Portrait of Shenxing Wei

Ph.D. Student @ vLAR Group

魏慎行 Shenxing Wei

The Hong Kong Polytechnic University

3D Vision · Surface Reconstruction · Anomaly Detection

Email Google Scholar GitHub

About Me

I am a Ph.D. student in the vLAR Group at The Hong Kong Polytechnic University, advised by Prof. Bo Yang since 2023.09. My research focuses on 3D vision, surface reconstruction, and 6D object pose estimation. I am interested in recovering continuous 3D geometry from visual observations, whether from unposed images, point clouds or Gaussian splats.

Previously, I received my M.Sc. degree in Computer Science and Technology from Xi'an Jiaotong University (2020.09 - 2023.06), advised by Prof. Yihong Gong, and my B.Sc. degree in Automation from Xi'an Jiaotong University (2016.09 - 2020.06).

Education

The Hong Kong Polytechnic University

2023.09 - Present

Ph.D., Department of Computing Advisor: Prof. Bo Yang

Xi'an Jiaotong University

2020.09 - 2023.06

M.Sc., Computer Science and Technology Advisor: Prof. Yihong Gong

Xi'an Jiaotong University

2016.09 - 2020.06

B.Sc., Automation

Research

3D Surface Reconstruction

Ray-based and raylet distance fields that generalize across scenes, reconstructing surfaces from posed images, point clouds and Gaussian splats.

6D Object Pose Estimation

Symmetry-aware geometry correspondences for estimating the 6D pose of unseen objects, connecting point-cloud registration with least-squares pose fitting.

Anomaly Detection

Few-shot and weakly-supervised anomaly detection and segmentation for industrial inspection, including online and topology-preserving transfer settings.

Publications

Listed in reverse chronological order. * indicates equal contribution.

FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images

Shenxing Wei, Jinxi Li, Zihui Zhang, Ajay Kumar, Wei Wang, Bo Yang

Conference on Neural Information Processing Systems (NeurIPS), 2026

OpenReview NeurIPS

EvObj animated comparison of the input scene, GrabS, our instance segmentation, and ground truth

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

Jiahao Chen, Zihui Zhang, Yafei Yang, Jinxi Li, Shenxing Wei, Zhixuan Sun, Bo Yang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

arXiv Code

PhysInOne teaser figure

PhysInOne: Visual Physics Learning and Reasoning in One Suite

Siyuan Zhou*, Hejun Wang*, Hu Cheng*, Jinxi Li*, Dongsheng Wang*, Junwei Jiang*, Yixiao Jin*, Jiayue Huang*, Shiwei Mao*, Shangjia Liu, Yafei Yang, Hongkang Song, Shenxing Wei, Zihui Zhang, Peng Huang, Shijie Liu, Zhengli Hao, Hao Li, Yitian Li, Wenqi Zhou, Zhihan Zhao, Zongqi He, Hongtao Wen, Shouwang Huang, Peng Yun, Bowen Cheng, Pok Kazaf Fu, Wai Kit Lai, Jiahao Chen, Kaiyuan Wang, Zhixuan Sun, Ziqi Li, Haochen Hu, Di Zhang, Chun Ho Yuen, Bing Wang, Zhihua Wang, Chuhang Zou, Bo Yang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

arXiv Code

RayletDF animated surface reconstruction comparisons from Gaussians and point clouds

RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians Highlight

Shenxing Wei*, Jinxi Li*, Yafei Yang, Siyuan Zhou, Bo Yang

IEEE/CVF International Conference on Computer Vision (ICCV), 2025

arXiv Code

Few-shot online anomaly detection and segmentation: initial training and online model updates (Figure 1)

Few-shot Online Anomaly Detection and Segmentation

Shenxing Wei, Xing Wei, Zhiheng Ma, Songlin Dong, Shaochen Zhang, Yihong Gong

Knowledge-Based Systems, 2024

arXiv DOI Code

GCPose comparison of category-level, template-based, and correspondence-based pose estimation frameworks (Figure 1)

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

Heng Zhao, Shenxing Wei, Dahu Shi, Wenming Tan, Zheyang Li, Ye Ren, Xing Wei, Yi Yang, Shiliang Pu

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

DOI

Topology-preserving transfer learning framework with anchor selection and topology modelling (Fig. 2)

Topology-Preserving Transfer Learning for Weakly-Supervised Anomaly Detection and Segmentation

Shenxing Wei, Xing Wei, Muhammad Rifki Kurniawan, Zhiheng Ma, Yihong Gong

Pattern Recognition Letters, 2023

DOI Code