Selected Publications

[Poinc-cloud based Perception]-[Vision based Perception]-[Trajectory Prediction]-[Full Records] <*Co-First Author; #Corresponding Author>

---

---

Poinc-cloud based Perception:

One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Driving
Huitong Yang, Xuyang Bai, Xinge Zhu#, and Yuexin Ma
IEEE International Conference on Robotics and Automation (ICRA), 2023, ​

BibTex-PDF

@article{yang2023one,
				title={One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Driving},
				author={Yang, Huitong and Bai, Xuyang and Zhu, Xinge and Ma, Yuexin},
				journal={arXiv preprint arXiv:2304.00525},
				year={2023}
			  }
			  }
			  }

See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
Yuhang Lu, Qi Jiang, Runnan Chen, Yuenan Hou, Xinge Zhu, Yuexin Ma
International Conference on Computer Vision (ICCV), 2023, ​

BibTex-PDF

@article{lu2023see,
				title={See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data},
				author={Lu, Yuhang and Jiang, Qi and Chen, Runnan and Hou, Yuenan and Zhu, Xinge and Ma, Yuexin},
				journal={arXiv preprint arXiv:2307.10782},
				year={2023}
			  }
			  }
			  }
			  }

CL3D: Unsupervised domain adaptation for cross-lidar 3d detection
Peng, Xidong and Xinge Zhu and Ma, Yuexin
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023, ​

BibTex-PDF

@inproceedings{peng2023cl3d,
	title={Cl3d: Unsupervised domain adaptation for cross-lidar 3d detection},
	author={Peng, Xidong and Zhu, Xinge and Ma, Yuexin},
	booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
	volume={37},
	number={2},
	pages={2047--2055},
	year={2023}
  }
  }
  }
  }
  }

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
Yuenan Hou, Xinge Zhu, Yuexin Ma, Chen Change Loy, and Yikang Li
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2022, ​
( 1st place in the leaderboard of SemanticKITTI Semantic Segmentation)

BibTex-PDF -GitHub Code

@inproceedings{hou2022point,
	title={Point-to-voxel knowledge distillation for lidar semantic segmentation},
	author={Hou, Yuenan and Zhu, Xinge and Ma, Yuexin and Loy, Chen Change and Li, Yikang},
	booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
	pages={8479--8488},
	year={2022}
  }
  }

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers
Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu and Chiew-Lan Tai
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2022, ​
( 1st place in the leaderboard of NuScenes Tracking.)

BibTex-PDF -GitHub Code

@article{bai2021pointdsc,
	title={{TransFusion}: {R}obust {L}iDAR-{C}amera {F}usion for {3}D {O}bject {D}etection with {T}ransformers},
	author={Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu and Chiew-Lan Tai},
	journal={CVPR},
	year={2022}
  }

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes
Peishan Cong, Xinge Zhu, Feng Qiao, Yiming Ren, Xidong Peng, Yuenan Hou, Lan Xu, Ruigang Yang, Dinesh Manocha, Yuexin Ma
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2022, ​

BibTex-PDF

@article{cong2021stcrowd,
	title={STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes},
	author={Peishan Cong, Xinge Zhu, Feng Qiao, Yiming Ren, Xidong Peng, Yuenan Hou, Lan Xu, Ruigang Yang, Dinesh Manocha, Yuexin Ma},
	journal={CVPR},
	year={2022}
  }

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
Xinge Zhu*, Hui Zhou*, Tai Wang, Fangzhou Hong, Yuexin Ma, Wei Li, Hongsheng Li, Dahua Lin
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2021, ​
(Oral Presentation; 1st place in the leaderboard of SemanticKITTI semantic segmentation (Nov.16 2020).)

BibTex-PDF -GitHub Code

@inproceedings{iccvleveraging,
	  title={Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation},
	  author={Xinge Zhu*, Hui Zhou*, Tai Wang, Fangzhou Hong, Yuexin Ma, Wei Li, Hongsheng Li, Dahua Lin},
	  booktitle={CVPR},
	  year={2021}
	}

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma*, Hongsheng Li, Ruigang Yang, Dahua Lin
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021​
(*Corresponding author)

BibTex-PDF -GitHub Code

@inproceedings{iccvleveraging,
	  title={Cylindrical and asymmetrical 3d convolution networks for lidar-based perception},
	  author={Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma*, Hongsheng Li, Ruigang Yang, Dahua Lin},
	  booktitle={TPAMI},
	  year={2021}
	}

LiDAR-based Panoptic Segmentation via Dynamic Shifting Network
Fangzhou Hong, Hui Zhou, Xinge Zhu, Hongsheng Li, Ziwei Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
(Rank 1st in the public leaderboard of SemanticKITTI Panoptic Segmentation (2020-11-16))

BibTex-PDF -Github Code

@inproceedings{Madelving,
	  title={LiDAR-based Panoptic Segmentation via Dynamic Shifting Network},
	  author={Fangzhou Hong, Hui Zhou, Xinge Zhu, Hongsheng Li, Ziwei Liu},
	  booktitle={CVPR},
	  year={2021}
	}

Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation
Peishan Cong, Xinge Zhu, Yuexin Ma
IEEE International Conference on Multimedia and Expo (ICME), 2021

BibTex-PDF

@inproceedings{Madelving,
	  title={Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation},
	  author={Peishan Cong, Xinge Zhu, Yuexin Ma},
	  booktitle={ICME},
	  year={2021}
	}

SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Xinge Zhu, Yuexin Ma, Tai Wang, Yan Xu, Jianping Shi, Dahua Lin
European Conference on Computer Vision (ECCV), 2020

