嵌套式高斯溅射

摘要

可调节渲染保真度的单模型场景绘制能力（即细节层次/LoD）对三维高斯泼溅（3DGS）的实际部署至关重要。现有离散式LoD方法仅能提供有限的操作点，而并发的连续LoD方法虽能实现更平滑的缩放，但在全容量渲染时往往出现明显质量下降，使得LoD成为代价高昂的设计决策。我们提出套娃式高斯泼溅（MGS），该训练框架可在不牺牲全容量渲染质量的前提下，为标准3DGS管线实现连续LoD。MGS通过学得一组有序的高斯分布，使得渲染任意前缀（即前k个泼溅点）都能生成连贯的重建结果，其保真度随预算增加而平滑提升。我们的核心思路是随机预算训练：每次迭代采样随机泼溅预算，同时优化对应前缀和完整高斯集合。该策略仅需两次前向传播且无需改动网络架构。在四个基准测试和六种基线方法上的实验表明，MGS在保持主干网络全容量性能的同时，可实现单模型内连续的速度-质量权衡。针对排序策略、训练目标和模型容量的广泛消融实验进一步验证了设计有效性。

English

The ability to render scenes at adjustable fidelity from a single model, known as level of detail (LoD), is crucial for practical deployment of 3D Gaussian Splatting (3DGS). Existing discrete LoD methods expose only a limited set of operating points, while concurrent continuous LoD approaches enable smoother scaling but often suffer noticeable quality degradation at full capacity, making LoD a costly design decision. We introduce Matryoshka Gaussian Splatting (MGS), a training framework that enables continuous LoD for standard 3DGS pipelines without sacrificing full-capacity rendering quality. MGS learns a single ordered set of Gaussians such that rendering any prefix, the first k splats, produces a coherent reconstruction whose fidelity improves smoothly with increasing budget. Our key idea is stochastic budget training: each iteration samples a random splat budget and optimises both the corresponding prefix and the full set. This strategy requires only two forward passes and introduces no architectural modifications. Experiments across four benchmarks and six baselines show that MGS matches the full-capacity performance of its backbone while enabling a continuous speed-quality trade-off from a single model. Extensive ablations on ordering strategies, training objectives, and model capacity further validate the designs.