Discriminative Network Research Articles

Radiomics‐guided generative adversarial network for automatic primary target volume segmentation for nasopharyngeal carcinoma using computed tomography images

AbstractBackgroundAutomatic primary gross tumor volume (GTVp) segmentation for nasopharyngeal carcinoma (NPC) is a quite challenging task because of the existence of similar visual characteristics between tumors and their surroundings, especially on computed tomography (CT) images with severe low contrast resolution. Therefore, most recently proposed methods based on radiomics or deep learning (DL) is difficult to achieve good results on CT datasets.PurposeA peritumoral radiomics‐guided generative adversarial network (PRG‐GAN) was proposed to address this challenge.MethodsA total of 157 NPC patients with CT images was collected and divided into training, validation, and testing cohorts of 108, 9, and 30 patients, respectively. The proposed model was based on a standard GAN consisting of a generator network and a discriminator network. Morphological dilation on the initial segmentation results from GAN was first conducted to delineate annular peritumoral region, in which radiomics features were extracted as priori guide knowledge. Then, radiomics features were fused with semantic features by the discriminator's fully connected layer to achieve the voxel‐level classification and segmentation. The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average symmetric surface distance (ASSD) were used to evaluate the segmentation performance using a paired samples t‐test with Bonferroni correction and Cohen's d (d) effect sizes. A two‐sided p‐value of less than 0.05 was considered statistically significant.ResultsThe model‐generated predictions had a high overlap ratio with the ground truth. The average DSC, HD95, and ASSD were significantly improved from 0.80 ± 0.12, 4.65 ± 4.71 mm, and 1.35 ± 1.15 mm of GAN to 0.85 ± 0.18 (p = 0.001, d = 0.71), 4.15 ± 7.56 mm (p = 0.002, d = 0.67), and 1.11 ± 1.65 mm (p < 0.001, d = 0.46) of PRG‐GAN, respectively.ConclusionIntegrating radiomics features into GAN is promising to solve unclear border limitations and increase the delineation accuracy of GTVp for patients with NPC.

Multi-Head Attention Affinity Diversity Sharing Network for Facial Expression Recognition

Facial expressions exhibit inherent similarities, variability, and complexity. In real-world scenarios, challenges such as partial occlusions, illumination changes, and individual differences further complicate the task of facial expression recognition (FER). To further improve the accuracy of FER, a Multi-head Attention Affinity and Diversity Sharing Network (MAADS) is proposed in this paper. MAADS comprises a Feature Discrimination Network (FDN), an Attention Distraction Network (ADN), and a Shared Fusion Network (SFN). To be specific, FDN first integrates attention weights into the objective function to capture the most discriminative features by using the proposed sparse affinity loss. Then, ADN employs multiple parallel attention networks to maximize diversity within spatial attention units and channel attention units, which guides the network to focus on distinct, non-overlapping facial regions. Finally, SFN deconstructs facial features into generic parts and unique parts, which allows the network to learn the distinctions between these features without having to relearn complete features from scratch. To validate the effectiveness of the proposed method, extensive experiments were conducted on several widely used in-the-wild datasets including RAF-DB, AffectNet-7, AffectNet-8, FERPlus, and SFEW. MAADS achieves the accuracy of 92.93%, 67.14%, 64.55%, 91.58%, and 62.41% on these datasets, respectively. The experimental results indicate that MAADS not only outperforms current state-of-the-art methods in recognition accuracy but also has a relatively low computational complexity.

Artificial Intelligence-Based Segmentation and Classification of Plant Images with Missing Parts and Fractal Dimension Estimation

Existing research on image-based plant classification has demonstrated high performance using artificial intelligence algorithms. However, limited camera viewing angles can cause parts of the plant to be invisible in the acquired images, leading to an inaccurate classification. However, this issue has not been addressed by previous research. Hence, our study aims to introduce a method to improve classification performance by taking these limitations into account; specifically, we incorporated both segmentation and classification networks structured as shallow networks to expedite the processing times. The proposed shallow plant segmentation network (Shal-PSN) performs adversarial learning based on a discriminator network; and a shallow plant classification network (Shal-PCN) with applied residual connections was also implemented. Moreover, the fractal dimension estimation is used in this study for analyzing the segmentation results. Additionally, this study evaluated the performance of the proposed Shal-PSN that achieved the dice scores (DSs) of 87.43% and 85.71% with PlantVillage and open leaf image (OLID-I) open datasets, respectively, in instances where 40–60% of plant parts were missing. Moreover, the results demonstrate that the proposed method increased the classification accuracy from 41.16% to 90.51% in the same instances. Overall, our approach achieved superior performance compared to the existing state-of-the-art classification methods.

