Saved in:
Bibliographic Details
Main Authors: Thirgood, Christopher, Mendez, Oscar, Ling, Erin Chao, Storey, Jon, Hadfield, Simon
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.12849
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917871036137472
author Thirgood, Christopher
Mendez, Oscar
Ling, Erin Chao
Storey, Jon
Hadfield, Simon
author_facet Thirgood, Christopher
Mendez, Oscar
Ling, Erin Chao
Storey, Jon
Hadfield, Simon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HyperGS: Hyperspectral 3D Gaussian Splatting
Thirgood, Christopher
Mendez, Oscar
Ling, Erin Chao
Storey, Jon
Hadfield, Simon
Computer Vision and Pattern Recognition
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.
title HyperGS: Hyperspectral 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.12849