Xingguang (Starry) Zhong

Xingguang Zhong

PhD Student

Contact:
Email: zhong@nulligg.uni-bonn.de
Tel: +49 – 228 – 73 – 29 01
Fax: +49 – 228 – 73 – 27 12
Office: Nussallee 15, EG, room 0.013

Address:
University of Bonn
Photogrammetry, IGG
Nussallee 15
53115 Bonn

Profiles: Google Scholar | Github

Research Interests

SLAM
Computer Vision
Robot Navigation

Short CV

Xingguang Zhong is a PhD student at the Photogrammetry & Robotics Lab at the University of Bonn since November 2021. He received his Master’s degree in mechatronics engineering and Bachelor’s degree in mechanical engineering.

Publications

2024

X. Zhong, Y. Pan, C. Stachniss, and J. Behley, “3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation,” in Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2024.
[BibTeX] [PDF]
```
@inproceedings{zhong2024cvpr,
author = {X. Zhong and Y. Pan and C. Stachniss and J. Behley},
title = {{3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation}},
booktitle = cvpr,
year = 2024,
}
```

Y. Pan, X. Zhong, L. Wiesmann, T. Posewsky, J. Behley, and C. Stachniss, “PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency,” arXiv Preprint, vol. arXiv:2401.09101, 2024.
[BibTeX] [PDF] [Code]

Accurate and robust localization and mapping are essential components for most autonomous robots. In this paper, we propose a SLAM system for building globally consistent maps, called PIN-SLAM, that is based on an elastic and compact point-based implicit neural map representation. Taking range measurements as input, our approach alternates between incremental learning of the local implicit signed distance field and the pose estimation given the current local map using a correspondence-free, point-to-implicit model registration. Our implicit map is based on sparse optimizable neural points, which are inherently elastic and deformable with the global pose adjustment when closing a loop. Loops are also detected using the neural point features. Extensive experiments validate that PIN-SLAM is robust to various environments and versatile to different range sensors such as LiDAR and RGB-D cameras. PIN-SLAM achieves pose estimation accuracy better or on par with the state-of-the-art LiDAR odometry or SLAM systems and outperforms the recent neural implicit SLAM approaches while maintaining a more consistent, and highly compact implicit map that can be reconstructed as accurate and complete meshes. Finally, thanks to the voxel hashing for efficient neural points indexing and the fast implicit map-based registration without closest point association, PIN-SLAM can run at the sensor frame rate on a moderate GPU. Codes will be available at: https://github.com/PRBonn/PIN_SLAM.

@article{pan2024arxiv,
author = {Y. Pan and X. Zhong and L. Wiesmann and T. Posewsky and J. Behley and C. Stachniss},
title = {{PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency}},
journal = arxiv,
year = 2024,
volume = {arXiv:2401.09101},
url = {http://arxiv.org/pdf/2401.09101v1},
abstract = {Accurate and robust localization and mapping are essential components for most autonomous robots. In this paper, we propose a SLAM system for building globally consistent maps, called PIN-SLAM, that is based on an elastic and compact point-based implicit neural map representation. Taking range measurements as input, our approach alternates between incremental learning of the local implicit signed distance field and the pose estimation given the current local map using a correspondence-free, point-to-implicit model registration. Our implicit map is based on sparse optimizable neural points, which are inherently elastic and deformable with the global pose adjustment when closing a loop. Loops are also detected using the neural point features. Extensive experiments validate that PIN-SLAM is robust to various environments and versatile to different range sensors such as LiDAR and RGB-D cameras. PIN-SLAM achieves pose estimation accuracy better or on par with the state-of-the-art LiDAR odometry or SLAM systems and outperforms the recent neural implicit SLAM approaches while maintaining a more consistent, and highly compact implicit map that can be reconstructed as accurate and complete meshes. Finally, thanks to the voxel hashing for efficient neural points indexing and the fast implicit map-based registration without closest point association, PIN-SLAM can run at the sensor frame rate on a moderate GPU. Codes will be available at: https://github.com/PRBonn/PIN_SLAM.},
codeurl = {https://github.com/PRBonn/PIN_SLAM}
}

2023

X. Zhong, Y. Pan, J. Behley, and C. Stachniss, “SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2023.
[BibTeX] [PDF] [Code] [Video]

@inproceedings{zhong2023icra,
author = {Zhong, Xingguang and Pan, Yue and Behley, Jens and Stachniss, Cyrill},
title = {{SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations}},
booktitle = icra,
year = 2023,
codeurl = {https://github.com/PRBonn/SHINE_mapping},
videourl = {https://youtu.be/jRqIupJgQZE},
}