Air Series Articles Released

Air Series is a collection of articles that are first authored by junior researchers.

This series focuses on a wide variety of topics in robot perception.

Air Series Articles I

AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration.
Bowen Li, Chen Wang, Pranay Reddy, Seungchan Kim, Sebastian Scherer.
European Conference on Computer Vision (ECCV), 2022.
```
@inproceedings{li2021airdet,
  title = {{AirDet}: Few-Shot Detection without Fine-tuning for Autonomous Exploration},
  author = {Li, Bowen and Wang, Chen and Reddy, Pranay and Kim, Seungchan and Scherer, Sebastian},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2022},
  url = {https://arxiv.org/abs/2112.01740},
  code = {https://github.com/sair-lab/AirDet},
  video = {https://youtu.be/n87XtKUjVbE}
}
```
```
Li, Bowen and Wang, Chen and Reddy, Pranay and Kim, Seungchan and Scherer, Sebastian, "AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration," European Conference on Computer Vision (ECCV), 2022.
```
AirObject: A Temporally Evolving Graph Embedding for Object Identification.
Nikhil Varma Keetha, Chen Wang, Yuheng Qiu, Kuan Xu, Sebastian Scherer.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
```
@inproceedings{keetha2021airobject,
  title = {{AirObject}: A Temporally Evolving Graph Embedding for Object Identification},
  author = {Keetha, Nikhil Varma and Wang, Chen and Qiu, Yuheng and Xu, Kuan and Scherer, Sebastian},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
  url = {https://arxiv.org/abs/2111.15150},
  video = {https://youtu.be/WZgn7hMZXhI},
  code = {https://github.com/sair-lab/AirObject},
  website = {https://sairlab.org/airobject/}
}
```
```
Keetha, Nikhil Varma and Wang, Chen and Qiu, Yuheng and Xu, Kuan and Scherer, Sebastian, "AirObject: A Temporally Evolving Graph Embedding for Object Identification," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
```
AirLoop: Lifelong Loop Closure Detection.
Dasong Gao, Chen Wang, Sebastian Scherer.
International Conference on Robotics and Automation (ICRA), 2022.
```
@inproceedings{gao2021lifelong,
  title = {{AirLoop}: Lifelong Loop Closure Detection},
  author = {Gao, Dasong and Wang, Chen and Scherer, Sebastian},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  year = {2022},
  url = {https://arxiv.org/abs/2109.08975},
  code = {https://github.com/sair-lab/AirLoop},
  video = {https://youtu.be/7uYAizKyGgE},
  website = {https://sairlab.org/airloop/}
}
```
```
Gao, Dasong and Wang, Chen and Scherer, Sebastian, "AirLoop: Lifelong Loop Closure Detection," International Conference on Robotics and Automation (ICRA), 2022.
```
AirDOS: Dynamic SLAM benefits from Articulated Objects.
Yuheng Qiu, Chen Wang, Wenshan Wang, Mina Henein, Sebastian Scherer.
International Conference on Robotics and Automation (ICRA), 2022.
```
@inproceedings{qiu2021airdos,
  title = {{AirDOS}: Dynamic SLAM benefits from Articulated Objects},
  author = {Qiu, Yuheng and Wang, Chen and Wang, Wenshan and Henein, Mina and Scherer, Sebastian},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  year = {2022},
  url = {https://arxiv.org/abs/2109.09903},
  code = {https://github.com/sair-lab/airdos},
  video = {https://youtu.be/O1mNIHcfnC0},
  website = {https://sairlab.org/airdos/}
}
```
```
Qiu, Yuheng and Wang, Chen and Wang, Wenshan and Henein, Mina and Scherer, Sebastian, "AirDOS: Dynamic SLAM benefits from Articulated Objects," International Conference on Robotics and Automation (ICRA), 2022.
```
AirCode: A Robust Object Encoding Method.
Kuan Xu, Chen Wang, Chao Chen, Wei Wu, Sebastian Scherer.
IEEE Robotics and Automation Letters (RA-L), 2022.

