Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory

TL;DR

This paper introduces an attention-based neural network for compressing solar images from NASA's SDO, achieving better rate-distortion performance and perceptual quality than traditional codecs like JPEG, JPEG2000, and BPG.

Contribution

The paper presents a novel attention-enhanced neural image compression method tailored for solar data, outperforming existing codecs in rate-distortion trade-offs.

Findings

Outperforms JPEG and JPEG2000 in rate-distortion.

Achieves superior perceptual quality.

Outperforms BPG in compression performance.

Abstract

NASA's Solar Dynamics Observatory (SDO) mission gathers 1.4 terabytes of data each day from its geosynchronous orbit in space. SDO data includes images of the Sun captured at different wavelengths, with the primary scientific goal of understanding the dynamic processes governing the Sun. Recently, end-to-end optimized artificial neural networks (ANN) have shown great potential in performing image compression. ANN-based compression schemes have outperformed conventional hand-engineered algorithms for lossy and lossless image compression. We have designed an ad-hoc ANN-based image compression scheme to reduce the amount of data needed to be stored and retrieved on space missions studying solar dynamics. In this work, we propose an attention module to make use of both local and non-local attention mechanisms in an adversarially trained neural image compression network. We have also demonstrated the superior perceptual quality of this neural image compressor. Our proposed algorithm for compressing images downloaded from the SDO spacecraft performs better in rate-distortion trade-off than the popular currently-in-use image compression codecs such as JPEG and JPEG2000. In addition we have shown that the proposed method outperforms state-of-the art lossy transform coding compression codec, i.e., BPG.