Voronoi-guided Bilateral 2D Gaussian Splatting for Arbitrary-Scale Hyperspectral Image Super-Resolution

TL;DR

This paper introduces GaussianHSI, a novel framework using Voronoi-guided bilateral Gaussian splatting for flexible, arbitrary-scale hyperspectral image super-resolution, enhancing spatial and spectral reconstruction fidelity.

Contribution

The paper proposes a new Gaussian splatting-based approach with Voronoi-guided spatial reconstruction and spectral detail enhancement for arbitrary-scale hyperspectral super-resolution.

Findings

GaussianHSI outperforms state-of-the-art methods on benchmark datasets.

The Voronoi-guided bilateral Gaussian splatting improves spatial reconstruction.

Spectral detail enhancement boosts spectral fidelity.

Abstract

Most existing hyperspectral image super-resolution methods require modifications for different scales, limiting their flexibility in arbitrary-scale reconstruction. 2D Gaussian splatting provides a continuous representation that is compatible with arbitrary-scale super-resolution. Existing methods often rely on rasterization strategies, which may limit flexible spatial modeling. Extending them to hyperspectral image super-resolution remains challenging, as the task requires adaptive spatial reconstruction while preserving spectral fidelity. This paper proposes GaussianHSI, a Gaussian-Splatting-based framework for arbitrary-scale hyperspectral image super-resolution. We develop a Voronoi-Guided Bilateral 2D Gaussian Splatting for spatial reconstruction. After predicting a set of Gaussian functions to represent the input, it associates each target pixel with relevant Gaussian functions through Voronoi-guided selection. The target pixel is then reconstructed by aggregating the selected Gaussian functions with reference-aware bilateral weighting, which considers both geometric relevance and consistency with low-resolution features. We further introduce a Spectral Detail Enhancement module to improve spectral reconstruction. Extensive experiments on benchmark datasets demonstrate the effectiveness of GaussianHSI over state-of-the-art methods for arbitrary-scale hyperspectral image super-resolution.