OpenVO：具有时间动态意识的开放世界视觉里程计
OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness
AI总结：
OpenVO通过时间动态信息编码和3D几何先验，提升在有限输入条件下对单目行车记录仪视频的现实尺度自我运动估计，实现鲁棒轨迹数据集构建。
摘要：
我们介绍了OpenVO，一种新的开放世界视觉里程计（VO）框架，能够在有限输入条件下考虑时间动态。OpenVO有效地从单目行车记录仪视频中估计现实尺度的自我运动，具有变化的观测率和未校准相机，从而能够从罕见驾驶事件记录中构建稳健的轨迹数据集。现有VO方法在固定观测频率（例如10Hz或12Hz）上训练，完全忽略了时间动态信息。许多先前方法还需要校准的相机，具有已知的内参。因此，当（1）在未见过的观测频率下部署或（2）应用于未校准的相机时，其性能会下降。这些显著限制了它们在许多下游任务中的通用性，例如从行车记录仪视频中提取轨迹。为了解决这些挑战，OpenVO（1）在双帧姿态回归框架中显式编码时间动态信息，并（2）利用从基础模型中衍生的3D几何先验。我们在三个主要自动驾驶基准测试中验证了我们的方法——KITTI、nuScenes和Argoverse 2，相对于最先进的方法，实现了超过20%的性能提升。在变化的观测率设置下，我们的方法显著更鲁棒，在所有指标上实现了46%-92%的误差降低。这些结果展示了OpenVO在现实世界3D重建和多样下游应用中的通用性。
英文摘要：
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.
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。
