Unlocking Generalization Power in LiDAR Point Cloud Registration, CVPR 2025 Highlight
Zhenxuan Zeng , Qiao Wu, Xiyu Zhang, Lin Yuanbo Wu, Pei An, Jiaqi Yang, Ji Wang, Peng Wang
paper / bibtex / code

@article{zeng2025unlocking,
  title={Unlocking Generalization Power in LiDAR Point Cloud Registration},
  author={Zeng, Zhenxuan and Wu, Qiao and Zhang, Xiyu and Wu, Lin Yuanbo and An, Pei and Yang, Jiaqi and Wang, Ji and Wang, Peng},
  journal={arXiv preprint arXiv:2503.10149},
  year={2025}
}

          


          
          

SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network, AAAI 2025
Ziming Nie, Qiao Wu, Chenlei Lv, Siwen Quan, Zhaoshuai Qi, Muze Wang, Jiaqi Yang
paper / bibtex / code

@article{nie2025spu,
  title={SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network},
  author={Nie, Ziming and Wu, Qiao and Lv, Chenlei and Quan, Siwen and Qi, Zhaoshuai and Wang, Muze and Yang, Jiaqi},
  journal={arXiv preprint arXiv:2502.19452},
  year={2025}
}

          


          
          

3D Single-object Tracking in Point Clouds with High Temporal Variation, ECCV 2024
Qiao Wu, Kun Sun, Pei An, Mathieu Salzmann, Yanning Zhang, Jiaqi Yang

We explore a new task in 3D SOT, and presented the first 3D SOT framework for high temporal variation scenarios, HVTrack. Its three main components, RPM, BEA, and CPA, allow HVTrack to achieve robustness to point cloud variations, similar object distractions, and background noise. HVTrack significantly outperforms existing trackers in high temporal variation scenarios (11.3% and 15.7% improvement in success and precision at medium intensity of variation). The performance gap between our HVTrack and existing trackers widens as variations are exacerbated. It also surpasses existing methods in both nuScenes and Waymo benchmarks of regular tracking, achieving SOTA.

@InProceedings{Wu_2024_HVTrack,
  author    = {Wu, Qiao and Sun, Kun and An, Pei and Salzmann, Mathieu and Zhang, Yanning and Yang, Jiaqi},
  title     = {3D Single-object Tracking in Point Clouds with High Temporal Variation},
  journal={arXiv preprint arXiv:2408.02049},
  year={2024}
}

          


          
          

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency, ICCV 2023
Qiao Wu, Jiaqi Yang, Kun Sun, Chu'ai Zhang, Yanning Zhang, Mathieu Salzmann

We propose the first semi-supervised approach to 3D Single Object Tracking. Our method, MixCycle, uses self and forward-backward cycle-consistency for supervision, and introduce a data augmentation strategy named SOTMixup to improve the tracker's robustness to point cloud diversity. It is generalizes to appearance matching-based trackers.

@InProceedings{Wu_2023_MixCycle,
  author    = {Wu, Qiao and Yang, Jiaqi and Sun, Kun and Zhang, Chu'ai and Zhang, Yanning and Salzmann, Mathieu},
  title     = {MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  year      = {2023},
  pages     = {13956-13966}
}

          


          
          

MAC: Maximal Cliques for 3D Registration, TPAMI 2024
Jiaqi Yang, Xiyu Zhang, Peng Wang, Yulan Guo, Kun Sun, Qiao Wu, Shikun Zhang, Yanning Zhang

This paper presents a 3D registration method with maximal cliques (MAC) for 3D point cloud registration (PCR). The key insight is to loosen the previous maximum clique constraint and mine more local consensus information in a graph for accurate pose hypotheses generation. In addition, we present a variant of MAC if given overlap prior, called MAC-OP. Extensive experiments demonstrate that both MAC and MAC-OP effectively increase registration recall, outperform various state-of-the-art methods, and boost the performance of deep-learned methods.

@article{yang2024mac,
  title={MAC: Maximal Cliques for 3D Registration},
  author={Yang, Jiaqi and Zhang, Xiyu and Wang, Peng and Guo, Yulan and Sun, Kun and Wu, Qiao and Zhang, Shikun and Zhang, Yanning},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2024},
  publisher={IEEE}
}