HybridGS compresses 3DGS scenes by training a compact, quantized Gaussian representation and feeding it to the standard GPCC point cloud encoder, achieving fast codec times at a modest rate-distortion cost.
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
REJECT 1representative citing papers
citing papers explorer
-
HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder
HybridGS compresses 3DGS scenes by training a compact, quantized Gaussian representation and feeding it to the standard GPCC point cloud encoder, achieving fast codec times at a modest rate-distortion cost.