可调控效率的3D高斯点云重建，一次生成即完成
EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images
- 分两阶段训练：先预测初始点，再按目标数量自适应调整
- 在密集视图下仍保持高效，支持任意指定点数约束
- 适合需要灵活控制渲染质量与速度的应用场景
前馈式3D高斯点云（3DGS）实现单次遍历场景重建，无需逐场景优化即可提供新视角合成的3D表示。然而，现有方法通常按视图预测像素对齐的基元，导致密集视图设置下基元数量过多，且无法显式控制预测高斯数量。为此，我们提出EcoSplat，首个支持效率可控的前馈式3DGS框架，可在推理时自适应地为任意目标基元数量生成3D表示。EcoSplat采用两阶段优化流程：第一阶段为像素对齐高斯训练（PGT），模型学习初始基元预测；第二阶段为重要性感知高斯微调（IGF），模型学习基元重要性并根据目标基元数量自适应调整参数。在多个密集视图设置下的大量实验表明，EcoSplat在严格基元数量约束下表现优于当前最优方法，适用于灵活的下游渲染任务。
原文摘要 · Abstract (English)
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.
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。