通过智能剪枝与新高斯形式，大幅压缩3D高斯溅射模型。
Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives
- 根据重建质量动态决定剪枝时机，提升效率
- 使用差分高斯单体建模正负密度，减少90%点数
- 适合追求轻量化3D渲染的开发者与研究者
3D高斯溅射（3DGS）虽实现实时逼真渲染，但需大量基元，导致冗余与高资源消耗，限制其在复杂场景中的应用。本文提出一种重建感知的自适应剪枝策略，依据重建质量动态调整剪枝时机与优化周期，有效减小模型规模并提升渲染质量。同时引入3D差分高斯（Difference-of-Gaussians）基元，单个基元联合建模正负密度，增强紧凑配置下的表达能力。实验表明，该方法可实现高达90%的高斯数量缩减，视觉质量媲美或优于现有最优方法。代码将公开。
原文摘要 · Abstract (English)
Recent significant advances in 3D scene representation have been driven by 3D Gaussian Splatting (3DGS), which has enabled real-time rendering with photorealistic quality. 3DGS often requires a large number of primitives to achieve high fidelity, leading to redundant representations and high resource consumption, thereby limiting its scalability for complex or large-scale scenes. Consequently, effective pruning strategies and more expressive primitives that can reduce redundancy while preserving visual quality are crucial for practical deployment. We propose an efficient, integrated reconstruction-aware pruning strategy that adaptively determines pruning timing and refining intervals based on reconstruction quality, thus reducing model size while enhancing rendering quality. Moreover, we introduce a 3D Difference-of-Gaussians primitive that jointly models both positive and negative densities in a single primitive, improving the expressiveness of Gaussians under compact configurations. Our method significantly improves model compactness, achieving up to 90\% reduction in Gaussian-count while delivering visual quality that is similar to, or in some cases better than, that produced by state-of-the-art methods. Code will be made publicly available.
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。