An interlaced point-voxel compression network with routing-weight-guided sparse convolutions reports 15.5% and 8% BD-rate savings over PCGCv2 and DeepPCC, but 22.9% worse than SparsePCGC.
Deep compression for dense point cloud maps,
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
-
PVINet: Point-Voxel Interlaced Network for Point Cloud Compression
An interlaced point-voxel compression network with routing-weight-guided sparse convolutions reports 15.5% and 8% BD-rate savings over PCGCv2 and DeepPCC, but 22.9% worse than SparsePCGC.