NeRF-based Spacecraft Reconstruction from Close-Range Monocular Imagery Under Illumination Variability and Pose Uncertainty
Researchers have developed new methods using Neural Radiance Fields (NeRF) to improve spacecraft pose estimation and 3D reconstruction from imagery. One approach uses NeRF-based augmentations to train pose estimators with significantly fewer images, overcoming the limitations of traditional CAD-based training. Another method enhances NeRF by incorporating per-image appearance embeddings and pose correction, making it more robust to variable lighting and inaccurate pose data during reconstruction. AI
IMPACT New NeRF-based techniques promise more robust and data-efficient spacecraft pose estimation and 3D reconstruction for space missions.