RGBDS-SLAM

RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting
Zhenzhong Cao¹²³, Jingtai Liu¹²³

Institute of Robotics and Automatic Information System, Nankai University, Tianjin 300350, China¹
Tianjin Key Laboratory of Intelligent Robotics, Tianjin 300350, China²
TBI center, Nankai University, Tianjin 300350, China³

Our code will be open source soon!

Prerequisites

# You can configure the environment required by our code by building a docker image
docker build -t rgbds-slam:v1 .

Results Download

You can download our results in google drive: results

Results Evaluation

# You can reimplement our results using the sh script file in the evaluation folder

./evl_metrics.sh

./evl_depth.sh

./evl_mIoU.sh

./evl_ate.sh

./evl_time.sh

Acknowledgement

Our work is based on Photo-SLAM, and by using or modifying this work further, you agree to adhere to their terms of usage and include the license file. We extend our sincere gratitude for their outstanding contributions.

Citation

@article{cao2024rgbds,
  title={RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting},
  author={Cao, Zhenzhong},
  journal={arXiv preprint arXiv:2412.01217},
  year={2024}
}