CVIVFeb 8, 2023

Hyperspectral Image Compression Using Implicit Neural Representation

arXiv:2302.04129v27 citationsh-index: 5
AI Analysis

This addresses storage and transmission challenges for hyperspectral images, which have hundreds of channels per pixel, but is incremental as it applies an existing method to a new domain.

The paper tackles hyperspectral image compression by using implicit neural representations to map pixel locations to intensities, achieving better compression than JPEG, JPEG2000, and PCA-DCT at low bitrates on four benchmarks.

Hyperspectral images, which record the electromagnetic spectrum for a pixel in the image of a scene, often store hundreds of channels per pixel and contain an order of magnitude more information than a typical similarly-sized color image. Consequently, concomitant with the decreasing cost of capturing these images, there is a need to develop efficient techniques for storing, transmitting, and analyzing hyperspectral images. This paper develops a method for hyperspectral image compression using implicit neural representations where a multilayer perceptron network $Φ_θ$ with sinusoidal activation functions ``learns'' to map pixel locations to pixel intensities for a given hyperspectral image $I$. $Φ_θ$ thus acts as a compressed encoding of this image. The original image is reconstructed by evaluating $Φ_θ$ at each pixel location. We have evaluated our method on four benchmarks -- Indian Pines, Cuprite, Pavia University, and Jasper Ridge -- and we show the proposed method achieves better compression than JPEG, JPEG2000, and PCA-DCT at low bitrates.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes