Saved in:
Bibliographic Details
Main Authors: Diaz, Santiago, Hu, Xinghui, Uwumukiza, Josiane, Lavezzi, Giovanni, Rodriguez-Fernandez, Victor, Linares, Richard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01079
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918111865733120
author Diaz, Santiago
Hu, Xinghui
Uwumukiza, Josiane
Lavezzi, Giovanni
Rodriguez-Fernandez, Victor
Linares, Richard
author_facet Diaz, Santiago
Hu, Xinghui
Uwumukiza, Josiane
Lavezzi, Giovanni
Rodriguez-Fernandez, Victor
Linares, Richard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01079
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction
Diaz, Santiago
Hu, Xinghui
Uwumukiza, Josiane
Lavezzi, Giovanni
Rodriguez-Fernandez, Victor
Linares, Richard
Computer Vision and Pattern Recognition
Machine Learning
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.
title DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2508.01079