Jul 2026· 2026 International Conference on Emerging Trends in Information, Communication & Systems (ICETICS)· pp. 1-6· 0 citations· 15 references
Abstract
Astronomical images captured using Space based or Ground based telescopes are majorly in grayscale, hiding the minute details of the intricate structures. Our paper presents a novel idea of the implementation of a Generative Adversarial Network (GAN) - based framework for astronomical image colorization. Our proposed model utilizes a U-Net-based generator and a PatchGAN discriminator to learn realistic color schemes from the grayscale input. The system was trained on the Hubble Space Telescope data set collected from NASA and ESA archives, comprising 673 high-resolution images, with an additional 99 images reserved for testing. The images are restricted to a resolution of 512 x 512 pixels due to computational limitations. Quantitative evaluation demonstrates that our proposed framework achieves an average Peak Signal-to-Noise Ratio (PSNR) of 31.46 dB, Structural Similarity Index Measure (SSIM) of 0.92, and Signal-to-Noise Ratio (SNR) of 26.85 dB which outperforms traditional approaches. The experimental results confirm that the model produces perceptually accurate, visually coherent, and scientifically meaningful and colorized outputs which contribute to enhanced visualization and analysis of astronomical data.
Overall, GenPix provides a challenging and realistic benchmark for evaluating modern detectors, and the proposed AAE offers an efficient, interpretable baseline for future research on general-purpose fake-image detection.
Guessoum Dalila, B. Nadjia, Boumahdi Fatima et al.· Iraqi Journal for Computer S...· 0 citations
In recent years, deep learning has become a fundamental technology across a wide array of scientific and industrial fields, largely fuelled by advances in computational capabilities. One area that has experienced substantial progress is face hallucination—the task of improving the resolution of facial images. This process is critical to various computer vision applications, including facial recognition, feature extraction, and identity verification. Recently, deep generative models, particularly Generative Adversarial Networks (GANs), have led the field. Although these models have produced remarkable results, there is still a pressing need to further improve both accuracy and output quality. In order to address these problems, we propose a new GAN-based face hallucination method. This method is primarily based on the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN). We present a personalised adaptation of ESRGAN that employs the VGG16 architecture with a compact pre-trained version. This method balances output image quality and computational efficiency. Experiments show that our approach is effective. The improved model obtains a maximum peak signal-to-noise ratio (PSNR) of 30.30. The Learned Perceptual Image Patch Similarity (LPIPS) score is 0.0817, whereas the Structural Similarity Index Measure (SSIM) is 0.8757. The results surpass many state-of-the-art methods available today. These enhancements have a significant impact and importance.
Sheetal S. Patil, A.M. Pawar, Nilofar Mulla et al.· International Journal of Eng...· 0 citations
Noise is commonly present in astrophotography images and can obscure faint astronomical structures
and reduce their scientific value. Traditional noise-reduction techniques often blur important details and
fail to preserve fine astronomical structures. This study investigated whether a deep learning–based
approach could more effectively reduce noise while preserving fine structural features in astronomical
images. It was hypothesized that a U-Net-style convolutional autoencoder (CAE) trained on synthetically
noised astrophotography data can serve as an effective, innovative tool to reconstruct higher quality
images. To test this hypothesis, a CAE was trained on publicly available astrophotography images
(107 images from the Messier catalog), and synthetic noise was added to these images to create paired
training data, allowing the model to learn a direct mapping from noisy inputs to clean outputs. Across 11
test images, the mean peak signal-to-noise ratio (PSNR) increased from 11.9 dB in noisy inputs to 33.0
dB after denoising, while the mean structural similarity index (SSIM) improved from 0.28 to 0.89. The
results showed that the CAE reduced the synthetic noise while preserving the most fine astronomical
structure. These findings motivate further evaluation of deep learning–based denoising methods for
astronomical image analysis.
Eiden Han· American Journal of Student...· 0 citations
In this work, an end-to-end generative adversarial framework for computational microwave imaging (CMI) is proposed to reconstruct the targets of interest directly from the measurements of targets obstructed by undesired objects. It integrates a conditional generative adversarial network (cGAN) with a learnable soft-threshold module (STM) to adaptively suppress non-target related information. The proposed framework is evaluated on a diverse dataset comprising MNIST digits obstructed by E-MNIST letters for training and testing, as well as on measurements acquired with an experimental CMI system. In addition, further studies involving objects with different geometries are conducted, demonstrating that the proposed approach can be adapted to other types of objects. Numerical experiments show that the proposed cGAN-STM achieves a normalized mean square error (NMSE) of 0.066 and a structural similarity index (SSIM) of 0.876 under ideal conditions. Comprehensive analyses, including benchmarking, analysis of the STM mechanism, and evaluation under different obstruction sizes, are also conducted. The performance of the model under different signal-to-noise ratio (SNR) scenarios is also evaluated, achieving reasonable reconstruction quality at 15 dB SNR with an NMSE of 0.168 and an SSIM of 0.700. Even at low SNR levels, recognizable target outlines are preserved. These results highlight the effectiveness and adaptability of the proposed method.
Jiaming Zhang, María García-Fernández, G. Álvarez-Narciandi et al.· 0 citations
This study builds and test a Deep Convolutional Generative Adversarial Network (DCGAN) that can produce realistic portraits of people's faces and proves that DCGANs are capable of creating realistic facial representations.
K. N. Reddy, A. Renuka· International Journal for Re...· 0 citations
DeepFakeBuster is presented as a confidence-calibrated adaptive ensemble for deepfake image detection by fusing together heterogeneous deep learning models built around detecting complementary forensic cues e.g., spatial inconsistencies, boundary artifacts, noise residuals, semantic consistency, and frequency-domain features.
Rachana Patil, R. Shinde, S. Patil et al.· Scientific Reports· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
