OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness

TL;DR

OpenVO is a new visual odometry framework that robustly estimates ego-motion from monocular dashcam footage under limited input conditions by encoding temporal dynamics and using geometric priors.

Contribution

It introduces a method that explicitly encodes temporal dynamics and leverages geometric priors, improving robustness across varying observation rates and uncalibrated cameras.

Findings

Achieves over 20% performance improvement on major benchmarks.

Reduces errors by 46%-92% under varying observation rates.

Effective for real-world 3D reconstruction and downstream tasks.

Abstract

We introduce OpenVO, a novel framework for Open-world Visual Odometry (VO) with temporal awareness under limited input conditions. OpenVO effectively estimates real-world-scale ego-motion from monocular dashcam footage with varying observation rates and uncalibrated cameras, enabling robust trajectory dataset construction from rare driving events recorded in dashcam. Existing VO methods are trained on fixed observation frequency (e.g., 10Hz or 12Hz), completely overlooking temporal dynamics information. Many prior methods also require calibrated cameras with known intrinsic parameters. Consequently, their performance degrades when (1) deployed under unseen observation frequencies or (2) applied to uncalibrated cameras. These significantly limit their generalizability to many downstream tasks, such as extracting trajectories from dashcam footage. To address these challenges, OpenVO (1) explicitly encodes temporal dynamics information within a two-frame pose regression framework and (2) leverages 3D geometric priors derived from foundation models. We validate our method on three major autonomous-driving benchmarks - KITTI, nuScenes, and Argoverse 2 - achieving more than 20 performance improvement over state-of-the-art approaches. Under varying observation rate settings, our method is significantly more robust, achieving 46%-92% lower errors across all metrics. These results demonstrate the versatility of OpenVO for real-world 3D reconstruction and diverse downstream applications.