# Direct Sparse Mapping

## TL;DR

This paper introduces DSM, a monocular visual SLAM system based on photometric bundle adjustment, capable of maintaining a persistent map that improves reobservation handling and achieves state-of-the-art accuracy on EuRoC datasets.

## Contribution

DSM is the first full monocular SLAM system utilizing PBA with a persistent map for better reobservation management.

## Key findings

- Achieves the most accurate results on EuRoC datasets for a direct method.
- Handles scene reobservations effectively with a persistent map.
- Demonstrates improved accuracy over existing PBA-based systems.

## Abstract

Photometric bundle adjustment, PBA, accurately estimates geometry from video. However, current PBA systems have a temporary map that cannot manage scene reobservations. We present, DSM, a full monocular visual SLAM based on PBA. Its persistent map handles reobservations, yielding the most accurate results up to date on EuRoC for a direct method.