Accepted to ICRA 2022
```
@article{xu2021aircode,
  title = {{AirCode}: A Robust Object Encoding Method},
  author = {Xu, Kuan and Wang, Chen and Chen, Chao and Wu, Wei and Scherer, Sebastian},
  journal = {IEEE Robotics and Automation Letters (RA-L)},
  year = {2022},
  url = {https://arxiv.org/abs/2105.00327},
  code = {https://github.com/sair-lab/AirCode},
  video = {https://youtu.be/TsdfSVz7hks},
  website = {https://sairlab.org/aircode/},
  addinfo = {Accepted to ICRA 2022}
}
```
```
Xu, Kuan and Wang, Chen and Chen, Chao and Wu, Wei and Scherer, Sebastian, "AirCode: A Robust Object Encoding Method," IEEE Robotics and Automation Letters (RA-L), 2022.
```

Air Series Articles II (To release)

AirRoom: Objects Matter in Room Reidentification.
Runmao Yao, Yi Du, Zhuoqun Chen, Haoze Zheng, Chen Wang.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
```
@inproceedings{yao2025airroom,
  title = {{AirRoom}: Objects Matter in Room Reidentification},
  author = {Yao, Runmao and Du, Yi and Chen, Zhuoqun and Zheng, Haoze and Wang, Chen},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  url = {https://arxiv.org/abs/2503.01130},
  website = {https://sairlab.org/airroom/},
  year = {2025}
}
```
```
Yao, Runmao and Du, Yi and Chen, Zhuoqun and Zheng, Haoze and Wang, Chen, "AirRoom: Objects Matter in Room Reidentification," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
```
AirSLAM: An Efficient and Illumination-Robust Point-Line Visual SLAM System.
Kuan Xu, Yuefan Hao, Shenghai Yuan, Chen Wang, Lihua Xie.
IEEE Transactions on Robotics (T-RO), 2025.

SAIR Lab Selected
```
@article{xu2025airslam,
  title = {{AirSLAM}: An Efficient and Illumination-Robust Point-Line Visual SLAM System},
  author = {Xu, Kuan and Hao, Yuefan and Yuan, Shenghai and Wang, Chen and Xie, Lihua},
  journal = {IEEE Transactions on Robotics (T-RO)},
  year = {2025},
  url = {https://arxiv.org/abs/2408.03520},
  code = {https://github.com/sair-lab/AirSLAM},
  video = {https://youtu.be/5OcR5KeO5nc},
  website = {https://sairlab.org/airslam},
  addendum = {SAIR Lab Selected}
}
```
```
Xu, Kuan and Hao, Yuefan and Yuan, Shenghai and Wang, Chen and Xie, Lihua, "AirSLAM: An Efficient and Illumination-Robust Point-Line Visual SLAM System," IEEE Transactions on Robotics (T-RO), 2025.
```
AirShot: Efficient Few-Shot Detection for Autonomous Exploration.
Zihan Wang, Bowen Li, Chen Wang, Sebastian Scherer.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
```
@inproceedings{wang2024airshot,
  title = {{AirShot}: Efficient Few-Shot Detection for Autonomous Exploration},
  author = {Wang, Zihan and Li, Bowen and Wang, Chen and Scherer, Sebastian},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year = {2024},
  url = {https://arxiv.org/abs/2404.05069}
}
```
```
Wang, Zihan and Li, Bowen and Wang, Chen and Scherer, Sebastian, "AirShot: Efficient Few-Shot Detection for Autonomous Exploration," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
```
AirIMU: Learning Uncertainty Propagation for Inertial Odometry.
Yuheng Qiu, Chen Wang, Xunfei Zhou, Youjie Xia, Sebastian Scherer.
arXiv preprint arXiv:2310.04874, 2024.
```
@article{qiu2023airimu,
  title = {{AirIMU}: Learning Uncertainty Propagation for Inertial Odometry},
  author = {Qiu, Yuheng and Wang, Chen and Zhou, Xunfei and Xia, Youjie and Scherer, Sebastian},
  journal = {arXiv preprint arXiv:2310.04874},
  year = {2024},
  url = {https://arxiv.org/abs/2310.04874},
  code = {https://pypose.org/tutorials/imu/imu_integrator_tutorial}
}
```
```
Qiu, Yuheng and Wang, Chen and Zhou, Xunfei and Xia, Youjie and Scherer, Sebastian, "AirIMU: Learning Uncertainty Propagation for Inertial Odometry," arXiv preprint arXiv:2310.04874, 2024.
```
AirLoc: Object-based Indoor Relocalization.
Aryan, Bowen Li, Sebastian Scherer, Yun-Jou Lin, Chen Wang.
arXiv preprint arXiv:2304.00954, 2024.
```
@article{aryan2023airloc,
  title = {{AirLoc}: Object-based Indoor Relocalization},
  author = {Aryan and Li, Bowen and Scherer, Sebastian and Lin, Yun-Jou and Wang, Chen},
  journal = {arXiv preprint arXiv:2304.00954},
  year = {2024},
  url = {https://arxiv.org/abs/2304.00954},
  video = {https://youtu.be/n6mp6KzGPgs},
  code = {https://github.com/sair-lab/AirLoc},
  website = {https://sairlab.org/airloc/}
}
```
```
Aryan and Li, Bowen and Scherer, Sebastian and Lin, Yun-Jou and Wang, Chen, "AirLoc: Object-based Indoor Relocalization," arXiv preprint arXiv:2304.00954, 2024.
```
AirVO: An Illumination-Robust Point-Line Visual Odometry.
Kuan Xu, Yuefan Hao, Shenghai Yuan, Chen Wang, Lihua Xie.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.

