SOURCE-LINKED INTELLIGENCE

Compressing 3D Gaussian Splatting via Cross-Representation Priors

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis but incurs high storage and transmission costs due to dense Gaussian primitives. Recent anchor-based compression reduces per-primitive redundancy, yet redundancy across anchors remains largely unexploited. We propose CRP-GS (Cross-Representation Priors for Gaussian Splatting), a rate-distortion optimized compression framework that leverages cross-representation priors to improve anchor-level entropy modeling. First, a Correspondence-Oriented Hierarchical Structure (COHS) organizes anchors by feature correspondence rather th

Read original source ↗ Open in workspace

recordType

paper

region

Global