Long-term Visual Map Sparsification with Heterogeneous GNN

03/29/2022
by   Ming-Fang Chang, et al.
0

We address the problem of map sparsification for long-term visual localization. For map sparsification, a commonly employed assumption is that the pre-build map and the later captured localization query are consistent. However, this assumption can be easily violated in the dynamic world. Additionally, the map size grows as new data accumulate through time, causing large data overhead in the long term. In this paper, we aim to overcome the environmental changes and reduce the map size at the same time by selecting points that are valuable to future localization. Inspired by the recent progress in Graph Neural Network(GNN), we propose the first work that models SfM maps as heterogeneous graphs and predicts 3D point importance scores with a GNN, which enables us to directly exploit the rich information in the SfM map graph. Two novel supervisions are proposed: 1) a data-fitting term for selecting valuable points to future localization based on training queries; 2) a K-Cover term for selecting sparse points with full map coverage. The experiments show that our method selected map points on stable and widely visible structures and outperformed baselines in localization performance.

READ FULL TEXT

page 1

page 6

page 8

page 11

page 12

research
05/28/2018

Long-term Large-scale Mapping and Localization Using maplab

This paper discusses a large-scale and long-term mapping and localizatio...
research
05/08/2021

Learning to Predict Repeatability of Interest Points

Many robotics applications require interest points that are highly repea...
research
08/12/2020

Optimal to-do list gamification

What should I work on first? What can wait until later? Which projects s...
research
08/08/2018

Map Management for Efficient Long-Term Visual Localization in Outdoor Environments

We present a complete map management process for a visual localization s...
research
08/08/2018

Appearance-Based Landmark Selection for Efficient Long-Term Visual Localization

We present an online landmark selection method for distributed long-term...
research
05/09/2023

ColonMapper: topological mapping and localization for colonoscopy

Mapping and localization in endoluminal cavities from colonoscopies or g...
research
11/29/2018

Visual SLAM with Network Uncertainty Informed Feature Selection

In order to facilitate long-term localization using a visual simultaneou...

Please sign up or login with your details

Forgot password? Click here to reset