Abstract
This work presents UNO, a unified monocular visual odometry framework that enables robust and adaptable pose estimation across diverse environments, platforms, and motion patterns. Unlike traditional methods that rely on deployment-specific tuning or predefined motion priors, our approach generalizes effectively across a wide range of real-world scenarios, including autonomous vehicles, aerial drones, mobile robots, and handheld devices. To this end, we introduce a Mixture-of-Experts strategy for local state estimation, with several specialized decoders that each handle a distinct class of ego-motion patterns. Moreover, we introduce a fully differentiable Gumbel-Softmax module that constructs a robust inter-frame correlation graph, selects the optimal expert decoder, and prunes erroneous estimates. These cues are then fed into a unified back-end that combines pre-trained, scale-independent depth priors with a lightweight bundling adjustment to enforce geometric consistency. We extensively evaluate our method on three major benchmark datasets: KITTI (outdoor/autonomous driving), EuRoC-MAV (indoor/aerial drones), and TUM-RGBD (indoor/handheld), demonstrating state-of-the-art performance.
Abstract (translated)
这项工作提出了UNO,一个统一的单目视觉里程计框架,能够在不同的环境、平台和运动模式下实现稳健且适应性强的姿态估计。与传统的依赖于特定部署调整或预定义运动先验的方法不同,我们的方法能够广泛适用于各种现实场景,包括自主车辆、空中无人机、移动机器人以及手持设备。为此,我们引入了专家混合策略来进行局部状态估计,并设计了几种专门处理不同类型自运动模式的解码器。此外,我们还提出了一种完全可微化的Gumbel-Softmax模块来构建稳健的帧间相关性图,选择最优专家解码器并修剪错误估算结果。这些线索随后被输入到一个统一的后端中,该后端结合了预训练且尺度无关的深度先验和轻量级捆绑调整以强制执行几何一致性。我们在三个主要基准数据集上对我们的方法进行了广泛评估:KITTI(户外/自动驾驶)、EuRoC-MAV(室内/空中无人机)和TUM-RGBD(室内/手持设备),展示了最先进的性能水平。
URL
https://arxiv.org/abs/2506.07013