Scale-Consistent Monocular Fisheye Visual Odometry via Spherical Bundle Adjustment-Guided Unsupervised Depth Learning
Overview
This research introduces S$^2$D-FVO, a monocular fisheye visual odometry framework that combines spherical bundle adjustment with unsupervised depth learning to improve scale consistency and depth estimation accuracy. The method uses tangent-space angular reprojection residuals derived from the spherical logarithmic map to handle fisheye distortion and integrates a median depth-based scale regularization term. Experiments on multiple public datasets and two newly collected large-scale datasets show that S$^2$D-FVO outperforms existing approaches in depth and trajectory estimation across different camera models.
Generated from attributed reports · Updated 4 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalScale-Consistent Monocular Fisheye Visual Odometry via Spherical Bundle Adjustment-Guided Unsupervised Depth Learning
This research introduces S$^2$D-FVO, a monocular fisheye visual odometry framework that combines spherical bundle adjustment with unsupervised depth learning to improve scale consistency and depth estimation accuracy. The method uses tangent-space angular reprojection residuals derived from the spherical logarithmic map to handle fisheye distortion and integrates a median depth-based scale regularization term. Experiments on multiple public datasets and two newly collected large-scale datasets show that S$^2$D-FVO outperforms existing approaches in depth and trajectory estimation across different camera models.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).