Advancements in Multi-Modal Face Recognition: A State-of-the-Art Review of Security Biometrics

This survey is a state-of-the-art review of recent advancements in face recognition, particularly multi-modal face recognition and its associated applications in the domain of security biometrics and identity verification. In this regard, the paper sheds light on the significance of the Sejong Face database and several other leading databases as equally significant tools in studying some of the most challenging tasks in face recognition: occluded and diverse face identification, cross-modality evaluation, and infrared-visible face detection. It also insists on the high challenge of face identification across scenarios and with different forms of disguise. In addition, it emphasizes the need for an effective security framework to be implemented with other major sectors that deal in finances. The purpose is to develop an exhaustive list of methodologies and innovations based on the Sejong Face Database with the intention of finding new methods and algorithms that guarantee accuracy and reliability. Specifically, the application of deep learning methods comprising convolutional neural networks with cross-modality discriminator networks and unit-class loss demonstrates significant advancements in the development of face recognition systems; consequently, these systems exhibit enhanced security and efficacy. The review article is an important source that points out the current status of the research, as well as future possibilities, regarding biometric authentication and its implications in the digital scenario.

An integrated three-stream network model for discriminating fish feeding intensity using multi-feature analysis and deep learning.

Feed costs constitute a significant part of the expenses in the aquaculture industry. However, feeding practices in fish farming often rely on the breeder's experience, leading to feed wastage and environmental pollution. To achieve precision in feeding, it is crucial to adjust the feed according to the fish's feeding state. Existing computer vision-based methods for assessing feeding intensity are limited by their dependence on a single spatial feature and manual threshold setting for determining feeding status constraints. These models lack practicality due to their specificity to certain scenarios and objectives. To address these limitations, we propose an integrated approach that combines computer vision technology with a Convolutional Neural Net-work (CNN) to assess the feeding intensity of farmed fish. Our method incorporates temporal, spatial, and data statistical features to provide a comprehensive evaluation of feeding intensity. Using computer vision techniques, we preprocessed feeding images of pearl gentian grouper, extracting temporal features through optical flow, spatial features via binarization, and statistical features using the gray-level co-occurrence matrix. These features are input into their respective specific feature discrimination networks, and the classification results of the three networks are fused to construct a three-stream network for feeding intensity discrimination. The results of our proposed three-stream network achieved an impressive accuracy of 99.3% in distinguishing feeding intensity. The model accurately categorizes feeding states into none, weak, and strong, providing a scientific basis for intelligent fish feeding in aquaculture. This advancement holds promise for promoting sustainable industry development by minimizing feed wastage and optimizing environmental impact.

Structural topology optimization based on deep learning

In the mechanical design of structures, traditional topology optimization methods involve numerous finite element iterative analyses, leading to a significant expenditure of computational resources. Therefore, the improved multi-scale gradient generative adversarial networks topology optimization technique is proposed. The topology optimization condition parameters are compressed into a low-dimensional latent space feature representation using the encoder, allowing the model to better extract features from these parameters. To speed up model training, the generator and discriminator networks use lightweight residual convolutional blocks. The hybrid attention mechanism extracts prominent region features from the topology optimization structure map. The model training process is guided by a multi-dimensional fusion loss function to enhance the quality of generated model samples. Finally, transferring the parameters of the low-resolution topology optimization model to the high-resolution model enables complete training on a limited amount of high-resolution topology optimization datasets. The experimental data on the low- and high-resolution topology optimization datasets demonstrate that, when compared to alternative methods, this method produces better-quality topology optimization structure maps. Additionally, it can generate high-resolution topology optimization structure maps in minimal time, enabling real-time topology optimization.

TrafficPro: A road speed prediction framework for urban signal-controlled road networks

In view of the problem that traditional deep learning models do not consider the active time-varying characteristics of traffic flow (signal control information) when predicting the speed of urban road networks, and have low prediction accuracy, this paper proposes a speed prediction framework based on generative adversarial networks and graph neural networks. In this framework, the generator network simultaneously encodes the road network traffic flow and signal control information through active and passive prediction modules to generate prediction results, and then uses the discriminator network to improve the generalization of the prediction results. This framework can obtain higher prediction accuracy than traditional time series models and deep learning models. In the real road network speed prediction scenario, this framework can reduce the prediction error compared to the best benchmark model 3%-4%.

Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image Watermarking

With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope with evolving deepfake generation technology and are susceptible to adversarial attacks. Alternatively, invisible image watermarking is being researched as a proactive defense technique that allows media authentication by verifying an invisible secret message embedded in the image pixels. A handful of invisible image watermarking techniques introduced for media authentication have proven vulnerable to basic image processing operations and watermark removal attacks. In response, we have proposed a semi-fragile image watermarking technique that embeds an invisible secret message into real images for media authentication. Our proposed watermarking framework is designed to be fragile to facial manipulations or tampering while being robust to benign image-processing operations and watermark removal attacks. This is facilitated through a unique architecture of our proposed technique consisting of critic and adversarial networks that enforce high image quality and resiliency to watermark removal efforts, respectively, along with the backbone encoder-decoder and the discriminator networks. This allows images shared over the Internet to retain the verifiable watermark as long as facial manipulations or any other Deepfake modification technique is not applied. Thorough experimental investigations on SOTA facial Deepfake datasets demonstrate that our proposed model can embed a \(64\) -bit secret as an imperceptible image watermark that can be recovered with a high-bit recovery accuracy when benign image processing operations are applied while being non-recoverable when unseen Deepfake manipulations are applied. In addition, our proposed watermarking technique demonstrates high resilience to several white-box and black-box watermark removal attacks. Thus, obtaining state-of-the-art performance.

Faceify- Human Face Sketch to Real

The Human Face Sketch to Real Image Application using deep learning presents the development of an innovative application designed to convert human face sketches into realistic image using advanced deep learning techniques. The primary objective of this research is to bridge the gap between manual sketching and digital realism, offering a powerful tool for artists, law enforcement, and digital content creators. The proposed system leverages generative adversarial networks (GANs), particularly a variant known as the Sketch-to-Image GAN (SI-GAN), which is optimizes for translating sparse and abstract sketch lines into high-fidelity facial representations. The architecture consists of a generator network that refines sketches into realistic images, and a discriminator network that distinguishes between generated images and real photographs, continuously enhancing the model’s output. To ensure high accuracy and detail preservation, the model is trained on a diverse dataset comprising thousands of paired sketch and real face images. Advanced techniques such as attention mechanisms and multi-scale feature extraction are incorporated to maintain the integrity of facial features and textures. Additionally, a user friendly interface has been developed, allowing users to input sketches and receive high-quality realistic images in real-time. Evaluation metrics, including structural similarity index (SSIM) and Frechet Inception Distance (FID), Indicate that the proposed model outperforms existing state-of-the-art methods in both quality and realism. Keywords: Image Translation, Conditional Generative Adversarial Networks (CGANs), Deep Learning, Mobile Application Development, Backend Integration, Face Sketch, Photorealistic Image.

HcGAN: Harmonic conditional generative adversarial network for efficiently generating high-quality IHC images from H&E

Generating high quality histopathology images like immunohistochemistry (IHC) stained images is essential for precise diagnosis and the advancement of computer-aided diagnostic (CAD) systems. Producing IHC images in laboratory is quite expensive and time consuming. Recently, some attempts have been made based on artificial intelligence techniques (particularly, deep learning) to generate IHC images. Existing IHC stained image generation methods, still have a limited performance due to the complex structures and variations in cells shapes, potential nonspecific staining and variable antibody sensitivity. This paper proposes a novel technique known as harmonic conditional generative adversarial network (HcGAN) for generating high quality IHC-stained images. To generate the IHC images, the HcGAN model is fed with the widely available hematoxylin and eosin (H&E) images that contain cellular and morphological underlying structures of diverse cancer tissues. Such approach helps generate high quality IHC images mimicking the real ones that highlight the positive cells. The proposed HcGAN model is based generative adversarial learning with generator and discriminator networks. In HcGAN, harmonic convolution based on discrete cosine transform filter banks is employed in the generator and discriminator networks instead of the standard convolution in order to improve visual quality of the generated images and address the issue of overfitting. Our qualitative and quantitative results demonstrate that the proposed HcGAN achieved the highest performance over state-of-the-art methods using two publicly available datasets.

Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control

ABSTRACTSignificant advancements have been made in the field of humanoid robot, particularly in walking control strategies. However, achieving straight‐legged walking remains a challenge. Both the traditional model‐based and the learning‐based control methods confront with difficulties in achieving natural humanoid gait feature. To address this issue, a general motion retargeting method is developed and also evaluated for humanoid robots with different structure, size and degrees of freedom. Moreover, a conditional adversarial motion priors method is proposed based on reinforcement learning and validated on the humanoid robot GTX‐III. Through various motion segments from the motion capture database, it is shown that this method can successfully enable the humanoid robot to perform straight‐legged walking with flexible and natural transitions between different gaits within a single discriminator network.

Modulation Format Recognition Scheme Based on Discriminant Network in Coherent Optical Communication System

In this paper, we skillfully utilize the discriminative ability of the discriminator to construct a conditional generative adversarial network, and propose a scheme that uses few symbols to achieve high accuracy recognition of modulation formats under low signal-to-noise ratio conditions in coherent optical communication. In the one thousand kilometres G.654E optical fiber transmission system, transmission experiments are conducted on the PDM-QPSK/-8PSK/-16QAM/-32QAM/-64QAM modulation format at 8G/16G/32G baud rates, and the signal-to-noise ratio parameters are traversed under experimental conditions. As a key technology in the next-generation elastic optical networks, the modulation format recognition scheme proposed in this paper achieves 100% recognition of the above five modulation formats without distinguishing signal transmission rates. The optical signal-to-noise ratio thresholds required to achieve 100% recognition accuracy are 12.4 dB, 14.3 dB, 15.4 dB, 16.2 dB, and 17.3 dB, respectively.

The Development of an Automated Approach for Designing Quantum Algorithms Using Circuits Generated By Generative Adversarial Networks (Gans)

The advent of quantum computing has inaugurated a novel epoch of computational prowess, offering the potential to tackle intricate problems with unparalleled speed (Zoufal et al., 2019). Quantum circuits, which are essential components of quantum computation, serve as representations of sequences of quantum gates designed for specific quantum processes (Zoufal et al., 2019). Nevertheless, the task of creating efficient quantum circuits continues to be a formidable and labor-intensive undertaking. This research proposal presents a unique methodology that utilizes Generative Adversarial Networks (GANs) to automate the process of generating quantum circuits that are specifically designed for particular quantum gates and operations (Zoufal et al., 2019). The main goal of this study is to create a model based on Generative Adversarial Networks (GANs) that can generate quantum circuits by leveraging the collaborative efforts of the generator and discriminator networks (Zoufal et al., 2019). The GAN model will be trained using a carefully selected dataset that includes established quantum circuits and their corresponding required quantum operations (Zoufal et al., 2019). This dataset will form the basis for the training process. Following this, the quantum circuits that are produced will be thoroughly assessed in terms of fidelity, efficiency, and resource allocation (Zoufal et al., 2019). Additionally, the objective of this work is to refine and optimize the circuits that are formed by employing reinforcement learning and gradient-based techniques (Zoufal et al., 2019). In addition to investigating circuit production, this research will delve into the practical implications and consequences of quantum circuits formed by Generative Adversarial Networks (GANs) on the development of quantum algorithms (Zoufal et al., 2019). The study's value is in its capacity to accelerate the creation of quantum algorithms through the automation of circuit design (Zoufal et al., 2019). This research makes a valuable contribution to the field of quantum computing by improving the efficiency and resource utilization of quantum circuits (Zoufal et al., 2019). These developments are crucial for the development of practical quantum computing applications and will play a significant role in the evolution of quantum algorithms and processing capabilities in the future (Zoufal et al., 2019).

MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks

In applications such as satellite remote sensing and aerial photography, imaging equipment must capture brightness information of different ground scenes within a restricted dynamic range. Due to camera sensor limitations, captured images can represent only a portion of such information, which results in lower resolution and lower dynamic range compared with real scenes. Image super resolution (SR) and multiple-exposure image fusion (MEF) are commonly employed technologies to address these issues. Nonetheless, these two problems are often researched in separate directions. In this paper, we propose MEFSR-GAN: an end-to-end framework based on generative adversarial networks that simultaneously combines super-resolution and multiple-exposure fusion. MEFSR-GAN includes a generator and two discriminators. The generator network consists of two parallel sub-networks for under-exposure and over-exposure, each containing a feature extraction block (FEB), a super-resolution block (SRB), and several multiple-exposure feedback blocks (MEFBs). It processes low-resolution under- and over-exposed images to produce high-resolution high dynamic range (HDR) images. These images are evaluated by two discriminator networks, driving the generator to generate realistic high-resolution HDR outputs through multi-goal training. Extensive qualitative and quantitative experiments were conducted on the SICE dataset, yielding a PSNR of 24.821 and an SSIM of 0.896 for 2× upscaling. These results demonstrate that MEFSR-GAN outperforms existing methods in terms of both visual effects and objective evaluation metrics, thereby establishing itself as a state-of-the-art technology.

Data Augmentation in Histopathological Classification: An Analysis Exploring GANs with XAI and Vision Transformers

Generative adversarial networks (GANs) create images by pitting a generator (G) against a discriminator (D) network, aiming to find a balance between the networks. However, achieving this balance is difficult because G is trained based on just one value representing D’s prediction, and only D can access image features. We introduce a novel approach for training GANs using explainable artificial intelligence (XAI) to enhance the quality and diversity of generated images in histopathological datasets. We leverage XAI to extract feature information from D and incorporate it into G via the loss function, a unique strategy not previously explored in this context. We demonstrate that this approach enriches the training with relevant information and promotes improved quality and more variability in the artificial images, decreasing the FID by up to 32.7% compared to traditional methods. In the data augmentation task, these images improve the classification accuracy of Transformer models by up to 3.81% compared to models without data augmentation and up to 3.01% compared to traditional GAN data augmentation. The Saliency method provides G with the most informative feature information. Overall, our work highlights the potential of XAI for enhancing GAN training and suggests avenues for further exploration in this field.

A simplified adversarial architecture for cross-subject silent speech recognition using electromyography

Objective. The decline in the performance of electromyography (EMG)-based silent speech recognition is widely attributed to disparities in speech patterns, articulation habits, and individual physiology among speakers. Feature alignment by learning a discriminative network that resolves domain offsets across speakers is an effective method to address this problem. The prevailing adversarial network with a branching discriminator specializing in domain discrimination renders insufficiently direct contribution to categorical predictions of the classifier.Approach. To this end, we propose a simplified discrepancy-based adversarial network with a streamlined end-to-end structure for EMG-based cross-subject silent speech recognition. Highly aligned features across subjects are obtained by introducing a Nuclear-norm Wasserstein discrepancy metric on the back end of the classification network, which could be utilized for both classification and domain discrimination. Given the low-level and implicitly noisy nature of myoelectric signals, we devise a cascaded adaptive rectification network as the front-end feature extraction network, adaptively reshaping the intermediate feature map with automatically learnable channel-wise thresholds. The resulting features effectively filter out domain-specific information between subjects while retaining domain-invariant features critical for cross-subject recognition.Main results. A series of sentence-level classification experiments with 100 Chinese sentences demonstrate the efficacy of our method, achieving an average accuracy of 89.46% tested on 40 new subjects by training with data from 60 subjects. Especially, our method achieves a remarkable 10.07% improvement compared to the state-of-the-art model when tested on 10 new subjects with 20 subjects employed for training, surpassing its result even with three times training subjects.Significance. Our study demonstrates an improved classification performance of the proposed adversarial architecture using cross-subject myoelectric signals, providing a promising prospect for EMG-based speech interactive application.

JOA‐GAN: An improved single‐image super‐resolution network for remote sensing based on GAN

AbstractImage super‐resolution (SR) has been widely applied in remote sensing to generate high‐resolution (HR) images without increasing hardware costs. However, SR is a severe ill‐posed problem. As deep learning advances, existing methods have solved this problem to a certain extent. However, the complex spatial distribution of remote sensing images still poses a challenge in effectively extracting abundant high‐frequency details from the images. Here, a single‐image super‐resolution (SISR) network based on the generative adversarial network (GAN) for remote sensing is presented, called JOA‐GAN. Firstly, a joint‐attention module (JOA) is proposed to focus the network on high‐frequency regions in remote sensing images to enhance the quality of image reconstruction. In the generator network, a multi‐scale densely connected feature extraction block (ERRDB) is proposed, which acquires features at different scales using MSconv blocks containing multi‐scale convolutions and automatically adjusts the features by JOA. In the discriminator network, the relative discriminator is used to compute the relative probability instead of the absolute probability, which helps the network learn clearer and more realistic texture details. JOA‐GAN is compared with other advanced methods, and the results demonstrate that JOA‐GAN has improved objective evaluation metrics and achieved superior visual effects.

