mlsanityData to 14 Oct 2026

Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images

arXiv 2505.24799 ↗First posted 30 May 2025eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Super-resolution aims to increase the resolution of satellite images by reconstructing high-frequency details, which go beyond na"ive upsampling. This has particular relevance for Earth observation missions like Sentinel-2, which offer frequent, regular coverage at no cost; but at coarse resolution. Its pixel footprint is too large to capture small features like houses, streets, or hedge rows. To address this, we present SEN4X, a hybrid super-resolution architecture that combines the advantages of single-image and multi-image techniques. It combines temporal oversampling from repeated Sentinel-2 acquisitions with a learned prior from high-resolution Pl'eiades Neo data. In doing so, SEN4X upgrades Sentinel-2 imagery to 2.5 m ground sampling distance. We test the super-resolved images on urban land-cover classification in Hanoi, Vietnam. We find that they lead to a significant performance improvement over state-of-the-art super-resolution baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 45 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

18 of 45 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  5. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  6. 2022SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understandingcited by 167
  7. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 73
  8. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  9. 2020Lightweight Temporal Self-Attention for Classifying Satellite Image Time Seriescited by 55
  10. 2021Continental-Scale Building Detection from High Resolution Satellite Imagerycited by 50
  11. 2018Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural networkcited by 44
  12. 2020HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagerycited by 42
6 more
  1. 2022Open High-Resolution Satellite Imagery: The WorldStrat Dataset -- With Application to Super-Resolutioncited by 40
  2. 2021Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineationcited by 19
  3. 2020Learned Multi-View Texture Super-Resolutioncited by 7
  4. 2024Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensingcited by 7
  5. 2024Cross-sensor super-resolution of irregularly sampled Sentinel-2 time seriescited by 6
  6. 2023L1BSR: Exploiting Detector Overlap for Self-Supervised Single-Image Super-Resolution of Sentinel-2 L1B Imagerycited by 3

Built on by

Not cited yet.