Jin Xie 谢晋

alt text 

School of Intelligence Science and Technology,
Nanjing University, Suzhou Campus,
No. 1520, Taihu Avenue, Huqiu District,
Suzhou, China
Email: csjxie [@] nju [DOT] edu [DOT] cn

About me

I am currently a Professor, Nanjing University. I was a research scientist in the Department of Electrical and Computer Engineering, New York University Abu Dhabi and New York University Tandon School of Engineering. I did my Ph.D study in the Department of Computing, Hong Kong Polytechnic University, under the supervision of Prof. Lei Zhang. Here is my full CV.

I am always looking for self-motivated and talent undergraduate/master/Ph.D students to work with me.


I mainly focus on 3D computer vision and its applications on autonomous driving and robotic manipulation, which lie at the intersection of machine learning, computer vision, computer graphics and robotics. My research goal aims to enable robotics to automatically perceive, understand, simulate 3D world and interact with 3D world from image, video and point cloud. Specifically, my research interests fall into 3D low-level imaging, 2D/3D scene understanding, 3D object navigation and planning, 2D/3D object and scene generation, 6D pose estimation and grasping for interaction, etc. I am also interested in vision foundation models and generative models. My recent focus includes:

  • 3D scene understanding lifted with 2D vision foundation models and large language models

  • 3D object and scene generation, including the generation of autonomous driving scene and human-scene interacton

  • Large language models guided object navigation and planning.

Find out more

Recent Publications

  1. Can Xu, Yuehui Han, Rui Xu, Le Hui, Yaqi Shen, Jin Xie and Jian Yang, " Multi-attribute Interactions Matter for 3D Visual Grounding", CVPR 2024. [arxiv] [code]

  2. Yun Zhu, Le Hui, Yaqi Shen and Jin Xie, " SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection", AAAI 2024. [arxiv] [code]

  3. Haobo Jiang, Mathieu Salzmann, Zheng Dang, Jin Xie and Jian Yang , " SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation", NeurIPS 2023. [arxiv] [code]

  4. Haobo Jiang, Zheng Dang, Shuo Gu, Jin Xie, Mathieu Salzmann and Jian Yang, " Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation", ICCV 2023. [pdf] [code]

  5. Le Hui, Linghua Tang, Yuchao Dai, Jin Xie and Jian Yang, "Efficient LiDAR Point Cloud Oversegmentation Network", ICCV 2023. [pdf] [code]

  6. Yaqi Shen, Le Hui, Jin Xie and Jian Yang, "Self-supervised 3D Scene Flow Estimation Guided by Superpoints", CVPR 2023. [arxiv] [code]

  7. Haobo Jiang, Zheng Dang, Zhen Wei, Jin Xie, Jian Yang and Mathieu Salzmann, "Robust Outlier Rejection for 3D Registration with Variational Bayes", CVPR 2023. [arxiv] [code]

  8. Haobo Jiang, Kaihao Lan, Le Hui, Guanyu Li, Jin Xie, Shangbing Gao and Jian Yang, "Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking", IEEE Trans. on Neural Network and Learning Systems. [arxiv] [code]

  9. Le Hui, Linghua Tang, Yaqi Shen, Jin Xie and Jian Yang, "Learning Superpoint Graph Cut for 3D Instance Segmentation", NeurIPS 2022. [pdf] [code]

  10. Le Hui, Lingpeng Wang, Linghua Tang, Kaihao Lan, Jin Xie and Jian Yang, "3D Siamese Transformer Network for Single Object Tracking on Point Clouds", ECCV 2022. [arxiv] [code]

  11. Mu He, Le Hui, Yikai Bian, Jian Ren, Jin Xie and Jian Yang, "RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation", ECCV 2022. [arxiv] [code]

  12. Yuehui Han, Le Hui, Haobo Jiang, Jianjun Qian and Jin Xie, "Generative Subgraph Contrast for Self-Supervised Graph Representation Learning", ECCV 2022. [arxiv] [code]

  13. Yikai Bian, Le Hui, Jianjun Qian and Jin Xie, "Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching", IROS 2022. [arxiv] [code]

  14. Rui Xu, Zongyan Han, Le Hui, Jianjun Qian and Jin Xie, "Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval", AAAI 2022. [arxiv] [code]

  15. Yaqi Shen, Le Hui, Haobo Jiang, Jin Xie and Jian Yang, "Reliable Inlier Evaluation for Unsupervised Point Cloud Registration", AAAI 2022.[arxiv] [code]

  16. Le Hui, Mingmei Cheng, Jin Xie, Jian Yang and Ming-Ming Cheng, "Efficient 3D Point Cloud Feature Learning for Large-scale Place Recognition", IEEE Trans. on Image Processing, 2022.[arxiv] [code]

  17. Le Hui, Lingpeng Wang, Mingmei Cheng, Jin Xie and Jian Yang, "3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds", NeurIPS 2021. [arxiv] [code]

  18. Le Hui, Jia Yuan, Mingmei Cheng, Jin Xie, Xiaoya Zhang and Jian Yang, "Superpoint Network for Point Cloud Oversegmetation", ICCV 2021. [pdf] [code]

  19. Le Hui, Hang Yang, Mingmei Cheng, Jin Xie and Jian Yang, "Pyramid Point Cloud Transformer for Large-scale Place Recognition", ICCV 2021. [pdf] [code]

  20. Haobo Jiang, Yaqi Shen, Jin Xie, Jun Li, Jianjun Qian and Jian Yang, "Sampling Network Guided Cross-entropy Method for Unsupervised Point Cloud Registration", ICCV 2021. [arxiv] [code]

  21. Yifan Zhao, Le Hui and Jin Xie, "SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering", ACM Multimedia 2021. [arxiv] [code]

  22. Haobo Jiang, Jin Xie, Jianjun Qian and Jian Yang, "Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration", IJCAI 2021. [arxiv]

  23. Haobo Jiang, Jin Xie and Jian Yang, "Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks", AAAI 2021. [pdf] [supp] [code]

  24. Mingmei Cheng, Le Hui, Jin Xie and Jian Yang, "SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network", AAAI 2021. [pdf] [code]

  25. Le Hui, Rui Xu, Jin Xie, Jianjun Qian and Jian Yang, "Progressive Point Cloud Deconvolution Generation Network", ECCV 2020. [arxiv] [code]

  26. Mingmei Cheng, Le Hui, Jin Xie, Jian Yang and Hui Kong, "Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation", IROS 2020. [arxiv] [code]

  27. Kangkan Wang, Jin Xie, Guofeng Zhang, Lei Liu and Jian Yang, "Sequential 3D Human Pose and Shape Estimation From Point Clouds", CVPR 2020. [pdf ] [code]

Full list of publications