Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Jennifer Nolan, Travis Driver, John Christian

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.

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

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.
Paper Structure (9 sections, 13 equations, 6 figures, 2 tables)

This paper contains 9 sections, 13 equations, 6 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Gaussian Splatting
  4. Small Body Photometry
  5. Background
  6. Photometry Implementation in 2DGS
  7. Experimental Setup
  8. Results
  9. Conclusion

Figures (6)

  • Figure 1: Our proposed AstroSplat framework compared to the traditional spherical harmonic (SH) parameterization. The SH parametrization results in (b) smoothed normals maps, while the physics-based reflectance modeling of AstroSplat yields more detailed (c) surface normals, (d) albedos, and (e) meshes.
  • Figure 2: 2DGS frame definitions. Relative orientation and positions of the local splat $\mathcal{S}$, world $\mathcal{W}$, camera $\mathcal{C}$, and pixel $\mathcal{P}$ frames. The origin of each frame is indicated by the point labeled $O$ and the basis directions are defined by $\textbf{t}$ vectors.
  • Figure 3: Photometry conventions. Photometric angles and their relationships to the Sun vector $\textbf{s}$, emission vector $\textbf{e}$, and normal $\textbf{n}$ with respect to a local patch centered at $\bm{\ell}$.
  • Figure 4: Qualitative comparison of test image renderings for each reflectance model.
  • Figure 5: Qualitative comparison of test image normals for each reflectance model.
  • ...and 1 more figures