Confident Splatting

Key Contributions

• Confidence scoring per splat via Beta distributions.
• Lossy pruning with strong compression–fidelity trade-off.
• Architecture-agnostic — plugs into any Gaussian Splatting pipeline.
• Proposes average confidence as a new scene quality metric.

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.

BibTeX

@article{razlighi2025confident,
  title={Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions},
  author={Razlighi, AmirHossein and Badali, Elahe and Kasaei, Shohreh},
  journal={arXiv preprint arXiv:2506.22973},
  year={2025}
}