Weihao Xia
  • Email
  • [GitHub] [Google Scholar] [CV]

    Biography

    I am currently a PhD/MPhil student at UCL. Before that, I received my master's degree from Tsinghua University. The topics of my research interests include computer vision and machine learning, especially their applications to visual content creation. I am currently working on image and video synthesis with multi-modal guidance such as sketch, label, audio, or text. I am also interested in implicit neural representations, image quality metrics, and semantic scene understanding. The ultimate vision of my research is to manifest and recreate the world through imagination.

    Research interests

    visual content creation: [ECCV'22], [TPAMI'22], [CVPR'21], [Neurocomputing'21], [MM'20], [NN'20]

    human perception and understanding: [ECCV'22], [CVPRW'22], [FG'21] [CVPRW'21], [TCSVT'21]

    There are also some paper collections based on my personal interests: gan inversionGitHub stars, neural renderingGitHub stars, image translationGitHub stars, clothed people digitalizationGitHub stars.

    News

    Publications

      — 2022

    High-fidelity GAN Inversion with Padding Space
    Qingyan Bai*, Yinghao Xu*, Jiapeng Zhu, Weihao Xia, Yujiu Yang, Yujun Shen
    European Conference on Computer Vision (ECCV), 2022
    [Project page] [Paper] [Code]
    Learning Quality-aware Dynamic Memory for Video Object Segmentation
    Y. Liu, R. Yu, F. Yin, X. Zhao, W. Zhao, W. Xia, Y. Yang
    European Conference on Computer Vision (ECCV), 2022
    [Paper] [Code]
    GAN Inversion: A Survey
    Weihao Xia, Yunlun Zhang, Yujiu Yang, Jing-Hao Xue, Bolei Zhou, Ming-Hsuan Yang
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022
    [Project page] [Paper]
    Identity-guided Face Generation with Multi-modal Contour Conditions
    Q. Bai, W. Xia, F. Yin, Y. Yang
    IEEE International Conference on Image Processing (ICIP), 2022
    [Paper] [Code]
    Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network
    S. Lao, Y. Gong, S. Shi, S. Yang, T. Wu, J. Wang, W. Xia, Y. Yang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2022
    [Paper] [Code]

      — 2021

    PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
    C. Tian, R. Yu, X. Zhao, W. Xia, H. Wang, Y. Yang
    IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2021
    [Paper] [Code]
    Towards Open-World Text-Guided Face Image Generation and Manipulation
    W. Xia, Y. Yang, J.-H. Xue, B. Wu
    arXiv.2104.08910 preprint, 2021
    [Paper] [Code]
    Region-Adaptive Deformable Network for Image Quality Assessment
    S. Shi*, Q. Bai*, M. Cao, W. Xia, J. Wang, Y. Chen, Y. Yang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2021
    [Paper] [Code]
    TediGAN: Text-Guided Diverse Face Image Generation and Manipulation
    W. Xia, Y. Yang, J.-H. Xue, B. Wu
    IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2021
    [Paper] [Code]
    Stroke Calibration and Completion for High-Quality Face Image Generation from Human-Like Sketches
    W. Xia, Y. Yang, J.-H. Xue
    Elsevier Neurocomputing (NEUCOM), 2021
    [Project page] [Paper]
    Domain Fingerprints for No-reference Image Quality Assessment
    W. Xia, Y. Yang, J.-H. Xue, J. Xiao
    IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2021
    [Project page] [Paper]

      — 2020

    Unsupervised Multi-Domain Multimodal Image-to-Image Translation with Explicit Domain-Constrained Disentanglement
    W. Xia, Y. Yang, J.-H. Xue
    Elsevier Neural Networks (NN), 2020
    [Project page] [Paper] [Code]
    InterpGaze: Controllable Continuous Gaze Redirection
    W. Xia, Y. Yang, J.-H. Xue, W. Feng
    ACM Multimedia (MM), 2020
    [Project page] [Paper] [Code]
    (* equal contribution, ‡ corresponding authorship)

    Professional Activities