UNO: Unified Self-Supervised Monocular Odometry for Platform-Agnostic Deployment

TL;DR

UNO is a versatile monocular visual odometry framework that adapts across various platforms and environments by using a mixture-of-experts approach, a differentiable selection module, and a unified back-end for robust pose estimation.

Contribution

It introduces a platform-agnostic monocular odometry method with a mixture-of-experts strategy and a differentiable expert selection mechanism for improved generalization.

Findings

Achieves state-of-the-art results on KITTI, EuRoC-MAV, and TUM-RGBD datasets.

Effectively handles diverse ego-motion patterns across different platforms.

Demonstrates robustness and adaptability in real-world scenarios.

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.