Moyun Liu (刘默耘)

Moyun Liu (刘默耘)

Huazhong University of Science and Technology

I am currently a Postdoctoral Researcher in the School of Mechanical Science and Engineering at Huazhong University of Science and Technology (HUST), under the supervision of Prof. Han Ding (Academician of the Chinese Academy of Sciences), Prof. Bo Tao (Changjiang Distinguished Professor), and Prof. Xingwei Zhao (recipient of the National Science Fund for Excellent Young Scholars).

I received both my M.S. and Ph.D. degrees in Mechanical Science and Engineering from HUST in 2021 and 2025, respectively, where I was advised by Prof. Youping Chen and Prof. Jingming Xie. Prior to that, I obtained my B.S. degree from Hubei University of Technology in 2019. From 2023 to 2025, I was a visiting student at the A*STAR Centre for Frontier AI Research (CFAR), Singapore, where I worked under the supervision of Prof. Joey Tianyi Zhou and Dr. Jiawei Du.

My current research interest includes embodied AI, humanoid robotics, and multimodal fusion.

🔥 News

  • 2025.08:   🎉 Our work “Generalized Probabilistic Graphical Modeling for Multi-view Bipartite Graph Clustering” has been accepted by IEEE TPAMI! Many thanks to Dr. Li Liang. [Paper (soon)] Code
  • 2025.07:   🎉 Our work “GaussianCross: Cross-modal Self-supervised 3D Representation Learning via Gaussian Splatting” has been accepted by ACM MM 2025! Many thanks to Mr. Ray Lei Yao. Paper Code
  • 2025.06:   🚀 I joined the State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, HUST, as a Postdoctoral Researcher. I have started my research on humanoid robotics.
  • 2025.06:  🎓 I have successfully completed my Ph.D. at HUST! Grateful for the support from my advisors, colleagues, and everyone who accompanied me on this journey.
  • 2025.05:  🏆 Our LaSSM and SGIFormer obtain first and second places on CVPR 2025 ScanNet++ Challenge, respectively. Many thanks to Mr. Ray Lei Yao.
  • 2025.04:  🙏 My visit at A*STAR has come to an end. I’m grateful to everyone I encountered!
  • 2025.04:  🎉 Our work “MAENet: Boost Image-Guided Point Cloud Completion More Accurate and Even” has been accepted by Information Fusion ! Paper Code
  • 2025.03:  🏆 Our previous paper “LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image” has been selected as an ESI Highly Cited Paper ! Paper Code
  • 2024.11:  💰 I Won the National Scholarship for PhD Student !
  • 2024.11:  🎉 Our work “SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation” has been accepted by IEEE TCSVT ! Many thanks to Mr. Ray Lei Yao. Paper Code
  • 2024.10:  🎉 Our work “GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models” has been accepted by IEEE TMM ! Paper Code
  • 2024.10:  🏆 We got 6th place in ToothFairy2 : Semi-supervised Teeth Segmentation hold on MICCAI2024 ! Many thanks to Mr. Jing HAO.
  • 2024.05:  🎉 Our work “Towards Better Unguided Depth Completion via Cross-Modality Knowledge Distillation in the Frequency Domain” has been accepted by IEEE TIV ! Paper
  • 2024.04:  🎉 Our work “MENet: Multi-Modal Mapping Enhancement Network for 3D Object Detection in Autonomous Driving” has been accepted by IEEE TITS ! Paper

📖 Educations

  • 2021.09 - 2025.06, Ph.D., School of Mechanical Science and Engineering, Huazhong University of Science and Technology.
  • 2023.05 - 2025.04, Visiting Ph.D. Student, A*STAR Centre for Frontier AI Research (CFAR).
  • 2019.06 - 2021.06, M.Eng., School of Mechanical Science and Engineering, Huazhong University of Science and Technology.
  • 2015.09 - 2019.06, B.Eng., School of Mechanical Engineering, Hubei University of Technology.

