DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction
This work addresses asteroid exploration and spacecraft navigation needs but is incremental as it benchmarks existing models on new data.
The paper tackled the problem of single-view 3D reconstruction for asteroids by benchmarking three state-of-the-art models on custom datasets, finding that model performance is domain-dependent with Hunyuan-3D achieving top perceptual scores on spacecraft and best geometric accuracy on asteroids.
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.