AstroSplat: Physics-Based Gaussian Splatting for Rendering and Reconstruction of Small Celestial Bodies

arXiv cs.CV / 3/13/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

Introduces AstroSplat, a physics-based Gaussian splatting framework that integrates planetary reflectance models for improved rendering and reconstruction of small-body surfaces.
Addresses limitations of appearance-based spherical harmonic parameterizations by explicitly modeling light-surface interactions and material properties.
Demonstrates improved autonomous reconstruction and photometric characterization using in-situ imagery, validated on NASA Dawn mission data.
Reports superior rendering performance and surface reconstruction accuracy compared to traditional spherical harmonic approaches.

Abstract

Image-based surface reconstruction and characterization are crucial for missions to small celestial bodies (e.g., asteroids), as it informs mission planning, navigation, and scientific analysis. Recent advances in Gaussian splatting enable high-fidelity neural scene representations but typically rely on a spherical harmonic intensity parameterization that is strictly appearance-based and does not explicitly model material properties or light-surface interactions. We introduce AstroSplat, a physics-based Gaussian splatting framework that integrates planetary reflectance models to improve the autonomous reconstruction and photometric characterization of small-body surfaces from in-situ imagery. The proposed framework is validated on real imagery taken by NASA's Dawn mission, where we demonstrate superior rendering performance and surface reconstruction accuracy compared to the typical spherical harmonic parameterization.