Reconstructing Satellites in 3D from Amateur Telescope Images

TL;DR

This paper introduces a new computational imaging framework that enables accurate 3D reconstruction of satellites from ground-based telescope images, overcoming atmospheric and observational challenges for improved space situational awareness.

Contribution

It presents a novel integration of image pre-processing, Gaussian Splatting, and BnB search for robust 3D satellite reconstruction from limited and noisy ground-based data.

Findings

Outperforms state-of-the-art NeRF-based methods in quantitative metrics.

Successfully reconstructs 3D models of Tiangong and ISS from ground observations.

Demonstrates robustness to atmospheric turbulence and low signal-to-noise ratios.

Abstract

Monitoring space objects is crucial for space situational awareness, yet reconstructing 3D satellite models from ground-based telescope images is challenging due to atmospheric turbulence, long observation distances, limited viewpoints, and low signal-to-noise ratios. In this paper, we propose a novel computational imaging framework that overcomes these obstacles by integrating a hybrid image pre-processing pipeline with a joint pose estimation and 3D reconstruction module based on controlled Gaussian Splatting (GS) and Branch-and-Bound (BnB) search. We validate our approach on both synthetic satellite datasets and on-sky observations of China's Tiangong Space Station and the International Space Station, achieving robust 3D reconstructions of low-Earth orbit satellites from ground-based data. Quantitative evaluations using SSIM, PSNR, LPIPS, and Chamfer Distance demonstrate that our method outperforms state-of-the-art NeRF-based approaches, and ablation studies confirm the critical role of each component. Our framework enables high-fidelity 3D satellite monitoring from Earth, offering a cost-effective alternative for space situational awareness. Project page: https://ai4scientificimaging.org/ReconstructingSatellites