the use of two loss functions, mean square error (MSE) and perceptual loss, to improve the performance of DGANDU-Net. MSE is used to learn and improve the extracted features, while perceptual loss is used to produce the final denoised image. The authors evaluate the performance of DGANDU-Net on a variety of noise levels and find that it outperforms other state-of-the-art denoising algorithms in terms of both visual quality and two evaluation indices, including peak signal-to-noise ratio (PSNR) and Structural Similarity Index Measure (SSIM). Specifically, for extremely noisy environments with a noise standard deviation of 75, DGANDU-Net achieves an average PSNR of 37.39[Formula: see text]dB in the test dataset. The authors conclude that DGANDU-Net is a promising new method for image denoising that has the potential to significantly improve the quality of medical images used for diagnosis and treatment.

Advancements in Spatial Domain Image Steganography: Techniques, Applications, and Future Outlook

Abstract. Image steganography, a technique for transmitting secret information hidden within images over public networks undetected, serves as a discreet alternative to cryptography in the field of information security. This article explores new steganography techniques based on the Least Significant Bit (LSB) method, widely recognized for its simplicity in embedding secret data by altering the least significant bit of pixels in the spatial domain. The performance of these LSB-based methods is critically assessed using criteria such as Peak Signal-to-Noise Ratio (PSNR), embedding capacity, and histogram analysis. A comprehensive review of recent literature provides a foundation for this evaluation, highlighting advancements and identifying areas for future improvement. Additionally, the article discusses practical applications of LSB-based steganography in healthcare, government operations, and cloud storage, suggesting directions for further research and development in this subtly powerful area of data security.

Physics-Driven Image Dehazing from the Perspective of Unmanned Aerial Vehicles

Drone vision is widely used in change detection, disaster response, and military reconnaissance due to its wide field of view and flexibility. However, under haze and thin cloud conditions, image quality is usually degraded due to atmospheric scattering. This results in issues like color distortion, reduced contrast, and lower clarity, which negatively impact the performance of subsequent advanced visual tasks. To improve the quality of unmanned aerial vehicle (UAV) images, we propose a dehazing method based on calibration of the atmospheric scattering model. We designed two specialized neural network structures to estimate the two unknown parameters in the atmospheric scattering model: the atmospheric light intensity A and medium transmission t. However, calculation errors always occur in both processes for estimating the two unknown parameters. The error accumulation for atmospheric light and medium transmission will cause the deviation in color fidelity and brightness. Therefore, we designed an encoder-decoder structure for irradiance guidance, which not only eliminates error accumulation but also enhances the detail in the restored image, achieving higher-quality dehazing results. Quantitative and qualitative evaluations indicate that our dehazing method outperforms existing techniques, effectively eliminating haze from drone images and significantly enhancing image clarity and quality in hazy conditions. Specifically, the compared experiment on the R100 dataset demonstrates that the proposed method improved the peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM) metrics by 6.9 dB and 0.08 over the second-best method, respectively. On the N100 dataset, the method improved the PSNR and SSIM metrics by 8.7 dB and 0.05 over the second-best method, respectively.

Advancing Electric Engineering Education through Immersive Virtual Reality: Deep Learning and Evolutionary Algorithms for Image Stitching and Rectification in Virtual Lab Environments

Virtual Reality (VR) technology has emerged as a transformative tool in education, offering immersive and interactive experiences that enhance learning outcomes. This paper delves into the application of image stitching and rectification techniques to create a VR lab environment, specifically tailored for electrical engineering education. The importance of VR technology in education is explored, highlighting its role in promoting active learning and providing experiential learning opportunities. The primary emphasis of this Paper lies in the smooth incorporation of image stitching algorithms for the creation of panoramic perspectives, along with the implementation of rectification techniques to correct irregular borders within the stitched images. By utilizing Convolutional Neural Networks (CNNs) and Genetic Algorithms (GAs), the proposed approach optimizes the rectification process, resulting in visually cohesive representations. Demonstrating the utilization of the VR lab across a range of situations, such as examining power transfer and creating control panels for water pumps in irrigation initiatives, the immersive setting enables students to delve into intricate systems. The performance of the proposed method was evaluated using various metrics, including mean squared error, peak signal to noise ratio (PSNR), structural similarity index (SSIM), and Fréchet inception distance (FID). the combination of deep learning algorithm specifically (CNN) and optimization algorithm specifically (Genetic algorithm (GA)) led to an increase in the accuracy of the rectified images where the average PSNR reached 23.98, SSIM was 0.8066, and FID was 18.72. Regarding the users’ opinion about the generated environment by stitching and rectifying images, participants demonstrated consistent positive sentiments, with mean scores ranging from 3.65 to 4.03, all above the scale midpoint, and moderate variability indicated by standard deviation values ranging from 1.070 to 1.251, suggesting general favorability with some variation in responses. This experience empowers the users to gain insights and cultivate essential problemsolving abilities at a heightened level. Collaborative learning is facilitated, enabling students to engage in collaborative projects regardless of their physical location. Through the synthesis of image processing techniques and VR technology, this research contributes to the enrichment of educational experiences and the advancement of electrical engineering education.

