A self-supervised point cloud model that encodes spatial structure into SSM latent states and adapts state-update scale to input length achieves new SOTA on ScanObjectNN and ModelNet40.
Decoupled local aggregation for point cloud learning, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
A self-supervised point cloud model that encodes spatial structure into SSM latent states and adapts state-update scale to input length achieves new SOTA on ScanObjectNN and ModelNet40.