A mesh-native CNN with variable-size convolution regions and parallel face-collapse pooling achieves competitive classification with substantially lower memory use.
Title resolution pending
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
-
MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes
A mesh-native CNN with variable-size convolution regions and parallel face-collapse pooling achieves competitive classification with substantially lower memory use.