Yuqi Cheng

Yuqi Cheng

Huazhong University of Science and Technology

🌐欢迎来到我的主页！我是程育奇，在华中科技大学取得了学士学位（2020）和硕士学位（2023，导师：李文龙教授）.目前我在华中科技大学攻读博士学位，导师为沈卫明院士。

🌐Welcome to my homepage! I am Cheng Yuqi (程育奇). I got my bachelor’s degree (2020) and Master’s degree (2023) from Huazhong University of Science and Technology. Now I am a Ph.D student in Huazhong University of Science and Technology under the supervision of Prof. Shen Weiming.

我的研究方向围绕工业视觉检测展开，涉及多视图点云的机器人采集、精简、配准、异常检测等. 后续研究重点为构建可实际使用的点云异常检测方法与更加通用的3D特征提取器。除了学术研究，我有很大的热情和兴趣参与实际项目的落地，目前我的研究成果已经在航空叶片、核电堆芯、汽车自动化产线等场景实现了应用。🚀🚀🚀

My research focuses on industrial vision inspection, involving multi-view point cloud robot acquisition, simplification, registration, anomaly detection, etc. Subsequent research focuses on building a practical point cloud anomaly detection method and a more general 3D feature extractor. In addition, I have great enthusiasm and interest to participate in practical applications, and my researches have been applied in aviation, nuclear power, automobiles and other scenarios.🚀🚀🚀

如果对我的学术研究或落地项目感兴趣，任何时候都可以联系我，我非常乐意与您进行交流！😊😊😊我未来十分希望能将学术研究的方法推向实际使用，如果有企业愿意给我提供这个机会，请联系我！🍻

If you are interested in my academic researches or projects, please feel free to contact me at any time, and I will be happy to communicate with you! 😊😊😊I really hope to push academic researches into practical application in the future, so if any enterprise is willing to provide me with this opportunity, please let me know!🍻

🔥 News

Peer-Reviewed Publications 
Manuscripts under Review 

# co-first author | * corresponding author

Peer-Reviewed Publications

  1. MVGR: Mean-Variance Minimization Global Registration Method for Multiview Point Cloud in Robot Inspection [Paper] [Code]
    Yuqi Cheng, Wenlong Li*, Cheng Jiang, Dongfang Wang, Hongwen Xing, Wei Xu
    IEEE Transactions on Instrumentation and Measurement (TIM). 2024. (JCR Q1)
  2. A novel cooling hole inspection method for turbine blade using 3D reconstruction of stereo vision [Paper]
    Yuqi Cheng, Wenlong Li*, Cheng Jiang, Gang Wang, Wei Xu, Qingyu Peng
    Measurement Science and Technology (MST). 2021. (JCR Q1)
  3. A novel point cloud simplification method using local conditional information [Paper]
    Yuqi Cheng, Wenlong Li, Cheng Jiang, Dongfang Wang, Jincheng Mao*, Wei Xu
    Measurement Science and Technology (MST). 2022. (JCR Q1)
  4. A point cloud semantic segmentation method for nuclear power reactors based on RandLA-Net Model [Paper]
    Yuqi Cheng, Dongfang Wang, Qingyu Peng, Wenlong Li*
    Journal of Advanced Manufacturing Science and Technology(JAMST). 2023.
  5. RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection [Paper] [Code]
    Yuqi Cheng, Yunkang Cao, Rui Chen, Weiming Shen
    IEEE 20th International Conference on Automation Science and Engineering (CASE). 2024.
  6. AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection [Paper] [Code]
    Yunkang Cao, Jiangning Zhang, Luca Frittoli, Yuqi Cheng, Weiming Shen*, Giacomo Boracchi
    European Conference on Computer Vision (ECCV). 2024.
  7. A Novel Path Error Compensation Method for Robotic Milling by Using Hybrid Temporal Network
    Qingyu Peng, Wenlong Li*, Cheng Jiang, Yuqi Cheng, Dongfang Wang, Wei Xu IEEE/ASME Transactions on Mechatronics (IEEE/ASME TMECH). 2024.
  8. A panoramic image stitching method for nuclear fuel assemblies [Paper]
    Bin Yang, Yuqi Cheng, Rui Chen, Li Li, Ran Guo, Hehui Geng, Tao Liu, and Wenlong Li
    Measurement Science and Technology (MST). 2023. (JCR Q1)
  9. An adaptive anisotropic bilateral filtering method for mesh data in scale space [Paper]
    Lingjie Su, Wenlong Li*, Yuqi Cheng, Dongfang Wang, Cheng Jiang, Wentao Yang, Haiwen Zhang, Wei Xu
    Measurement Science and Technology (MST). 2024. (JCR Q1)
  10. An illumination-robust edge detection method for nuclear fuel assembly deformation measurement [Paper]
    Rui Chen, Yuqi Cheng, Wentao Yang, Bin Yang and Wenlong Li*
    2023 3rd International Conference on Mechanical Automation and Electronic Information Engineering (MAEIE). 2023.

