DSOL: A Fast Direct Sparse Odometry Scheme

TL;DR

DSOL is an enhanced, faster version of Direct Sparse Odometry that significantly improves processing speed and accuracy for rapid motions, especially on resource-limited devices.

Contribution

The paper introduces algorithmic and implementation improvements to DSO, achieving approximately 5x speedup and enabling higher frame rate processing.

Findings

Speed increased by about 5x on average.

Better results on rapid motions due to higher frame rates.

Open-source implementation available.

Abstract

In this paper, we describe Direct Sparse Odometry Lite (DSOL), an improved version of Direct Sparse Odometry (DSO). We propose several algorithmic and implementation enhancements which speed up computation by a significant factor (on average 5x) even on resource constrained platforms. The increase in speed allows us to process images at higher frame rates, which in turn provides better results on rapid motions. Our open-source implementation is available at https://github.com/versatran01/dsol.