Structure-Preserving Unpaired Image Translation to Photometrically Calibrate JunoCam with Hubble Data

2025/11/27 by Aditya Singh, Shachi Shah, Singh, Aditya Pratap +11
Physics and Astronomy · #Astro and Planetary Science #Computer Vision and Pattern Recognition (cs.CV) #Earth and Planetary Astrophysics (astro-ph.EP) #FOS: Computer and information sciences #FOS: Physical sciences #Gamma-ray bursts and supernovae #Instrumentation and Methods for Astrophysics (astro-ph.IM) #Planetary Science and Exploration

paper · pdf · doi:10.48550/arxiv.2511.22668

openalex publication_date 2025/11/27 · openalex created_date 2025/12/03 · openalex updated_date 2026/07/28

Abstract

Insights into Jupiter's atmospheric dynamics are vital for understanding planetary meteorology and exoplanetary gas giant atmospheres. To study these dynamics, we require high-resolution, photometrically calibrated observations. Over the last 9 years, the Juno spacecraft's optical camera, JunoCam, has generated a unique dataset with high spatial resolution, wide coverage during perijove passes, and a long baseline. However, JunoCam lacks absolute photometric calibration, hindering quantitative analysis of the Jovian atmosphere. Using observations from the Hubble Space Telescope (HST) as a proxy for a calibrated sensor, we present a novel method for performing unpaired image-to-image translation (I2I) between JunoCam and HST, focusing on addressing the resolution discrepancy between the two sensors. Our structure-preserving I2I method, SP-I2I, incorporates explicit frequency-space constraints designed to preserve high-frequency features ensuring the retention of fine, small-scale spatial structures - essential for studying Jupiter's atmosphere. We demonstrate that state-of-the-art unpaired image-to-image translation methods are inadequate to address this problem, and, importantly, we show the broader impact of our proposed solution on relevant remote sensing data for the pansharpening task.

Citations

• Unpaired Image-to-Image Translation with Content Preserving Perspective: A Review
• Schrödinger Bridge Flow for Unpaired Data Translation
• Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization
• Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts
• Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
• Explicitly Minimizing the Blur Error of Variational Autoencoders
• HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
• Simpler is better: spectral regularization and up-sampling techniques for variational autoencoders
• On the Frequency Bias of Generative Models
• Generative Adversarial Networks
• F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
• Diffusion Schr "odinger Bridge with Applications to Score-Based\n Generative Modeling
• Exploring The Effect of High-frequency Components in GANs Training
• Improved Denoising Diffusion Probabilistic Models
• Image-to-Image Translation: Methods and Applications
• Focal Frequency Loss for Image Reconstruction and Synthesis
• Vertical Structure and Color of Jovian Latitudinal Cloud Bands during the Juno Era
• SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
• DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs
• Contrastive Learning for Unpaired Image-to-Image Translation
• Denoising Diffusion Probabilistic Models
• Frequency Bias in Neural Networks for Input of Non-Uniform Density
• AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks
• Frequency Separation for Real-World Super-Resolution
• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
• Diverse Image-to-Image Translation via Disentangled Representations
• Multimodal Unsupervised Image-to-Image Translation
• Optimizing the Latent Space of Generative Networks
• DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Unsupervised Image-to-Image Translation Networks
• Image-to-Image Translation with Conditional Adversarial Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Photometric and Astrometric Calibration of the JWST Instrument Complement

Related

• Vertical Structure and Color of Jovian Latitudinal Cloud Bands during the Juno Era
• Observing Jupiter's polar stratospheric haze with HST/STIS. An HST White\n Paper
• High-precision astrometry and photometry with the JWST/MIRI imager
• The crucial role of HST during the NASA Juno mission: a "Juno initiative"
• Characterising The Atmospheric Dynamics Of HD209458b-like Hot Jupiters Using AI Driven Image Recognition/Categorisation