Distillation of a 688M-parameter MASt3R teacher yields up to 7x smaller students that retain most lunar reconstruction accuracy and outperform sparse-supervised baselines.
arXiv preprint arXiv:2412.16719 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction
Distillation of a 688M-parameter MASt3R teacher yields up to 7x smaller students that retain most lunar reconstruction accuracy and outperform sparse-supervised baselines.