UniMetric：面向视觉几何基础模型的通用度量尺度恢复方法
UniMetric: Universal Metric Scale Recovery for Visual Geometry Foundation Models
AI总结：
UniMetric是一种通用无训练的度量尺度恢复框架，通过结合视觉语言模型的物体高度先验，在MetricBench数据集上显著降低9种几何基础模型的深度、重建及轨迹误差，提升了各模型的度量尺度恢复性能。
摘要：
多模态基础模型的最新进展，以GPT-6 Astra为代表，为通用具身推理与规划带来了前景。利用互联网视频进行具身预训练需要可靠的物理尺度标注，但视觉几何基础模型（GFM）在恢复场景结构与相机运动时往往无法获得可靠的度量尺度。本文表明，常见物体的不确定尺寸先验可共同约束重建的共享尺度。基于该见解，我们提出UniMetric，这是一种无需额外传感器或特定任务度量监督、适用于几何基础模型的通用且无需训练的度量尺度恢复框架。具体而言，Metric Prior Acquisition（度量先验获取）模块从视觉语言模型（VLM）中提取物体高度区间；Semantic-Geometric Alignment（语义-几何对齐）模块在每一帧中沿估计的支撑面法线测量重建物体高度，并将先验转换为尺度区间；Global Scale Recovery（全局尺度恢复）模块通过凸目标函数协调这些区间，当区间重叠时生成共同可行的尺度，否则生成唯一折中尺度。估计的序列级尺度被统一应用于重建点与相机平移。利用真实VLM先验的对照实验表明，结合观测结果可在精确相对物体高度下提升尺度准确性。为在无真实尺度对齐的情况下评估GFM重建的度量准确性，我们引入MetricBench，涵盖12个具身、驾驶及路边子集，均带有传感器衍生的真实值。在9种几何基础模型上，UniMetric将平均深度Abs Rel、重建Chamfer距离及轨迹误差分别降低54.2%、83.8%和65.6%，在套件层面的所有三个任务上均提升了每个模型。我们发布了UniMetric代码与MetricBench数据集。
英文摘要：
Recent advances in multimodal foundation models, exemplified by GPT-6 Astra, raise the prospect of general-purpose embodied reasoning and planning. Using Internet videos for embodied pretraining calls for reliable physical-scale annotations. Yet visual geometry foundation models often recover scene structure and camera motion without reliable metric scale. We show that uncertain size priors of familiar objects can jointly constrain a reconstruction's shared scale. Building on this insight, we present UniMetric, a universal and training-free metric scale recovery framework for geometry foundation models, without additional sensors or task-specific metric supervision. Specifically, Metric Prior Acquisition elicits object height intervals from a vision-language model. Semantic-Geometric Alignment measures reconstructed object heights along the estimated support-surface normal in each frame and converts the priors into scale intervals. Global Scale Recovery reconciles these intervals through a convex objective, yielding a jointly feasible scale when they overlap and a unique compromise otherwise. The estimated sequence-level scale is applied uniformly to reconstructed points and camera translations. Controlled experiments with real VLM priors show that combining observations improves scale accuracy with exact relative object heights. To evaluate metric accuracy on GFM reconstructions without ground-truth scale alignment, we introduce MetricBench, covering twelve embodied, driving, and roadside subsets with sensor-derived ground truth. Across nine geometry foundation models, UniMetric reduces mean depth Abs Rel, reconstruction Chamfer distance, and trajectory error by 54.2%, 83.8%, and 65.6%, respectively, improving every model on all three tasks at the suite level. We release the UniMetric code and MetricBench data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
