DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction
By: Santiago Diaz , Xinghui Hu , Josiane Uwumukiza and more
Potential Business Impact:
Builds accurate 3D models of asteroids and spacecraft
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.
Similar Papers
A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Flight Computers
CV and Pattern Recognition
Helps robots find and fix spaceship damage automatically.
Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset
CV and Pattern Recognition
Helps robots map the Moon's surface accurately.
NeRF-based Visualization of 3D Cues Supporting Data-Driven Spacecraft Pose Estimation
CV and Pattern Recognition
Shows how robots see and know where to go.