CAS‐GAN: A Novel Generative Adversarial Network‐Based Architecture for Coronary Artery Segmentation

ABSTRACTAccurate and automated segmentation of x‐ray coronary angiography (XRCA) is crucial for both diagnosing and treating coronary artery diseases. Despite the outstanding results achieved by deep learning (DL)‐based methods in this area, this task remains challenging due to several factors such as poor image quality, the presence of motion artifacts, and inherent variability in vessel structure sizes. To address this challenge, this paper introduces a novel GAN‐based architecture for coronary artery segmentation using XRCA images. This architecture includes a novel U‐Net variant with two types of self‐attention blocks in the generator segment. An auxiliary path connects the attention block and the prediction block to enhance feature generalization, improving vessel structure delineation, especially thin vessels in low‐contrast regions. In parallel, the discriminator network employs a residual CNN with similar attention blocks for balanced performance and improved predictive capabilities. With a streamlined 6.74 M parameters, the resulting architecture surpasses existing methods in efficiency. We assess its efficacy on three coronary artery datasets: our private “CORONAR,” and the public “DCA1” and “CHUAC” datasets. Empirical results showcase our model's superiority across these datasets, utilizing both original and preprocessed images. Notably, our proposed architecture achieves the highest F1‐score of 0.7972 for the CHUAC dataset, 0.8245 for the DCA1 dataset, and 0.8333 for the CORONAR dataset.

A novel image semantic communication method via dynamic decision generation network and generative adversarial network

Effectively compressing transmitted images and reducing the distortion of reconstructed images are challenges in image semantic communication. This paper proposes a novel image semantic communication model that integrates a dynamic decision generation network and a generative adversarial network to address these challenges as efficiently as possible. At the transmitter, features are extracted and selected based on the channel’s signal-to-noise ratio (SNR) using semantic encoding and a dynamic decision generation network. This semantic approach can effectively compress transmitted images, thereby reducing communication traffic. At the receiver, the generator/decoder collaborates with the discriminator network, enhancing image reconstruction quality through adversarial and perceptual losses. The experimental results on the CIFAR-10 dataset demonstrate that our scheme achieves a peak SNR of 26 dB, a structural similarity of 0.9, and a compression ratio (CR) of 81.5% in an AWGN channel with an SNR of 3 dB. Similarly, in the Rayleigh fading channel, the peak SNR is 23 dB, structural similarity is 0.8, and the CR is 80.5%. The learned perceptual image patch similarity in both channels is below 0.008. These experiments thoroughly demonstrate that the proposed semantic communication is a superior deep learning-based joint source-channel coding method, offering a high CR and low distortion of reconstructed images.

Learning-Based Super-Resolution Imaging of Turbulent Flames in Both Time and 3D Space Using Double GAN Architectures

This article presents a spatiotemporal super-resolution (SR) reconstruction model for two common flame types, a swirling and then a jet flame, using double generative adversarial network (GAN) architectures. The approach develops two sets of generator and discriminator networks to learn topographic and temporal features and infer high spatiotemporal resolution turbulent flame structure from supplied low-resolution counterparts at two time points. In this work, numerically simulated 3D turbulent swirling and jet flame structures were used as training data to update the model parameters of the GAN networks. The effectiveness of our model was then thoroughly evaluated in comparison to other traditional interpolation methods. An upscaling factor of 2 in space, which corresponded to an 8-fold increase in the total voxel number and a double time frame acceleration, was used to verify the model’s ability on a swirling flame. The results demonstrate that the assessment metrics, peak signal-to-noise ratio (PSNR), overall error (ER), and structural similarity index (SSIM), with average values of 35.27 dB, 1.7%, and 0.985, respectively, in the spatiotemporal SR results, can reach acceptable accuracy. As a second verification to highlight the present model’s potential universal applicability to flame data of diverse types and shapes, we applied the model to a turbulent jet flame and had equal success. This work provides a different method for acquiring high-resolution 3D structure and further boosting repeat rate, demonstrating the potential of deep learning technology for combustion diagnosis.