|
|
|
Davy |
Arias |
|
|
|
|
|
|
|
| L1BSR produces a 5m high-resolution (HR) output with all bands correctly registered from a single 10m low-resolution (LR) Sentinel-2 L1B image with misaligned bands. Note that our method is trained on real data with self-supervision, i.e. without any ground truth HR targets. |
|
Project developed at the ENS Paris-Saclay, Centre Borelli and accepted at EarthVision 2023. |
| We propose L1BSR, a deep learning-based method for super-resolution and band alignment of Sentinel-2 L1B RGBN bands. It uses self-supervision on real L1B data to avoid the need for high-resolution ground truth. A cross-spectral registration network is trained to compute an optical flow between different spectral bands. Results show comparable performance to supervised methods on synthetic and real L1B data. |
 |
| Super-Resolution framework. Overview of our proposed self-supervised L1BSR framework for Sentinel-2 L1B at training time. Note that at inference time, only one input and the reconstruction module are required. |
 |
| Cross-Spectral Registration framework. Training setup of our proposed cross-spectral registration (CSR) module. |
 |
| Sensor layout of the Sentinel-2 MSI. The Sentinel-2 MSI carries 12 CMOS detectors for the VNIR bands, with adjacent detectors having overlapping fields of view that result in overlapping regions in level-1B (L1B) images. The push-broom acquisition is done in the vertical direction. |
| The L1BSR dataset includes 3740 pairs of overlapping image crops extracted from two L1B products. Each crop has a height of around 400 pixels and a variable width that depends on the overlap width between detectors for RGBN bands, typically around 120-200 pixels. In addition to detector parallax, there is also cross-band parallax for each detector, resulting in shifts between bands. Pre-registration is performed for both cross-band and cross-detector parallax, with a precision of up to a few pixels (typically less than 10 pixels). |
| Examples of overlapping L1B crops from the L1BSR dataset. |
|
| We compare our self-supervised method L1BSR with a L1C-based supervised method, which uses PlanetScope images as ground-truth HR targets to train the SR model. The L1B and L1C images are from the same acquisition. |
 |
N. L. Nguyen, J. Anger, A. Davy, P. Arias, and G. Facciolo L1BSR: Exploiting Detector Overlap for Self-Supervised Single-Image Super-Resolution of Sentinel-2 L1B Imagery. In EarthVision 2023. (hosted on ArXiv) |
Acknowledgements |