VIDAR: Visual-Inertial Dense Alignment and Reconstruction via a Geometric Foundation Model
This paper introduces VIDAR, a framework for metric dense monocular reconstruction using visual-inertial odometry and Depth Anything 3.
The authors propose a new approach to metric dense monocular reconstruction by combining visual-inertial odometry and a dense monocular foundation model.
Before reading this…
Applications
- →Robotics
- →Computer Vision
To understand this paper, make sure you know these concepts first:
- Understanding of monocular foundation models, visual-inertial odometry, and dense reconstruction.find papers →
Abstract
More Like ThisMonocular 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.