Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
This work addresses storage and computational efficiency for real-time 3D rendering applications, representing an incremental improvement over existing Gaussian Splatting methods.
The paper tackles the problem of excessive storage and computational overhead in 3D Gaussian Splatting by proposing a confidence-based compression method using learnable Beta distributions, achieving favorable trade-offs between compression and fidelity compared to prior work.
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