# VIDAR：通过几何基础模型的视觉-惯性稠密对齐与重建

> 原文链接：https://robotics.hellobike.com/papers/2026-07-19-2607-17171
> 频道：papers | 更新日期：2026-07-19 | 标签：arxiv, cs.RO
> 核心摘要：VIDAR将SVO+IMU里程计与Depth Anything 3耦合，在EuRoC和TUM RGB-D验证单目度量稠密重建。

# VIDAR：通过几何基础模型的视觉-惯性稠密对齐与重建

::: v-pre
> 原文链接：[VIDAR: Visual-Inertial Dense Alignment and Reconstruction via a Geometric Foundation Model](https://arxiv.org/abs/2607.17171)（arXiv 2607.17171 · 发布日期：2026-07-19）

**VIDAR: Visual-Inertial Dense Alignment and Reconstruction via a Geometric Foundation Model**

VIDAR将SVO+IMU里程计与Depth Anything 3耦合，在EuRoC和TUM RGB-D验证单目度量稠密重建。

## 核心要点

- 单目基础模型可提供稠密几何，但通常缺乏稳定的度量尺度。
- 视觉-惯性前端作为度量锚，提供相机位姿、尺度和一致世界坐标系。
- Depth Anything 3的局部几何预测跨时间对齐，并融合为全局重建。
- 在EuRoC上，位姿注入将尺度误差降至约1%，解耦混合mean F@0.10达0.676。

**验证范围与局限**：验证范围为EuRoC和TUM RGB-D上的单目度量稠密重建实验。

## 英文摘要 (Abstract)

Monocular foundation models provide dense geometry but usually lack a stable metric scale. This paper presents VIDAR, a visual-inertial dense reconstruction framework that couples SVO+IMU odometry with Depth Anything 3. VIDAR uses the visual-inertial front end as a metric anchor: it provides camera poses, scale, and a consistent world frame for aligning dense foundation-model predictions across time. The foundation model then contributes detailed local geometry that is fused into a global reconstruction. We study both pose-conditioned DA3 and a decoupled alignment strategy. On EuRoC, pose injection reduces scale error to about 1\% and reaches 0.463 mean F@0.10; the decoupled hybrid improves this to 0.676 without ground-truth poses. Results on EuRoC and TUM RGB-D show that VIDAR is a practical route to metric dense monocular reconstruction.

作者：Diyari Mohammed Salih, Lingxiang Hu, Naïma Ait Oufroukh, Fabien Bonardi
:::

## 原始参考来源 (Sources)

- [arXiv 2607.17171：VIDAR: Visual-Inertial Dense Alignment and Reconstruction via a Geometric Foundation Model](https://arxiv.org/abs/2607.17171)