CoE trains a single network with off-diagonal, orthogonality, and contrastive losses to produce coupled embeddings from raw point clouds, enabling dense non-rigid correspondence by nearest neighbor search.
Scape: shape completion and animation of people
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CoE: Deep Coupled Embedding for Non-Rigid Point Cloud Correspondences
CoE trains a single network with off-diagonal, orthogonality, and contrastive losses to produce coupled embeddings from raw point clouds, enabling dense non-rigid correspondence by nearest neighbor search.