Multi-spectral Entropy Constrained Neural Compression of Solar Imagery

TL;DR

This paper introduces a transformer-based neural image compression method tailored for multi-spectral solar imagery, effectively capturing inter- and intra-wavelength redundancies to outperform traditional algorithms.

Contribution

It presents a novel multi-spectral neural compressor with inter-window attention and shift invariance, improving compression efficiency and spectral decorrelation.

Findings

Outperforms conventional compression algorithms

Better decorrelates images across multiple wavelengths

Effective in capturing spectral redundancies

Abstract

Missions studying the dynamic behaviour of the Sun are defined to capture multi-spectral images of the sun and transmit them to the ground station in a daily basis. To make transmission efficient and feasible, image compression systems need to be exploited. Recently successful end-to-end optimized neural network-based image compression systems have shown great potential to be used in an ad-hoc manner. In this work we have proposed a transformer-based multi-spectral neural image compressor to efficiently capture redundancies both intra/inter-wavelength. To unleash the locality of window-based self attention mechanism, we propose an inter-window aggregated token multi head self attention. Additionally to make the neural compressor autoencoder shift invariant, a randomly shifted window attention mechanism is used which makes the transformer blocks insensitive to translations in their input domain. We demonstrate that the proposed approach not only outperforms the conventional compression algorithms but also it is able to better decorrelates images along the multiple wavelengths compared to single spectral compression.