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

2026-04-19

AI Summary

Existing hyperspectral image super-resolution methods struggle to simultaneously achieve arbitrary-scale reconstruction, spatial adaptability, and spectral fidelity. To address this challenge, this work proposes GaussianHSI, a novel framework that introduces Voronoi-guided bilaterally weighted 2D Gaussian splatting for the first time in this domain. By leveraging Voronoi diagrams to select relevant Gaussians and incorporating reference-aware bilateral weights for pixel reconstruction, the method enables continuous-scale super-resolution without retraining. Additionally, a dedicated spectral detail enhancement module is designed to improve spectral reconstruction quality. Extensive experiments demonstrate that GaussianHSI significantly outperforms current state-of-the-art approaches across multiple benchmark datasets, effectively balancing spatial flexibility with spectral accuracy.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• hyperspectral image super-resolution
• arbitrary-scale reconstruction
• spatial modeling
• spectral fidelity

Innovation

• Gaussian Splatting
• Arbitrary-Scale Super-Resolution
• Voronoi-Guided Selection
• Bilateral Weighting
• Hyperspectral Image Reconstruction