Learning rotation invariance in descriptors matches the performance of matcher-level invariance but allows earlier invariance, faster matchers, and no loss in upright performance when trained at scale.
Learning rotation-equivariant features for visual corre- spondence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Who Handles Orientation? Investigating Invariance in Feature Matching
Learning rotation invariance in descriptors matches the performance of matcher-level invariance but allows earlier invariance, faster matchers, and no loss in upright performance when trained at scale.