Edge segmentation method for Si3N4 bearing rolling elements microcracks with profile-distortion

For the profile-distortion of Si3N4 bearing rolling elements microcracks image. A coupling method of variable-scale truncated median filtering and detection-driven active contour model is proposed. Details are as follows. The sigmoid activation function is constructed to dynamically adjust the circular window. The local threshold truncation is designed to adapt to the characteristics of different regions in the image. The area threshold is defined to eliminate non-target features. The mean peak signal-to-noise ratio (PSNR) of filtered images is about 40.263. The edge overlap rate is as low as 0.1027. The mean accuracy of feature extraction is about 94.33 %. To sum up, the influence result from profile-distortion on the accuracy of feature extraction of Si3N4 bearing rolling elements microcracks is effectively solved.

Millimeter-Wave Radar Clutter Suppression Based on Cycle-Consistency Generative Adversarial Network

Vehicle-mounted millimeter-wave radar is widely used in autonomous driving systems for its ability to observe road scenes at all times and in all weathers. However, the data collected by millimeter-wave radar are seriously affected by the existence of clutter. This clutter will result in false detection during object detection. To address this issue, a feature extraction network with clutter suppression is necessary. This paper proposes a new clutter suppression method for millimeter-wave Range–Angle (RA) images based on a cycle-consistency generative adversarial network (CycleGAN). The generator of the method can be used as the feature extraction network of the object detection. The method aims to convert cluttered images into clutter-free images by unsupervised learning. In this method, an attention gate (AG) is introduced into the generator, a spatial attention mechanism that improves the ability of the model to automatically learn to focus on the features of targets and suppress the clutter of the background. Additionally, the target consistency loss term is added to the loss function to maintain target integrity while suppressing network training overfitting. The public dataset CRUW is utilized to evaluate the performance of the proposed method, which is compared and analyzed with traditional methods and deep learning methods. Experimental results show that the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the proposed method reach 39.846 and 0.990, respectively.

Beam quality measurement and image analysis of RF optical emission system

With the development of radio-over-fiber (ROF), beam quality is also an important parameter in evaluating ROF systems. Therefore, this paper selects the low-frequency to very high frequency (VHF) direct modulated optical emission system to verify its feasibility and excellent performance. It then analyzes the beam quality and image processing. In this paper, MATLAB is selected for the theoretical simulation, then CMOS is used to collect light spots, RayCiV2.5 is used to Gaussian fit the light field intensity distribution, and finally the ideal and actual light spot parameters are compared. Due to the influence of noise, this paper also preprocessed the image by brightness adjustment, filtering, edge fitting, etc. It proposed a fast two-sided filtering algorithm, which obtained a high peak signal-to-noise ratio (PSNR) and strong applicability. The results show that the edge-mode rejection ratio is as high as 33.6 dB, the beam quality is good, and it can be well applied in ROF. The M2 factor is 2.75, the optical field intensity Gaussian fit is 99.8 %, and the signal-to-noise ratio (SNR) is as high as 54.7 dB. Moreover, the image is robust after fast bilateral filtering.

Multi-Source Fusion Enhanced Feature Segmentation in Remote Sensing Imagery

Abstract. With deepening application of deep learning technology in the field of remote sensing, several challenges persist in the segmentation of remote sensing optical images. These challenges include: (1) insufficient availability of deep learning-based remote sensing semantic segmentation datasets; (2) inadequate utilization of multi-source remote sensing data in the field of semantic segmentation; (3) limited sample size for effective model training, as well as the need to enhance both the speed and accuracy of model training. To address these challenges, this study introduces a multi-source remote sensing dataset consisting of 15000 data pairs, each comprising remote sensing multispectral data, synthetic aperture radar(SAR) images, land use and land cover(LULC) data, digital elevation model (DEM) data as well as the analysis data including Slope, Aspect, and Hillshade. Through the application of an end-to-end network based on pix2pix, effective fusion and feature enhancement of multi-source remote sensing data were achieved. The structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and Spectral Angle Mapper(SAM) values reached 0.84, 23.14, and 0.19, respectively, representing significant improvements over the baseline Pix2pix model’s performance metrics of 0.62, 18.84, and 0.23. In downstream semantic segmentation applications, the enhanced dataset was utilized to train semantic segmentation models for remote sensing image analysis. This approach effectively improved the training speed and segmentation accuracy of the models, with the mean intersection over union (mIoU) increasing from 0.467 to 0.481 and accuracy rising from 0.734 to 0.746. Moreover, the visual representation of remote sensing image segmentation demonstrated noticeable enhancements.

