A lossless point cloud geometry codec overfits a small sparse-convolution network per group of frames and entropy-codes octree occupancy using the network's predicted probabilities.
3d point cloud compression: A survey
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
-
LINR-PCGC: Lossless Implicit Neural Representations for Point Cloud Geometry Compression
A lossless point cloud geometry codec overfits a small sparse-convolution network per group of frames and entropy-codes octree occupancy using the network's predicted probabilities.