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.

翻译：从单一模型以可调整保真度渲染场景的能力，即细节层次（LoD），对于3D高斯喷溅（3DGS）的实际部署至关重要。现有离散LoD方法仅暴露有限的操作点，而同步连续LoD方法虽能实现更平滑的缩放，但往往在全容量下出现显著质量下降，使得LoD成为代价高昂的设计决策。我们提出玛特罗什卡高斯喷溅（MGS），一种训练框架，可为标准3DGS流程提供连续LoD，且不牺牲全容量渲染质量。MGS学习单一有序高斯集合，使得渲染任意前缀（前k个喷溅点）时，能产生保真度随预算增加而平滑提升的连贯重建。我们的核心思想是随机预算训练：每次迭代采样随机喷溅预算，并同时优化对应前缀与全集。该策略仅需两次前向传播，且无需修改架构。在四个基准测试与六个基线方法上的实验表明，MGS在实现全容量性能匹配的同时，支持从单一模型获取连续速度-质量权衡。关于排序策略、训练目标与模型容量的广泛消融实验进一步验证了该设计。