# Hybrid Camera Pose Estimation with Online Partitioning for SLAM

## TL;DR

This paper introduces a real-time hybrid camera pose estimation framework for SLAM that uses dynamic partitioning and motion averaging to improve accuracy and efficiency over traditional fixed-size methods.

## Contribution

It proposes a novel dynamic partitioning scheme and integrates motion averaging into monocular SLAM, enhancing local and global pose estimation accuracy.

## Key findings

- Significantly improves local bundle adjustment accuracy
- Enhances global camera motion alignment efficiency
- Outperforms conventional SLAM approaches on benchmarks

## Abstract

This paper presents a hybrid real-time camera pose estimation framework with a novel partitioning scheme and introduces motion averaging to monocular Simultaneous Localization and Mapping (SLAM) systems. Breaking through the limitations of fixed-size temporal partitioning in many conventional SLAM pipelines, our approach significantly improves the accuracy of local bundle adjustment by gathering spatially-strongly-connected cameras into each block. With the dynamic initialization using intermediate computation values, \XL{we improve the Levenberg-Marquardt solver to further enhance the efficiency of the local optimization.} Moreover, the dense data association between blocks by our co-visibility-based partitioning enables us to explore and implement motion averaging to efficiently align the blocks globally, updating camera motion estimations on-the-fly. Experiments on benchmarks convincingly demonstrate the practicality and robustness of our proposed approach by significantly outperforming conventional approaches.