Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry

TL;DR

This paper introduces a self-supervised, geometry-guided initialization method for monocular visual odometry that enhances robustness and accuracy, especially in challenging outdoor scenarios with large motions and dynamic objects.

Contribution

It proposes leveraging a frozen large-scale pre-trained monocular depth estimator to improve dense SLAM initialization without additional fine-tuning.

Findings

Significant improvements on KITTI odometry benchmark.

Enhanced robustness in large motion and dynamic object scenarios.

Effective initialization method for dense SLAM models.

Abstract

Monocular visual odometry is a key technology in various autonomous systems. Traditional feature-based methods suffer from failures due to poor lighting, insufficient texture, and large motions. In contrast, recent learning-based dense SLAM methods exploit iterative dense bundle adjustment to address such failure cases, and achieve robust and accurate localization in a wide variety of real environments, without depending on domain-specific supervision. However, despite its potential, the methods still struggle with scenarios involving large motion and object dynamics. In this study, we diagnose key weaknesses in a popular learning-based dense SLAM model (DROID-SLAM) by analyzing major failure cases on outdoor benchmarks and exposing various shortcomings of its optimization process. We then propose the use of self-supervised priors leveraging a frozen large-scale pre-trained monocular depth estimator to initialize the dense bundle adjustment process, leading to robust visual odometry without the need to fine-tune the SLAM backbone. Despite its simplicity, the proposed method demonstrates significant improvements on KITTI odometry, as well as the challenging DDAD benchmark.