A training-only regularizer makes cross-modal 2D-3D matching representations recoverable by weak probes, improving robustness and pose accuracy on 7-Scenes and RGB-D Scenes V2.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching
A training-only regularizer makes cross-modal 2D-3D matching representations recoverable by weak probes, improving robustness and pose accuracy on 7-Scenes and RGB-D Scenes V2.