SID-SLAM: Semi-Direct Information-Driven RGB-D SLAM
Alejandro Fontán, Riccardo Giubilato, Laura Oliva-Maza, Javier Civera, Rudolph Triebel
Abstract
This work presents SID-SLAM, a complete SLAM framework for RGB-D cameras. Our main contribution is a semi-direct approach that, for the first time, combines tightly and indistinctly photometric and feature-based image measurements. Additionally, SID-SLAM uses information metrics to reduce the state size with a minimal impact in the accuracy. Our evaluation on several public datasets shows that we achieve state-of-the-art performance regarding accuracy, robustness and computational footprint in CPU real time. In order to facilitate research on semi-direct SLAM, we record the Minimal Texture dataset, composed by RGB-D sequences challenging for current baselines and in which our pipeline excels.
BibTeX
@inproceedings{ral2023_sidslamsemidirec,
title = {SID-SLAM: Semi-Direct Information-Driven RGB-D SLAM},
author = {Alejandro Fontán and Riccardo Giubilato and Laura Oliva-Maza and Javier Civera and Rudolph Triebel},
booktitle = {RA-L 2023},
year = {2023}
}