HyVIC: A Metric-Driven Spatio-Spectral Hyperspectral Image Compression Architecture Based on Variational Autoencoders
HyVIC is a configurable Variational Autoencoder for hyperspectral image compression that allows independent control over spatial and spectral feature learning. It addresses limitations of existing models by explicitly accounting for spatio-spectral redundancies in hyperspectral data, leading to improved rate-distortion performance compared to previous methods.