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

• URL: http://arxiv.org/abs/2505.24799v2
• Date: Mon, 02 Jun 2025 15:11:16 GMT
• Title: Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images
• Authors: Aditya Retnanto, Son Le, Sebastian Mueller, Armin Leitner, Michael Riffler, Konrad Schindler, Yohan Iddawela,
• Abstract summary: SEN4X is a hybrid super-resolution architecture that combines the advantages of single-image and multi-image techniques.<n>It upgrades Sentinel-2 imagery to 2.5 m ground sampling distance.<n>We find that they lead to a significant performance improvement over state-of-the-art super-resolution baselines.
• Score: 12.869627326096762
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations [61.448005005426666]
  We consider two challenging issues in reference-based super-resolution (RefSR) for smartphone. We propose a novel self-supervised learning approach for real-world RefSR from observations at dual and multiple camera zooms.
  arXiv  Detail & Related papers  (2024-05-03T15:20:30Z)
• Cross-sensor super-resolution of irregularly sampled Sentinel-2 time series [2.9748898344267785]
  We introduce BreizhSR, a new dataset for 4x super-resolution of Sentinel-2 time series. We show that using multiple images significantly improves super-resolution performance. We observe a trade-off between spectral fidelity and perceptual quality of the reconstructed HR images.
  arXiv  Detail & Related papers  (2024-04-25T08:36:09Z)
• Passive superresolution imaging of incoherent objects [63.942632088208505]
  Method consists of measuring the field's spatial mode components in the image plane in the overcomplete basis of Hermite-Gaussian modes and their superpositions. Deep neural network is used to reconstruct the object from these measurements.
  arXiv  Detail & Related papers  (2023-04-19T15:53:09Z)
• On The Role of Alias and Band-Shift for Sentinel-2 Super-Resolution [5.897281612951907]
  In this work, we study the problem of single-image super-resolution (SISR) of Sentinel-2 imagery. We show that thanks to its unique sensor specification, namely the inter-band shift and alias, that deep-learning methods are able to recover fine details.
  arXiv  Detail & Related papers  (2023-02-22T17:08:45Z)
• Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images [11.169492436455423]
  DeepSent is a new deep network for super-resolving multitemporal series of Sentinel-2 images. We show that our solution outperforms other state-of-the-art techniques that realize either multitemporal or multispectral data fusion. We have applied our method to super-resolve real-world Sentinel-2 images, enhancing the spatial resolution of all the spectral bands to 3.3 m nominal ground sampling distance.
  arXiv  Detail & Related papers  (2023-01-26T15:01:25Z)
• MuS2: A Benchmark for Sentinel-2 Multi-Image Super-Resolution [6.480645418615952]
  Insufficient spatial resolution of satellite imagery, including Sentinel-2 data, is a serious limitation in many practical use cases. Super-resolution reconstruction is receiving considerable attention from the remote sensing community. We introduce a new MuS2 benchmark for multi-image super-resolution reconstruction of Sentinel-2 images.
  arXiv  Detail & Related papers  (2022-10-06T08:29:54Z)
• Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation [23.025397327720874]
  We present the first results of applying multi-image super-resolution (MISR) to multi-spectral remote sensing imagery. We show that MISR is superior to single-image super-resolution and other baselines on a range of image fidelity metrics.
  arXiv  Detail & Related papers  (2021-11-05T02:49:04Z)
• Projected GANs Converge Faster [50.23237734403834]
  Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Our Projected GAN improves image quality, sample efficiency, and convergence speed.
  arXiv  Detail & Related papers  (2021-11-01T15:11:01Z)
• Exploiting Raw Images for Real-Scene Super-Resolution [105.18021110372133]
  We study the problem of real-scene single image super-resolution to bridge the gap between synthetic data and real captured images. We propose a method to generate more realistic training data by mimicking the imaging process of digital cameras. We also develop a two-branch convolutional neural network to exploit the radiance information originally-recorded in raw images.
  arXiv  Detail & Related papers  (2021-02-02T16:10:15Z)
• Gated Fusion Network for Degraded Image Super Resolution [78.67168802945069]
  We propose a dual-branch convolutional neural network to extract base features and recovered features separately. By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process.
  arXiv  Detail & Related papers  (2020-03-02T13:28:32Z)
• HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery [55.253395881190436]
  Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem. This is important for satellite monitoring of human impact on the planet. We present HighRes-net, the first deep learning approach to MFSR that learns its sub-tasks in an end-to-end fashion.
  arXiv  Detail & Related papers  (2020-02-15T22:17:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.