HyperGS: Hyperspectral 3D Gaussian Splatting

TL;DR

HyperGS is a new framework for hyperspectral view synthesis that uses latent 3D Gaussian splatting to produce high-fidelity, multi-view spectral reconstructions efficiently, outperforming existing methods.

Contribution

It introduces HyperGS, a novel hyperspectral view synthesis method with a new 3D Gaussian splatting technique and a benchmark for HNVS.

Findings

14dB accuracy improvement over previous models

Effective handling of high-dimensional hyperspectral data

Robust performance on real and simulated scenes

Abstract

We introduce HyperGS, a novel framework for Hyperspectral Novel View Synthesis (HNVS), based on a new latent 3D Gaussian Splatting (3DGS) technique. Our approach enables simultaneous spatial and spectral renderings by encoding material properties from multi-view 3D hyperspectral datasets. HyperGS reconstructs high-fidelity views from arbitrary perspectives with improved accuracy and speed, outperforming currently existing methods. To address the challenges of high-dimensional data, we perform view synthesis in a learned latent space, incorporating a pixel-wise adaptive density function and a pruning technique for increased training stability and efficiency. Additionally, we introduce the first HNVS benchmark, implementing a number of new baselines based on recent SOTA RGB-NVS techniques, alongside the small number of prior works on HNVS. We demonstrate HyperGS's robustness through extensive evaluation of real and simulated hyperspectral scenes with a 14db accuracy improvement upon previously published models.