Cross-sensor super-resolution of irregularly sampled Sentinel-2 time series
This work addresses the trade-off between acquisition frequency and spatial resolution in satellite imaging for Earth Observation, though it is incremental as it extends existing methods to handle irregular time series.
The paper tackled super-resolution of irregularly sampled Sentinel-2 satellite time series by extending deep learning methods like SRDiff and HighRes-net, showing that using multiple images significantly improves performance, with a trade-off observed between spectral fidelity and perceptual quality.
Satellite imaging generally presents a trade-off between the frequency of acquisitions and the spatial resolution of the images. Super-resolution is often advanced as a way to get the best of both worlds. In this work, we investigate multi-image super-resolution of satellite image time series, i.e. how multiple images of the same area acquired at different dates can help reconstruct a higher resolution observation. In particular, we extend state-of-the-art deep single and multi-image super-resolution algorithms, such as SRDiff and HighRes-net, to deal with irregularly sampled Sentinel-2 time series. We introduce BreizhSR, a new dataset for 4x super-resolution of Sentinel-2 time series using very high-resolution SPOT-6 imagery of Brittany, a French region. We show that using multiple images significantly improves super-resolution performance, and that a well-designed temporal positional encoding allows us to perform super-resolution for different times of the series. In addition, we observe a trade-off between spectral fidelity and perceptual quality of the reconstructed HR images, questioning future directions for super-resolution of Earth Observation data.