SAIR Lab Selected
```
@inproceedings{xu2023airvo,
  title = {{AirVO}: An Illumination-Robust Point-Line Visual Odometry},
  author = {Xu, Kuan and Hao, Yuefan and Yuan, Shenghai and Wang, Chen and Xie, Lihua},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year = {2023},
  url = {https://arxiv.org/abs/2212.07595},
  code = {https://github.com/sair-lab/AirVO},
  video = {https://youtu.be/YfOCLll_PfU},
  website = {https://sairlab.org/airvo/},
  addendum = {SAIR Lab Selected}
}
```
```
Xu, Kuan and Hao, Yuefan and Yuan, Shenghai and Wang, Chen and Xie, Lihua, "AirVO: An Illumination-Robust Point-Line Visual Odometry," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.
```
AirLine: Efficient Learnable Line Detection with Local Edge Voting.
Xiao Lin, Chen Wang.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.
```
@inproceedings{lin2023airline,
  title = {{AirLine}: Efficient Learnable Line Detection with Local Edge Voting},
  author = {Lin, Xiao and Wang, Chen},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year = {2023},
  url = {https://arxiv.org/abs/2303.16500},
  video = {https://youtu.be/EKDx3Z9qYUQ},
  code = {https://github.com/sair-lab/AirLine},
  website = {https://sairlab.org/airline/}
}
```
```
Lin, Xiao and Wang, Chen, "AirLine: Efficient Learnable Line Detection with Local Edge Voting," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.
```

First Author Information (When work was done)

Bowen Li
- Junior student at Tongji University, China.
- Now: PhD student of CMU RI.
Nikhil Varma Keetha
- Junior student at Indian Institute of Technology Dhanbad.
- Now: PhD student of CMU RI.
Dasong Gao
- Master student at Carnegie Mellon University.
- Now: PhD student of MIT EECS.
Yuheng Qiu
- Undergraduate of Chinese University of Hong Kong.
- Now: PhD student of CMU ME.
Kuan Xu
- Master’s Graduate of Harbin Institute of Technology, China.
- Now: PhD student of NTU EEE.
Xiao Lin
- Freshman at Georgia Institute of Technology.
- Now: Senior student at Georgia Institute of Technology.
Aryan
- Junior student at Delhi Technological University.
- Now: Master’s student of CMU RI.
Zihan Wang
- Junior student at University of Edinburgh.
- Now: Master’s student of CMU RI.
Runmao Yao
- Junior student at Tsinghua University.
- Now: Senior student at Tsinghua University.

Contribution

AirDet: Few-shot Detection without Fine-tunning
- The first practical few-shot object detection method that requires no fine-tunning.
- It achieves even better results than the exhaustively fine-tuned methods (up to 60% improvements).
- Validated on real world sequences from DARPA Subterranean (SubT) challenge.

Only three examples are given for novel object detection without fine-tunning.

AirObject: Temporal Object Embedding
- The first temporal object embedding method.
- It achieves the state-of-the-art performance for video object identification.
- Robust to severe occlusion, perceptual aliasing, viewpoint shift, deformation, and scale transform.
- Project Page: https://sairlab.org/airobject

AirDOS: Dynamic Object-aware SLAM (DOS) system
- The first DOS system showing that camera pose estimation can be improved by incorporating dynamic articulated objects.
- Establish 4-D dynamic object maps.
- Project Page: https://sairlab.org/airdos

Dynamic Objects can correct the camera pose estimation.

AirLoop: Lifelong Learning for Robots
- The first lifelong learning method for loop closure detection.
- Model incremental improvement even after deployment.
- Project Page: https://sairlab.org/airloop

The model is able to correct previously made mistakes after learning more environments.

AirCode: Robust Object Encoding
- The first deep point-based object encoding for single image.
- It achieves the state-of-the-art performance for object re-identification.
- Robust to viewpoint shift, object deformation, and scale transform.
- Project Page: https://sairlab.org/aircode

More information can be found at the research page.