HFBRI-MAE substitutes handcrafted rotation-invariant local and global features into a masked autoencoder, letting it classify and segment arbitrarily rotated point clouds without alignment failures.
CrossPoint: Self-supervised cross-modal contrastive learning for 3D point cloud understanding,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysis
HFBRI-MAE substitutes handcrafted rotation-invariant local and global features into a masked autoencoder, letting it classify and segment arbitrarily rotated point clouds without alignment failures.