A Novel Detection Transformer Framework for Ship Detection in Synthetic Aperture Radar Imagery Using Advanced Feature Fusion and Polarimetric Techniques

Ship detection in synthetic aperture radar (SAR) imagery faces significant challenges due to the limitations of traditional methods, such as convolutional neural network (CNN) and anchor-based matching approaches, which struggle with accurately detecting smaller targets as well as adapting to varying environmental conditions. These methods, relying on either intensity values or single-target characteristics, often fail to enhance the signal-to-clutter ratio (SCR) and are prone to false detections due to environmental factors. To address these issues, a novel framework is introduced that leverages the detection transformer (DETR) model along with advanced feature fusion techniques to enhance ship detection. This feature enhancement DETR (FEDETR) module manages clutter and improves feature extraction through preprocessing techniques such as filtering, denoising, and applying maximum and median pooling with various kernel sizes. Furthermore, it combines metrics like the line spread function (LSF), peak signal-to-noise ratio (PSNR), and F1 score to predict optimal pooling configurations and thus enhance edge sharpness, image fidelity, and detection accuracy. Complementing this, the weighted feature fusion (WFF) module integrates polarimetric SAR (PolSAR) methods such as Pauli decomposition, coherence matrix analysis, and feature volume and helix scattering (Fvh) components decomposition, along with FEDETR attention maps, to provide detailed radar scattering insights that enhance ship response characterization. Finally, by integrating wave polarization properties, the ability to distinguish and characterize targets is augmented, thereby improving SCR and facilitating the detection of weakly scattered targets in SAR imagery. Overall, this new framework significantly boosts DETR’s performance, offering a robust solution for maritime surveillance and security.

Image Stitching of Low-Resolution Retinography Using Fundus Blur Filter and Homography Convolutional Neural Network

Great advances in stitching high-quality retinal images have been made in recent years. On the other hand, very few studies have been carried out on low-resolution retinal imaging. This work investigates the challenges of low-resolution retinal images obtained by the D-EYE smartphone-based fundus camera. The proposed method uses homography estimation to register and stitch low-quality retinal images into a cohesive mosaic. First, a Siamese neural network extracts features from a pair of images, after which the correlation of their feature maps is computed. This correlation map is fed through four independent CNNs to estimate the homography parameters, each specializing in different corner coordinates. Our model was trained on a synthetic dataset generated from the Microsoft Common Objects in Context (MSCOCO) dataset; this work added an important data augmentation phase to improve the quality of the model. Then, the same is evaluated on the FIRE retina and D-EYE datasets for performance measurement using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The obtained results are promising: the average PSNR was 26.14 dB, with an SSIM of 0.96 on the D-EYE dataset. Compared to the method that uses a single neural network for homography calculations, our approach improves the PSNR by 7.96 dB and achieves a 7.86% higher SSIM score.

Secure and Robust Dual Watermarking for Western Blot Images

The rapid growth of digital data sharing has created a pressing need to safeguard the integrity, authenticity, and security of bioanalytical images, such as Western blots, online. To address this challenge, we propose a novel hybrid biometric watermarking technique that combines randomised singular value decomposition (RSVD), discrete wavelet transform (DWT), schur transform, pseudo magic cube, and chaotic encryption, making the watermarking of Western blot images more secure, robust, and imperceptible. Our approach surpasses state-of-the-art methods, ensuring imperceptible watermarking and robust protection against tampering and unauthorised use. By integrating spatial and transform-domain techniques, we achieve superior performance, outperforming existing methods with a peak signal-to-noise ratio (PSNR) of 48.7581, structural similarity index (SSIM) of 0.9998, a normalised correlation (NC) of 0.9996, an average number of changing pixel rate (NPCR) of 0.9961, and an average unified average changing intensity (UACI) of 0.3334. Our technique sets a new standard for digital image protection in scientific research, addressing critical challenges in tampering, copyright protection, and data security. With its high performance and security, our approach enables the trustworthy sharing and publication of Western blot images in the digital era.