BibTex-PDF -Github Code

@inproceedings{ssneccv,
	  title={SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds},
	  author={Xinge Zhu, Yuexin Ma, Tai Wang, Yan Xu, Jianping Shi, Dahua Lin},
	  booktitle={ECCV},
	  year={2020}
	}

Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds
Tai Wang, Xinge Zhu , Dahua Lin
Conference on Robot Learning (CoRL), 2020​
(A new voxel representation)

BibTex-PDF - Spotlight Talk

@inproceedings{reconfigvoxel,
	  title={Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds},
	  author={Tai Wang, Xinge Zhu, Dahua Lin},
	  booktitle={CoRL},
	  year={2020}
	}

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li
Conference on Robot Learning (CoRL), 2020

BibTex-PDF

@inproceedings{tang2020local,
	  title={SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks},
	  author={Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li},
	  booktitle={CoRL},
	  year={2020}
	}

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li
IEEE/CVF International Conference on Computer Vision (ICCV), 2019​

BibTex-PDF

@inproceedings{xu2019depth,
	  title={Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints},
	  author={Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li},
	  booktitle={ICCV},
	  year={2019}
	}

---

---

Vision based Perception:

SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation
Xidong Peng, Xinge Zhu, Tai Wang, Yuexin Ma
IEEE Winter Conference on Applications of Computer Vision (WACV), 2022​

BibTex-PDF

@inproceedings{peng2022side,
	  title={SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation},
	  author={Xidong Peng, Xinge Zhu, Tai Wang, Yuexin Ma},
	  booktitle={WACV},
	  year={2022}
	}

AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach
Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Yuexin Ma, Zhe Wang, Jianping Shi
International Journal of Computer Vision (IJCV), 2021​

BibTex-PDF

@inproceedings{song2021ada2,
	  title={AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach},
	  author={Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Yuexin Ma, Zhe Wang, Jianping Shi},
	  booktitle={IJCV},
	  year={2021}
	}

AdaStereo: a simple and efficient approach for adaptive stereo matching
Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Zhe Wang, Jianping Shi
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021​

BibTex-PDF

@inproceedings{song2021ada,
	  title={AdaStereo: a simple and efficient approach for adaptive stereo matching},
	  author={Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Zhe Wang, Jianping Shi},
	  booktitle={CVPR},
	  year={2021}
	}

Probabilistic and geometric depth: Detecting objects in perspective
Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin
Conference on Robot Learning (CoRL), 2021

BibTex-PDF -GitHub Code

@inproceedings{wang2021prob,
	  title={Probabilistic and geometric depth: Detecting objects in perspective},
	  author={Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin},
	  booktitle={CoRL},
	  year={2021}
	}

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin
ICCV Workshop on 3D Object Detection from Images(ICCVW), 2021

(Best Paper Award)

BibTex-PDF -GitHub Code

@inproceedings{wang2021fcos3d,
	  title={FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection},
	  author={Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin},
	  booktitle={ICCVW},
	  year={2021}
	}

Tensor Low-Rank Reconstruction for Semantic Segmentation
Wanli Chen, Xinge Zhu, Ruoqi Sun, Junjun He, Ruiyu Li, Xiaoyong Shen, Bei Yu
European Conference on Computer Vision (ECCV), 2020​

BibTex-PDF -GitHub Code

@inproceedings{chen2020tensor,
	  title={Tensor Low-Rank Reconstruction for Semantic Segmentation},
	  author={Wanli Chen, Xinge Zhu, Ruoqi Sun, Junjun He, Ruiyu Li, Xiaoyong Shen, Bei Yu},
	  booktitle={ECCV},
	  year={2020}
	}

Adapting Object Detectors via Selective Cross-domain Alignment
Xinge Zhu, Jiangmiao Pang, Ceyuan Yang, Jianping Shi, Dahua Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 ​

BibTex-PDF -GitHub Code

@inproceedings{zhu2019adapting,
	  title={Adapting Object Detectors via Selective Cross-domain Alignment},
	  author={Xinge Zhu, Jiangmiao Pang, Ceyuan Yang, Jianping Shi, Dahua Lin},
	  booktitle={CVPR},
	  year={2019}
	}

Not all areas are equal: Transfer learning for semantic segmentation via hierarchical region selection
Ruoqi Sun*, Xinge Zhu*, Chongruo Wu, Chen Huang, Jianping Shi, Lizhuang Ma
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 ​
(Oral Presentation, 5.5% acceptance rate) (*denotes equal contribution)

BibTex-PDF

@inproceedings{run2019notall,
	  title={Not all areas are equal: Transfer learning for semantic segmentation via hierarchical region selection},
	  author={Ruoqi Sun*, Xinge Zhu*, Chongruo Wu, Chen Huang, Jianping Shi, Lizhuang Ma},
	  booktitle={CVPR},
	  year={2019}
	}

Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
Xinge Zhu, Hui Zhou, Ceyuan Yang, Jianping Shi, Dahua Lin
European Conference on Computer Vision (ECCV), 2018.​

BibTex-PDF

@inproceedings{zhu2018pena,
  title={Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation},
  author={Xinge Zhu, Hui Zhou, Ceyuan Yang, Jianping Shi, Dahua Lin},
  booktitle={ECCV},
  year={2018}
}

Generative Adversarial Frontal View to Bird View Synthesis
Xinge Zhu, Zhichao Yin, Jianping Shi, Hongsheng Li, Dahua Lin
International Conference on 3D Vision (3DV), 2018 (Spotlight)​

BibTex-PDF -GitHub Code

@inproceedings{zhu2018gene,
  title={Generative Adversarial Frontal View to Bird View Synthesis},
  author={Xinge Zhu, Zhichao Yin, Jianping Shi, Hongsheng Li, Dahua Lin},
  booktitle={3DV},
  year={2018}
}

---

---

Trajectory Prediction: