明智剪枝，清晰重建：基于自适应剪枝与差分高斯基元的紧凑 3D 高斯泼溅
Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives
提供一种重建感知的自适应剪枝调度（依据重建质量动态决定剪枝时机与细化间隔），以及把正负密度联合建模的差分高斯基元，可直接嵌入现有 3DGS 训练管线以在保持渲染质量的同时大幅压缩高斯数量。
原文依据 a 3D Difference-of-Gaussians primitive that jointly models both positive and negative densities in a single primitive
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期三维场景表示领域的重大进展由 3D 高斯泼溅（3DGS）推动，它实现了具有照片级质量的实时渲染。3DGS 往往需要大量基元才能达到高保真度，这导致表示冗余与资源消耗过高，从而限制了其在复杂或大规模场景中的可扩展性。因此，能够减少冗余同时保持视觉质量的有效剪枝策略与更具表现力的基元，对实际部署至关重要。我们提出了一种高效的、集成重建感知的剪枝策略，它根据重建质量自适应地确定剪枝时机与细化间隔，从而在减小模型规模的同时提升渲染质量。此外，我们引入了一种 3D 差分高斯基元，在单个基元中联合建模正密度与负密度，提升了紧凑配置下高斯的表达能力。我们的方法显著提升了模型紧凑性，在高斯数量上最多减少 90%，同时交付的视觉质量与最优方法相近，在某些情况下甚至更优。
英文原文摘要 1225 字符
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.