mlsanityData to 7 Oct 2026

Self-Supervised Super-Resolution for Sentinel-5P Hyperspectral Images

arXiv 2604.17652 ↗First posted 19 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Sentinel-5P (S5P) plays a critical role in atmospheric monitoring; however, its spatial resolution limits fine-scale analysis. Existing super-resolution (SR) approaches rely on supervised learning with synthetic low-resolution (LR) data, since true high-resolution (HR) data do not exist, limiting their applicability to real observations. We propose a self-supervised hyperspectral SR framework for S5P that enables training without HR ground truth. The method combines Stein's Unbiased Risk Estimator (SURE) with an equivariant imaging constraint, incorporating the S5P degradation operator and noise statistics derived from signal-to-noise ratio (SNR) metadata. We also introduce depthwise separable convolution U-Net architectures designed for efficiency and spectral fidelity. The framework is evaluated in two settings: (i) LR-HR, where synthetic LR data are used for direct comparison with supervised learning, and (ii) GT-SHR, where super-resolved images surpass the native spatial resolution without HR reference. Results across multiple bands show that self-supervised models achieve performance comparable to supervised methods while maintaining strong consistency. Qualitative analysis shows improved spatial detail over bicubic interpolation, and validation with EMIT data confirms that reconstructed structures are physically meaningful. Code is available at https://github.com/hyamomar/Sentinel-5P-Super-Resolution/tree/main/self_supervised

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 69 references that are in the map. First posted on arXiv 19 Apr 2026.

Builds on

19 of 69 references.

References · 19

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  4. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  5. 2017Deep Image Priorcited by 1,097
  6. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  7. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  8. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  9. 2019Blind Super-Resolution Kernel Estimation using an Internal-GANcited by 175
  10. 2021Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurementscited by 56
  11. 2018Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural networkcited by 44
  12. 2021Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolutioncited by 31
7 more
  1. 2023HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion Modelscited by 31
  2. 2023ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolutioncited by 23
  3. 2023Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and Deblurringcited by 14
  4. 2022Dual-Stage Approach Toward Hyperspectral Image Super-Resolutioncited by 13
  5. 2023A Spectral Diffusion Prior for Hyperspectral Image Super-Resolutioncited by 8
  6. 2025Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Surveycited by 7
  7. 2025Depth Separable architecture for Sentinel-5P Super-Resolutioncited by 1

Built on by

Not cited yet.