|
Jin Xie 谢晋
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 am also recruiting postdocs to join our team.
Research
I mainly focus on 3D computer vision and its applications on autonomous driving and robotics, 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 physical world and interact with 3D physical world from images, videos and point clouds. Specifically, my research interests fall into 3D low-level imaging, 3D scene understanding and generation, robotics navigation and grasping for interaction, etc.
My recent focus includes:
Spatial understanding and inference lifted with foundation models.
3D and video generation with physical simulation for world model.
Vision-language-action model for robotics navigation and grasping.
Reinforcement learning for high-dimensional robotics control.
Novel autonomous system design and implementation.
Recent Publications
 |
FUSER: Feed-Forward Multiview 3D Registration Transformer and SE(3)N
Diffusion Refinement
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Haobo Jiang, Jin Xie, Jian Yang, Liang Yu and Jianmin Zheng
[arxiv] [project] [code]
|
 |
IntrinsicWeather: Controllable Weather Editing in Intrinsic Space
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Yixin Zhu, Zuo-liang Zhu, Jian Yang, Milos Hasan, Jin Xie and Beibei Wang
[arxiv] [project] [code]
|
 |
GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Yonghao Zhao, Yupeng Gao, Jian Yang, Jin Xie and Beibei Wang
[arxiv] [project] [code]
|
 |
A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimation
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Kangjian Zhu, Haobo Jiang, Jianjun Qian and Jin Xie
[arxiv] [project] [code]
|
 |
Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Yun Zhu, Jianjun Qian, Jian Yang, Jin Xie and Na Zhao
[arxiv] [project] [code]
|
 |
MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot
3D Instance Segmentation
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Yibo Zhao, Yigong Zhang and Jin Xie
[arxiv] [project] [code]
|
 |
GEM: Generating LiDAR World Model via Deformable Mamba
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Yang Wu, Zhaojiang Liu, Qiang Meng, Youquan Liu, Renliang Weng, Jianjun Qian, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
International Conference on Computer Vision and Pattern Recognition, CVPR 2026
Ze-xin Yin, Liu Liu, Xinjie Wang, Wei Sui, Zhizhong Su, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving
International Conference on Learning Representations, ICLR 2026
Ziyue Zhu, Zhanqian Wu, Zhenxin Zhu, Lijun Zhou, Haiyang Sun, Bing Wang, Kun Ma, Guang Chen, Hangjun Ye, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
International Conference on Robotics, ICRA 2026
Kai Deng, Jiawei Xu, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
ACM SIGGRAPH Asia Conference, SIGGRAPH Asia 2025
Kai Deng, Yigong Zhang, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
AD-GS: Object-aware B-spline Gaussian Splatting for Self-supervised Autonomous Driving
International Conference on Computer Vision, ICCV 2025
Jiawei Xu, Kai Deng, Zexin Fan, Shenlong Wang, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
DiffPCI: Large Motion Point Cloud Frame Interpolation with Diffusion Model
International Conference on Computer Vision, ICCV 2025
Tianyu Zhang, Haobo Jiang, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
GSRecon: Efficient Generalizable Gaussian Splatting for Surface Reconstruction from Sparse Views
International Conference on Computer Vision, ICCV 2025
Hang Yang, Le Hui, Jianjun Qian, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
Generative Point Cloud Registration
International Conference on Machine Learning, ICML 2025
Haobo Jiang, Jin Xie, Jian Yang, Liang Yu and Jianmin Zheng
[arxiv] [project] [code]
|
 |
Voxelsplat: Dynamic Gaussian Splatting as An Effective Loss for Occupancy and Flow Prediction
International Conference on Computer Vision and Pattern Recognition, CVPR 2025
Ziyue Zhu, Jiang-jiang Liu, Jingdong Wang, Jian Yang, Shenlong Wang and Jin Xie
[arxiv] [project] [code]
|
 |
Zero-shot RGB-D Point Cloud Registration with Pretrained Large Vision Model
International Conference on Computer Vision and Pattern Recognition, CVPR 2025
Haobo Jiang, Jin Xie, Jian Yang, Liang Yu and Jianmin Zheng
[arxiv] [project] [code]
|
 |
WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion
International Conference on Computer Vision and Pattern Recognition, CVPR 2025
Yang Wu, Yun Zhu, Kaihua Zhang, Jianjun Qian, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
Learning Class Prototypes for Unified 3D Object Detection with Sparse Supervision
International Conference on Computer Vision and Pattern Recognition, CVPR 2025
Yun Zhu, Le Hui, Hang Yang, Jianjun Qian, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
Sketchy Bounding-box Supervision for 3D Instance Segmentation
International Conference on Computer Vision and Pattern Recognition, CVPR 2025
Qian Deng, Le Hui, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
NaviFormer: A Spatio-Temporal Context-Aware Transformer for Object Navigation
AAAI Conference on Artificial Intelligence, AAAI 2025
Wei Xie, Haobo Jiang, Yun Zhu, Jianjun Qian and Jin Xie
[arxiv] [project] [code]
|
 |
Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Gaussian Splatting
Conference on Neural Information Processing Systems, NeurIPS 2024
Jiawei Xu, Zexin Fan, Jian Yang and Jin Xie
[arxiv] [project] [code]
|
 |
FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation
European Conference on Computer Vision, ECCV 2024
Tianyu Zhang, Guocheng Qian, Jin Xie and Jian Yang
[arxiv] [project] [code]
|
 |
Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer
European Conference on Computer Vision, ECCV 2024
Yang Wu, Kaihua Zhang, Jianjun Qian, Jin Xie and Jian Yang
[arxiv] [project] [code]
|
 |
Masked Motion Prediction with Semantic Contrast for Point Cloud Sequence Learning
European Conference on Computer Vision, ECCV 2024
Yuehui Han, Can Xu, Rui Xu, Jianjun Qian and Jin Xie
[arxiv] [project] [code]
|
 |
Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem
European Conference on Computer Vision, ECCV 2024
Qianliang Wu, Haobo Jiang, Lei Luo, Jun Li, Yaqing Ding, Jin Xie and Jian Yang
[arxiv] [project] [code]
|
 |
Multi-attribute Interactions Matter for 3D Visual Grounding
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2024
Can Xu, Yuehui Han, Rui Xu, Le Hui, Yaqi Shen, Jin Xie and Jian Yang
[arxiv] [project] [code]
|
Full list of publications
|
