EcoSplat：效率可控的多视图图像前馈三维高斯泼溅
EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images
把「预测多少个高斯基元」变成推理时可调的显式控制变量，用两阶段（像素对齐预训练 + 重要性感知微调）让同一前馈模型在任意基元预算下输出 3DGS 表示，可直接用于显存/带宽受限的渲染与下游任务。
原文依据 the first efficiency-controllable feed-forward 3DGS framework that adaptively predicts the 3D representation for any given target primitive count at inference time
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论前馈三维高斯泼溅（3DGS）实现了高效的单次场景重建，无需逐场景优化即可为新视角合成提供三维表示。然而，现有方法通常逐视图预测像素对齐的基元，在稠密视图设定下会产生过多的基元，且无法显式控制所预测高斯的数量。为此，我们提出 EcoSplat，这是首个效率可控的前馈 3DGS 框架，可在推理时针对任意给定的目标基元数量自适应地预测三维表示。EcoSplat 采用两阶段优化过程：第一阶段为像素对齐高斯训练（PGT），模型在此阶段学习初始基元预测；第二阶段为重要性感知高斯微调（IGF），模型在此阶段学习对基元排序，并根据目标基元数量自适应地调整其参数。在多种稠密视图设定下的大量实验表明，EcoSplat 具有鲁棒性，并在严格的基元数量约束下优于最优方法，因而非常适合灵活的下游渲染任务。代码与项目主页将公开。
英文原文摘要 1215 字符
Feed-forward 3D Gaussian Splatting (3DGS) enables efficient one-pass scene reconstruction, providing 3D representations for novel view synthesis without per-scene optimization. However, existing methods typically predict pixel-aligned primitives per-view, producing an excessive number of primitives in dense-view settings and offering no explicit control over the number of predicted Gaussians. To address this, we propose EcoSplat, the first efficiency-controllable feed-forward 3DGS framework that adaptively predicts the 3D representation for any given target primitive count at inference time. EcoSplat adopts a two-stage optimization process. The first stage is Pixel-aligned Gaussian Training (PGT) where our model learns initial primitive prediction. The second stage is Importance-aware Gaussian Finetuning (IGF) stage where our model learns rank primitives and adaptively adjust their parameters based on the target primitive count. Extensive experiments across multiple dense-view settings show that EcoSplat is robust and outperforms state-of-the-art methods under strict primitive-count constraints, making it well-suited for flexible downstream rendering tasks. Code and project page will be released.