AGILE-GS：面向主动三维高斯泼溅的锚点引导快速下一最佳视角选择
AGILE-GS: Anchor-Guided Fast Next-Best-View Selection for Active 3D Gaussian Splatting
查看机构详情
- Lehigh University（理海大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
AGILE-GS提出锚点引导的下一最佳视角选择方法，分离信息搜索与相机选择，通过虚拟锚点优化和贪心提炼候选清单，大幅降低选择延迟，性能匹配或超越现有基线。
中文摘要 AI 辅助
辐射场需要数百个视角，且视角的放置位置与数量同样重要。针对三维高斯泼溅（3DGS）的下一最佳视角（NBV）选择通常会对候选池中的每个视角进行评分并保留一个最优视角。然而，搜索信息与选择相机是两个可分离的问题。我们提出AGILE-GS，一种将两者分离的锚点引导NBV方法。通过黎曼梯度上升在SE(3)上优化一个虚拟锚点姿态，以最大化期望信息增益。该锚点姿态无需可达或位于候选池中；它标记了模型最不确定的位置。候选视角根据锚点的观察几何进行评分，一个贪心的岭杠杆步骤将候选池提炼为一个小型、无冗余的候选清单，无需渲染任何候选视角。该清单有两种使用方式。AGILE-GS取清单中的第一个视角作为下一视角，因此无需为任何候选视角计算Fisher信息。AGILE-GS+计算清单中每个视角的Fisher信息增益并选择最佳视角，从而将昂贵的评估仅应用于少量视角而非整个候选池。在标准基准测试和闭环具身采集中，两种方法均匹配或超越现有基线，同时将选择延迟降低一至两个数量级。
英文摘要
Radiance fields need hundreds of views, and their placement matters as much as their number. Next-best-view (NBV) selection for 3D Gaussian Splatting (3DGS) usually scores every candidate in the pool and keeps one. Searching for information and choosing a camera, however, are separable problems. We present AGILE-GS, an anchor-guided NBV method that separates the two. A virtual anchor pose is optimized on SE(3) by Riemannian gradient ascent on expected information gain. It need not be reachable or in the pool; it marks where the model is most uncertain. Candidates are scored against the anchor's viewing geometry, and a greedy ridge-leverage step distills the pool into a small, non-redundant shortlist without rendering any candidate. The shortlist can be used in two ways. AGILE-GS takes the first view on it as the next view, so no Fisher information is computed for any candidate. AGILE-GS+ computes the Fisher information gain of each shortlisted view and picks the best, so the expensive evaluation runs on a handful of views rather than the whole pool. On standard benchmarks and in closed-loop embodied acquisition, both match or exceed existing baselines while cutting selection latency by one to two orders of magnitude.
