TDFANet: Encoding Sequential 4D Radar Point Clouds Using Trajectory-Guided Deformable Feature Aggregation for Place Recognition

Place recognition is essential for achieving closed-loop or global positioning in autonomous vehicles and mobile robots. Despite recent advancements in place recognition using 2D cameras or 3D LiDAR, it remains to be seen how to use 4D radar for place recognition - an increasingly popular sensor for its robustness against adverse weather and lighting conditions. Compared to LiDAR point clouds, radar data are drastically sparser, noisier and in much lower resolution, which hampers their ability to effectively represent scenes, posing significant challenges for 4D radar-based place recognition. This work addresses these challenges by leveraging multi-modal information from sequential 4D radar scans and effectively extracting and aggregating spatio-temporalthis http URLapproach follows a principled pipeline that comprises (1) dynamic points removal and ego-velocity estimation from velocity property, (2) bird's eye view (BEV) feature encoding on the refined point cloud, (3) feature alignment using BEV feature map motion trajectory calculated by ego-velocity, (4) multi-scale spatio-temporal features of the aligned BEV feature maps are extracted andthis http URL-world experimental results validate the feasibility of the proposed method and demonstrate its robustness in handling dynamic environments. Source codes are available.

@article{lu2025_2504.05103,
  title={ TDFANet: Encoding Sequential 4D Radar Point Clouds Using Trajectory-Guided Deformable Feature Aggregation for Place Recognition },
  author={ Shouyi Lu and Guirong Zhuo and Haitao Wang and Quan Zhou and Huanyu Zhou and Renbo Huang and Minqing Huang and Lianqing Zheng and Qiang Shu },
  journal={arXiv preprint arXiv:2504.05103},
  year={ 2025 }
}