mlsanityData to 14 Oct 2026

StrCGAN: A Generative Framework for Stellar Image Restoration

arXiv 2509.19805 ↗First posted 24 Sep 2025cs.CV astro-ph.IM astro-ph.SRcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce StrCGAN (Stellar Cyclic GAN), a generative model designed to enhance low-resolution astrophotography images. Our goal is to reconstruct high fidelity ground truth like representations of stellar objects, a task that is challenging due to the limited resolution and quality of small-telescope observations such as the MobilTelesco dataset. Traditional models such as CycleGAN provide a foundation for image to image translation but often distort the morphology of stars and produce barely resembling images. To overcome these limitations, we extend the CycleGAN framework with some key innovations: multi-spectral fusion to align optical and near infrared (NIR) domains, and astrophysical regularization modules to preserve stellar morphology. Ground truth references from multi-mission all sky surveys spanning optical to NIR guide the training process, ensuring that reconstructions remain consistent across spectral bands. Together, these components allow StrCGAN to generate reconstructions that are visually sharper outperforming standard GAN models in the task of astrophysical image enhancement.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 38 references that are in the map. First posted on arXiv 24 Sep 2025.

Builds on

21 of 38 references.

References · 21

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  7. 2014Conditional Generative Adversarial Netscited by 2,162
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  9. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  10. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  11. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  12. 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
9 more
  1. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  2. 2016Stacked Generative Adversarial Networkscited by 44
  3. 2019Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low Lightcited by 9
  4. 2021CharacterGAN: Few-Shot Keypoint Character Animation and Reposingcited by 9
  5. 2023Radio astronomical images object detection and segmentation: A benchmark on deep learning methodscited by 4
  6. 2024Seg-CycleGAN : SAR-to-optical image translation guided by a downstream taskcited by 4
  7. 2021Generative Adversarial Networks for Astronomical Images Generationcited by 1
  8. 2025Astrophotography turbulence mitigation via generative modelscited by 1
  9. 2025Benchmarking Deep Learning-Based Object Detection Models on Feature Deficient Astrophotography Imagery Datasetcited by 1

Built on by

Not cited yet.