The reviewed record of science sign in
Pith

arxiv: 2506.22973 · v1 · pith:CZQGIRGY · submitted 2025-06-28 · cs.GR · cs.CV

Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:CZQGIRGYrecord.jsonopen to challenge →

classification cs.GR cs.CV
keywords splattingcompressionconfidencegaussianbetadistributionsfidelitylearnable
0
0 comments X
read the original abstract

3D Gaussian Splatting enables high-quality real-time rendering but often produces millions of splats, resulting in excessive storage and computational overhead. We propose a novel lossy compression method based on learnable confidence scores modeled as Beta distributions. Each splat's confidence is optimized through reconstruction-aware losses, enabling pruning of low-confidence splats while preserving visual fidelity. The proposed approach is architecture-agnostic and can be applied to any Gaussian Splatting variant. In addition, the average confidence values serve as a new metric to assess the quality of the scene. Extensive experiments demonstrate favorable trade-offs between compression and fidelity compared to prior work. Our code and data are publicly available at https://github.com/amirhossein-razlighi/Confident-Splatting

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.