Manuscripts under Review

  1. Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework
    Yuqi Cheng#, Yunkang Cao#, Guoyang Xie, Zhichao Lu, Weiming Shen*
    IEEE Transactions on Systems, Man, and Cybernetics: Systems (IEEE TSMC) . (Under Review)
  2. Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection
    Yuqi Cheng, Yunkang Cao, Dongfang Wang, Weiming Shen*, Wenlong Li
    Transactions on Automation Science and Engineering (IEEE TASE) . (Under Review)
  3. VTFusion: A Vision-Text Multimodal Fusion Network for Few-Shot Anomaly Detection
    Yuxin Jiang, Yunkang Cao, Yuqi Cheng, Yiheng Zhang, Weiming Shen*
    IEEE Transactions on Cybernetics (IEEE TCYB). (Under Review)
  4. Segment any anomaly without training via hybrid prompt regularization [Paper] [Code]
    Yunkang Cao, Xiaohao Xu, Chen Sun, Yuqi Cheng, Zongwei Du, Liang Gao, Weiming Shen*
    IEEE Transactions on Cybernetics (IEEE TCYB). (Under Review)
  5. A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect [Paper]
    Yunkang Cao, Xiaohao Xu, Jiangning Zhang, Yuqi Cheng, Xiaonan Huang, Guansong Pang, Weiming Shen* (Under Review)
  6. A robust probability-based joint registration method of multiple point clouds considering local consistency
    Lingjie Su, Wei Xu*, Shuyang Zhao, Yuqi Cheng, Wenlong Li
    IEEE International Conference on Robotics and Automation (ICRA). (Under Review)

💻 Projects

TIM 2024
sym

Multi-view registration of car body

[Introduction]

  • An industrial robot is equipped with 3D sensors to collect point clouds from multiple perspectives, and the proposed method MVGR is utilized for multi-view point cloud registration to obtain high-quality car body data.

[Challenge]

  • Due to the positioning deviation of the robot, the point clouds collected by various poses inevitably have uneven density and stratification, leading to a significant compromise in the overall quality of multiview point clouds.
MST 2021
sym

Inspection of turbine blade cooling holes

[Introduction]

  • An industrial robot is equipped with binocular camera to collect images of the blade, and then the number and aperture of cooling holes are calculated by the distribution property and binocular reconstruction principle.

[Challenge]

  • Complex blade shape; holes distributed on the curved surface; weak feature.
MST 2023
sym

Panoramic image stitching and dimension calculation for nuclear fuel assemblies.

[Introduction]

  • The videos are recorded when pulling the fuel assembly under water. Then the videos are utilized to restore the panoramic images to further calculate the key dimensions.

[Challenge]

  • Radiation noise, thermal disturbance, weak texture, large-scale object.
CASE 2024
sym

Foreign object recognition

[Introduction]

  • Instances of machine wear or human error may result in foreign objects falling onto the platform, thereby disrupting operations and posing safety hazards. Consequently, detecting foreign objects on the work platform is framed as an unsupervised anomaly detection challenge.

[Challenge]

  • Abnormal data are hard to collect, uneven illumination, domain gap.
Work
sym

Mobile E-Ink Screen Surface Defect Detection

[Introduction]

  • A high-resolution detection device is built to detect abnormal products by using unsupervised anomaly detection technology.

[Challenge]

  • Tiny defect, illumination dependent, abnormal data are hard to collect.

🥇 Honors and Awards

  • National First Price, “Challenge Cup” National College Student Business Plan Competition. 2023. (Leader)
  • 2nd place CVPR VAND Zero-shot Anomaly Detection Challenge. 2023. (Participator)
  • National Third Prize, China Postgraduate Robot Innovation and Design Competition. 2021. (Leader)
  • Provincial First Price, “Challenge Cup” National College Student Business Plan Competition. 2022. (Leader)
  • Provincial Second Price, China International College Students’ Innovation Competition. 2024. (Leader)
  • Future STAR (Highest honors in School of Mechanical Science and Engineering). 2024.
  • National Scholarship (Rank first in the major). 2022.
  • Merit Student, 2021, 2022.
  • The First Prize Scholarship, 2020,2021,2022,2023.

📖 Educations

  • 2023.09 - present, Huazhong University of Science and Technology

    State Key Laboratory of Digital Manufacturing Equipment and Technology
    Ph.D. Candidate in Mechanical Engineering                                      Advisor: Weiming Shen

  • 2020.09 - 2023.06, Huazhong University of Science and Technology

    State Key Laboratory of Digital Manufacturing Equipment and Technology
    M.S. in Mechanical Engineering                                                        Advisor: Wenlong Li

  • 2016.09 - 2020.06, Huazhong University of Science and Technology

    B.S. in Mechanical Design, Manufacture & Automation    

💬 Conference Presentation

  • 2024.08, “RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection”, CASE2024, Italy.

💻 Internships

  • 2019.07 - 2019.08, Huawei(华为), China. Design of Huawei cloud fault diagnosis algorithm.
  • 2022.05 - 2022.08, Meituan(美团), China. Research on 3D object detection in UAV delivery.