Improved 3D Gaussian Splatting of Unknown Spacecraft Structure Using Space Environment Illumination Knowledge
arXiv:2512.23998 · doi:10.1109/iSpaRo66239.2025.11437016
Abstract
This work presents a novel pipeline to recover the 3D structure of an unknown target spacecraft from a sequence of images captured during Rendezvous and Proximity Operations (RPO) in space. The target's geometry and appearance are represented as a 3D Gaussian Splatting (3DGS) model. However, learning 3DGS requires static scenes, an assumption in contrast to dynamic lighting conditions encountered in spaceborne imagery. The trained 3DGS model can also be used for camera pose estimation through photometric optimization. Therefore, in addition to recovering a geometrically accurate 3DGS model, the photometric accuracy of the rendered images is imperative to downstream pose estimation tasks during the RPO process. This work proposes to incorporate the prior knowledge of the Sun's position, estimated and maintained by the servicer spacecraft, into the training pipeline for improved photometric quality of 3DGS rasterization. Experimental studies demonstrate the effectiveness of the proposed solution, as 3DGS models trained on a sequence of images learn to adapt to rapidly changing illumination conditions in space and reflect global shadowing and self-occlusion.
Presented at 2025 IEEE International Conference on Space Robotics (iSpaRo)
References in corpus (9)
- ORB-SLAM: a Versatile and Accurate Monocular SLAM System
- Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
- Satellite Pose Estimation Challenge: Dataset, Competition Design and Results
- Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap
- Adaptive Neural Network-based Unscented Kalman Filter for Robust Pose Tracking of Noncooperative Spacecraft
- GS^3: Efficient Relighting with Triple Gaussian Splatting
- Online Supervised Training of Spaceborne Vision during Proximity Operations using Adaptive Kalman Filtering
- Object-centric Reconstruction and Tracking of Dynamic Unknown Objects using 3D Gaussian Splatting
- Bridging the Domain Gap for Flight-Ready Spaceborne Vision