DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 1 Aug 2025.
Builds on
16 of 28 references.
References · 16
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
- 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
- 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
- 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
- 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
- 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
- 2024Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusioncited by 31
4 more
- 2024General Purpose Image Encoder DINOv2 for Medical Image Registrationcited by 11
- 2023Instant-NeRF: Instant On-Device Neural Radiance Field Training via Algorithm-Accelerator Co-Designed Near-Memory Processingcited by 6
- 2024DreamSat: Towards a General 3D Model for Novel View Synthesis of Space Objectscited by 5
- 2025Fast Learning of Non-Cooperative Spacecraft 3D Models through Primitive Initializationcited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.