HyVIC: A Metric-Driven Spatio-Spectral Hyperspectral Image Compression Architecture Based on Variational Autoencoders

2026-03-27

AI Summary

This work proposes HyVIC, a variational autoencoder-based compression framework tailored for hyperspectral images, addressing the limitation of existing methods that rely on natural image models and fail to effectively capture their unique spatial-spectral redundancy. HyVIC introduces an explicit joint spatial-spectral modeling architecture within a variational compression framework and incorporates a metric-driven hyperparameter optimization strategy to balance the learning of spatial and spectral features. The method integrates an adjustable spatial-spectral encoder, a hyperprior module, and a BD-PSNR-guided optimization mechanism. Evaluated on two benchmark datasets, HyVIC significantly outperforms state-of-the-art approaches, achieving up to a 4.66 dB gain in BD-PSNR and enabling high-fidelity reconstruction across a wide range of compression ratios.

Abstract

The rapid growth of hyperspectral data archives in remote sensing (RS) necessitates effective compression methods for storage and transmission. Recent advances in learning-based hyperspectral image (HSI) compression have significantly enhanced both reconstruction fidelity and compression efficiency. However, existing methods typically adapt variational image compression models designed for natural images, without adequately accounting for the distinct spatio-spectral redundancies inherent in HSIs. In particular, they lack explicit architectural designs to balance spatial and spectral feature learning, limiting their ability to effectively leverage the unique characteristics of hyperspectral data. To address this issue, we introduce spatio-spectral variational hyperspectral image compression architecture (HyVIC). The proposed model comprises four main components: 1) adjustable spatio-spectral encoder; 2) spatio-spectral hyperencoder; 3) spatio-spectral hyperdecoder; and 4) adjustable spatio-spectral decoder. We demonstrate that the trade-off between spatial and spectral feature learning is crucial for the reconstruction fidelity, and therefore present a metric-driven strategy to systematically select the hyperparameters of the proposed model. Extensive experiments on two benchmark datasets demonstrate the effectiveness of the proposed model, achieving high spatial and spectral reconstruction fidelity across a wide range of compression ratios (CRs) and improving the state of the art by up to 4.66dB in terms of BD-PSNR. Based on our results, we offer insights and derive practical guidelines to guide future research directions in learning-based variational HSI compression. Our code and pre-trained model weights are publicly available at https://git.tu-berlin.de/rsim/hyvic .

Problem

• hyperspectral image compression
• spatio-spectral redundancy
• variational autoencoders
• feature learning balance
• remote sensing

Innovation

• spatio-spectral compression
• variational autoencoder
• hyperspectral image compression
• metric-driven optimization
• learned image compression