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

Amirhossein Razlighi, Elaheh Badali Golezani, Shohreh Kasaei

Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions: 3 upvotes on Hugging Face Daily Papers, #15 of 18 papers on 2025-07-02. Day-by-day upvote history.

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

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.