Direct Visual-Inertial Odometry with Semi-Dense Mapping

TL;DR

This paper introduces a direct visual-inertial odometry system that combines dense visual tracking and IMU data in a tightly-coupled optimization framework, improving pose estimation and semi-dense map reconstruction.

Contribution

It presents a novel tightly-coupled nonlinear optimization method integrating direct dense tracking with IMU pre-integration for improved odometry.

Findings

Achieves competitive accuracy in indoor scenes

Effectively suppresses scale drift with IMU constraints

Demonstrates robustness on real-world datasets

Abstract

The paper presents a direct visual-inertial odometry system. In particular, a tightly coupled nonlinear optimization based method is proposed by integrating the recent advances in direct dense tracking and Inertial Measurement Unit (IMU) pre-integration, and a factor graph optimization is adapted to estimate the pose of the camera and rebuild a semi-dense map. Two sliding windows are maintained in the proposed approach. The first one, based on Direct Sparse Odometry (DSO), is to estimate the depths of candidate points for mapping and dense visual tracking. In the second one, measurements from the IMU pre-integration and dense visual tracking are fused probabilistically using a tightly-coupled, optimization-based sensor fusion framework. As a result, the IMU pre-integration provides additional constraints to suppress the scale drift induced by the visual odometry. Evaluations on real-world benchmark datasets show that the proposed method achieves competitive results in indoor scenes.