💻 Internships

📝 Selected Publications

sym

MAENet: Boost Image-Guided Point Cloud Completion More Accurate and Even

Moyun Liu, Ziheng Yang, Bing Chen, Youping Chen, Jingming Xie, Lei Yao, Lap-Pui Chau, Jiawei Du, Joey Tianyi Zhou

Information Fusion, 2025 |

  • We propose a point cloud completion method that ensures both accuracy and uniformity in the completed results.
sym

Towards Better Unguided Depth Completion via Cross-Modality Knowledge Distillation in the Frequency Domain

Moyun Liu, Bing Chen, Youping Chen, Jingming Xie, Lei Yao, Yang Zhang, Qin Hu, Jiawei Du, Joey Tianyi Zhou

IEEE Transactions on Intelligent Vehicles, 2024

  • We analyze the contribution of camera image for depth completion and propose a better unguided depth completion framework.
sym

MENet: Multi-Modal Mapping Enhancement Network for 3D Object Detection in Autonomous Driving

Moyun Liu, Youping Chen, Jingming Xie, Yijie Zhu, Yang Zhang, Lei Yao, Zhenshan Bing, Genghang Zhuang, Kai Huang, Joey Tianyi Zhou

IEEE Transactions on Intelligent Transportation Systems, 2024

  • We propose a multi-modal mapping enhancement network named MENet for 3D object detection.
sym

A Concise but High-performing Network for Image Guided Depth Completion in Autonomous Driving

Moyun Liu, Bing Chen, Youping Chen, Jingming Xie, Lei Yao, Yang Zhang, Joey Tianyi Zhou

Knowledge-Based Systems, 2024 |

  • We propose a fast and effective depth completion network based on the image guidance.
sym

GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models

Jing Hao*, Moyun Liu*, Jinrong Yang, Kuo Feng Hung

IEEE Transactions on Multimedia, 2024 |

  • The first to propose exploring to the solution of glass surface segmentation by fully harnessing the capabilities of existing VFMs.
sym

LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image

🏆ESI Highly Cited Paper

Moyun Liu, Youping Chen, Jingming Xie, Lei He, Yang Zhang

IEEE Sensors Journal, 2023 |

  • We propose a weld defect detection method based on convolution neural network, namely Lighter and Faster YOLO (LF-YOLO).
sym

Adaptive fusion affinity graph with noise-free online low-rank representation for natural image segmentation

Yang Zhang, Moyun Liu, Huiming Zhang, Guodong Sun, and Jingwu He

Pattern Recognition, 2023

  • We propose an adaptive fusion affinity graph (AFA-graph) with noise-free low-rank representation in an online manner for natural image segmentation
sym

A lightweight and accurate recognition framework for signs of X-ray weld images

Moyun Liu, Jingming Xie, Jing Hao, Yang Zhang, Xuzhan Chen, Youping Chen

Computers in Industry, 2022

  • We propose a signs recognition framework based on convolutional neural networks (CNNs) for weld images. The proposed framework firstly contains a shallow classification network for correcting the pose of images, and a narrow network for final weld information recognition.
sym

A Unified Light Framework for Real-time Fault Detection of Freight Train Images

Yang Zhang, Moyun Liu*, Yang Yang, Yanwen Guo, Huiming Zhang

IEEE Transactions on Industrial Informatics, 2021

  • We propose a unified light framework to improve detection accuracy while supporting a real-time operation with a low resource requirement.
sym

Affinity fusion graph-based framework for natural image segmentation

Yang Zhang, Moyun Liu, Jingwu He, Fei Pan, Yanwen Guo

IEEE Transactions on Multimedia, 2021 |

  • We propose an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation.

📝 Other Publications

👨‍🎓 Academic Service

  • Reviewer

IEEE Transactions on Pattern Analysis and Machine Intelligence

IEEE Transactions on Intelligent Transportation Systems

IEEE Transactions on Intelligent Vehicles

IEEE Transactions on Industrial Informatics

IEEE Transactions on Automation Science and Engineering

IEEE Transactions on Artificial Intelligence

IEEE Sensors Journal

Information Fusion

Pattern Recognition

Computers in Industry

Knowledge-Based Systems

Engineering Applications of Artificial Intelligence

Expert Systems With Applications

International Conference on Learning Representations (ICLR)

ACM Multimedia (ACM MM)

  • Conference Service

Program Committees of 2023 the 1st International Conference on AI-generated Content (AIGC2023)