A local-to-global auto-encoder with hierarchical self-attention learns point cloud features that beat existing unsupervised methods on classification, retrieval, and upsampling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention
A local-to-global auto-encoder with hierarchical self-attention learns point cloud features that beat existing unsupervised methods on classification, retrieval, and upsampling.