Unsupervised Knowledge Distillation for Satellite Multiview Stereo With Uncertainty-Aware Supervision (opens in new tab)

This article proposes an unsupervised knowledge distillation (KD) framework for satellite multiview stereo (MVS) reconstruction under label-free settings. A teacher–student paradigm is adopted, where a teacher MVS network is first trained using self-supervised multiview geometric constraints, including photometric consistency, feature similarity, smoothness, and structural similarity. The teacher produces multiview height predictions, and geometry-aware uncertainty is inferred from cross-view...