English

DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction

Computer Vision and Pattern Recognition 2025-08-05 v1 Machine Learning

Abstract

To enhance asteroid exploration and autonomous spacecraft navigation, we introduce DreamSat-2.0, a pipeline that benchmarks three state-of-the-art 3D reconstruction models-Hunyuan-3D, Trellis-3D, and Ouroboros-3D-on custom spacecraft and asteroid datasets. Our systematic analysis, using 2D perceptual (image quality) and 3D geometric (shape accuracy) metrics, reveals that model performance is domain-dependent. While models produce higher-quality images of complex spacecraft, they achieve better geometric reconstructions for the simpler forms of asteroids. New benchmarks are established, with Hunyuan-3D achieving top perceptual scores on spacecraft but its best geometric accuracy on asteroids, marking a significant advance over our prior work.

Cite

@article{arxiv.2508.01079,
  title  = {DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction},
  author = {Santiago Diaz and Xinghui Hu and Josiane Uwumukiza and Giovanni Lavezzi and Victor Rodriguez-Fernandez and Richard Linares},
  journal= {arXiv preprint arXiv:2508.01079},
  year   = {2025}
}
R2 v1 2026-07-01T04:30:20.771Z