avatar

Wencheng Han

Postdoctoral Fellow
State Key Laboratory of Internet of Things for Smart City (University of Macau)
wencheng256@gmail.com


About Me

Hello and welcome! I am Wencheng Han, a postdoctoral fellow at the State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC), University of Macau. I recently completed my Ph.D. in June 2025 under the supervision of Prof. Jianbing Shen. My academic journey began with a bachelor’s degree from Shandong University (2012–2016), followed by a master’s degree at Beijing Institute of Technology (2019–2022). I completed my Ph.D. in just three years, focusing on computer vision and autonomous driving. Before my graduate studies, I worked at Sina Weibo as a Recommendation System Development Engineer (2016–2019), where I gained hands-on experience in large-scale machine learning systems.

My research interests include perception for autonomous driving—such as Monocular Depth Estimation, Monocular 3D Object Detection, and Visual Tracking—as well as AI for medical applications, particularly in multi-modal learning and medical imaging.

Research Interests

News

Publications

  1. AAAI2025
    Dme-driver: Integrating human decision logic and 3d scene perception in autonomous driving
    Wencheng Han, D Guo, C Xu, J Shen
    AAAI Conference on Artificial Intelligence 2025
    PDF

  2. AAAI2025
    Language prompt for autonomous driving
    D Wu, Wencheng Han* (co-first author), T Wang, Y Liu, C Xu, X Zhang, J Shen
    AAAI Conference on Artificial Intelligence 2025
    PDF Code

  3. T-PAMI
    Weakly Supervised Monocular 3D Object Detection by Spatial-Temporal View Consistency
    Wencheng Han, R Tao, H Ling, J Shen
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IF=23.6), doi: 10.1109/TPAMI.2024.3466915, 2024

  4. ACM MM 2024
    Prior Metadata-Driven RAW Reconstruction: Eliminating the Need for Per-Image Metadata
    Wencheng Han, C Zhang, Y Zhou, W Liu, C Qian, C Xu, J Shen
    ACM Multimedia 2024.

  5. T-PAMI
    Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks
    Wencheng Han, X Dong, Y Zhang, D Crandall, CZ Xu, J Shen
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IF=23.6), doi: 10.1109/TPAMI.2024.3400873, 2024

  6. ECCV2024
    High-Precision Self-Supervised Monocular Depth Estimation with Rich-Resource Prior
    Wencheng Han, J Shen
    European Conference on Computer Vision (ECCV), 2024.
    PDF Code

  7. ECCV2024
    RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception
    C Li, Wencheng Han* (co-first author), J Yin, S Zhao, J Shen
    European Conference on Computer Vision (ECCV), 2024.
    PDF Code

  8. CVPR2024
    Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering
    C Zhang, Wencheng Han* (co-first author), Y Zhou, J Shen, C Xu, W Liu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    PDF

  9. ICCV2023
    Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network
    Wencheng Han, Junbo Yin, Jianbing Shen
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    PDF Code

  10. CVPR2023
    Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency
    Runzhou Tao*, Wencheng Han* (co-first author), Zhongying Qiu, Cheng-zhong Xu, Jianbing Shen
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
    PDF Code

  11. CVPR2023
    Referring Multi-Object Tracking
    Dongming Wu*, Wencheng Han* (co-first author), Tiancai Wang, Xingping Dong, Xiangyu Zhang, Jianbing Shen
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
    PDF Code

  12. ECCV2022
    Brnet: Exploring comprehensive features for monocular depth estimation
    Wencheng Han, Junbo Yin, Xiaogang Jin, Xiangdong Dai, Jianbing Shen
    European Conference on Computer Vision (ECCV), 2022.
    PDF Code

  13. CVPR2021
    Learning to fuse asymmetric feature maps in siamese trackers
    Wencheng Han, Xingping Dong, Fahad Shahbaz Khan, Ling Shao, Jianbing Shen
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    PDF Code

Services

Program Committee/Conference Reviewers

Journal Reviewers


Powered by Jekyll and Minimal Light theme.