Visual Communication Method of Multi-Frame Film and Television Special Effects Images Based on Deep Learning

In the view of art form change, there is a perspective problem in the detail part of multi-frame film and television special effects (TSEs) images in the special effects rendering module, which leads to the greater ambiguity of multi-frame film and TSEs images. In order to advance the talent of identifying the detail structures and characteristics of multi-frame film and TSEs images, a visual communication technology of multi-frame film and TSEs images in the view of art form change grounded on deep learning is suggested. The transmission relation model of detail characteristics of multi-frame film and TSEs images in the field of artistic form change is constructed, and the attenuation treatment of detail action special effects of multi-frame film and TSEs images in the field of artistic form change is carried out with the assistance of deep learning approaches. The detailed information and color of multi-frame film and TSEs images are obtained by using prior map knowledge instead of rendering basic color. Over the technique of filtering and preserving, the multi-frame film and TSEs images are directed to screen the detailed feature quantity of the input film and TSEs images in the field of artistic form change. In addition, the Sobel operator is practiced to perceive the scrawny edge information of multi-frame film and TSEs images, and block fitting interpolation and depth filtering analysis are used in the edge area to realize the visual communication and color feature parameter identification and amplification of multi-frame film and TSEs images in the field of artistic form change, so as to improve the fuzzy enhancement of multi-frame film and TSEs images. The test results and results indicate that the average Peak signal-to-noise ratio (PSNR) of the proposed method is about 37.7166[Formula: see text]dB, which is 49.08% and 52.08% higher than the PSNRs of the Harris method and SUFR method, respectively. It has been confirmed that this scheme can successfully solve the edge blurring and distortion problems of multi-frame movies and image images in the field of art form change.

Unsupervised Denoising in Spectral CT: Multi-Dimensional U-Net for Energy Channel Regularisation

Spectral Computed Tomography (CT) is a versatile imaging technique widely utilized in industry, medicine, and scientific research. This technique allows us to observe the energy-dependent X-ray attenuation throughout an object by using Photon Counting Detector (PCD) technology. However, a major drawback of spectral CT is the increase in noise due to a lower achievable photon count when using more energy channels. This challenge often complicates quantitative material identification, which is a major application of the technology. In this study, we investigate the Noise2Inverse image denoising approach for noise removal in spectral computed tomography. Our unsupervised deep learning-based model uses a multi-dimensional U-Net paired with a block-based training approach modified for additional energy-channel regularization. We conducted experiments using two simulated spectral CT phantoms, each with a unique shape and material composition, and a real scan of a biological sample containing a characteristic K-edge. orangeMeasuring the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) for the simulated data and the contrast-to-noise ratio (CNR) for the real-world data, our approach not only outperforms previously used methods—namely the unsupervised Low2High method and the total variation-constrained iterative reconstruction method—but also does not require complex parameter tuning.

Quantum color image watermarking scheme based on quantum discrete cosine transform

Quantum watermarking is a technique that embeds specific information into a quantum carrier, used for digital copyright protection. This paper introduces a new quantum color image watermarking method that combines Quantum LOG (QLOG) edge detection with Quantum Discrete Cosine Transform (QDCT) technology. First, edge detection is used on the RGB channels of the quantum color image. This helps identify the best channel for embedding the watermark. Next, the image is decomposed using the quantum Haar wavelet transform (QHWT). The image is then processed with QDCT, selecting the mid-frequency parts for watermark embedding. Using QDCT improves the watermark’s resistance to JPEG compression. The invisibility of the watermark is verified by assessing its Peak Signal-to-Noise Ratio (PSNR) and histogram. Comparative analysis shows strong resistance to various noise attacks. Simulation results confirm that the watermarking technique maintains high visual quality and resists different adversarial attacks.

Dimensionality Reduction for the Real-Time Light-Field View Synthesis of Kernel-Based Models

Several frameworks have been proposed for delivering interactive, panoramic, camera-captured, six-degrees-of-freedom video content. However, it remains unclear which framework will meet all requirements the best. In this work, we focus on a Steered Mixture of Experts (SMoE) for 4D planar light fields, which is a kernel-based representation. For SMoE to be viable in interactive light-field experiences, real-time view synthesis is crucial yet unsolved. This paper presents two key contributions: a mathematical derivation of a view-specific, intrinsically 2D model from the original 4D light field model and a GPU graphics pipeline that synthesizes these viewpoints in real time. Configuring the proposed GPU implementation for high accuracy, a frequency of 180 to 290 Hz at a resolution of 2048×2048 pixels on an NVIDIA RTX 2080Ti is achieved. Compared to NVIDIA’s instant-ngp Neural Radiance Fields (NeRFs) with the default configuration, our light field rendering technique is 42 to 597 times faster. Additionally, allowing near-imperceptible artifacts in the reconstruction process can further increase speed by 40%. A first-order Taylor approximation causes imperfect views with peak signal-to-noise ratio (PSNR) scores between 45 dB and 63 dB compared to the reference implementation. In conclusion, we present an efficient algorithm for synthesizing 2D views at arbitrary viewpoints from 4D planar light-field SMoE models, enabling real-time, interactive, and high-quality light-field rendering within the SMoE framework.