用可学习的置信度压缩3D高斯点云，兼顾画质与效率。
Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
- 用贝塔分布建模每个点的置信度，通过重建损失优化
- 压缩后仍保持高质量渲染，支持任意高斯点云框架
- 置信度均值可作新画质评估指标，适合实时渲染场景
3D高斯点云实现高质量实时渲染，但常产生数百万个点，导致存储和计算开销过大。本文提出一种基于可学习置信度的有损压缩方法，将置信度建模为贝塔分布。每个点的置信度通过重建感知损失进行优化，实现对低置信度点的剔除，同时保持视觉保真度。该方法具有架构无关性，可应用于任意高斯点云变体。此外，平均置信度值可作为场景质量的新评估指标。大量实验表明，相比已有方法，该方法在压缩率与保真度之间实现了更优权衡。代码与数据已公开于 https://github.com/amirhossein-razlighi/Confident-Splatting。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。