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

2025-08-01

AI Summary

This study addresses the challenge of single-view 3D reconstruction of asteroids—a critical task for deep-space exploration. We propose the first systematic, mission-oriented evaluation framework tailored to spacecraft-based asteroid imaging scenarios. Our methodology integrates 2D perceptual metrics (e.g., LPIPS, FID) with 3D geometric metrics (e.g., Chamfer Distance, F-Score) and conducts quantitative benchmarking on a newly curated spacecraft-asteroid image dataset, evaluating three state-of-the-art models: Hunyuan-3D, Trellis-3D, and Ouroboros-3D. Results reveal strong domain-specific performance: Hunyuan-3D achieves superior image fidelity, whereas Ouroboros-3D excels in geometric reconstruction accuracy. This work establishes a novel benchmark for asteroid single-view reconstruction, uncovers model adaptability patterns—particularly between complex versus simple asteroid morphologies—and provides a verifiable, open-source evaluation paradigm to support lightweight, real-time autonomous navigation in deep-space missions.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: State Estimation
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

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.

Problem

• Benchmarking 3D reconstruction models for asteroid exploration
• Evaluating domain-dependent performance on spacecraft and asteroids
• Establishing new benchmarks for perceptual and geometric accuracy

Innovation

• Benchmarks three 3D reconstruction models
• Uses 2D perceptual and 3D geometric metrics
• Establishes new domain-dependent performance benchmarks