PhD Student, UCL

I am a PhD student at UCL, advised by Jing-Hao Xue. Previously, I received a master’s degree from Tsinghua University, supervised by Yujiu Yang. During the past few years, I have the pleasure in working with Cengiz Öztireli (University of Cambridge), Raoul de Charette (Astra-Vision Team, INRIA Paris), Ming-Hsuan Yang (UC Merced), Bolei Zhou (UCLA), and Yulun Zhang (ETH Zürich).

My research seeks to marry the worlds of computer science and human cognition to create intelligent systems that enhance and augment human perception and creativity. I work at the intersection of Computer Vision, Human-Computer Interaction, and Neuroscience. The goal is to manifest and recreate the world through imagination by developing models that encompass various multisensory perceptual data as multi-modal control factors, including visual, auditory, and tactile inputs.

  • [12/2023] Talk at UCL PhD seminar.
  • [10/2023] One paper is accepted to WACV 2024. Two papers are accepted to NeurIPS 2023 Workshops.
  • [09/2023] One paper on Generative 3D-aware Models is accepted to ACM Computing Surveys.
  • [09/2023] I am invited to serve as a Reviewer for AAAI 2024, AISTATS 2024, CVPR 2024.
  • [07/2023] I attend the Cambridge ELLIS Unit Summer School on Probabipstic Machine Learning in Cambridge, UK.
  • [02/2023] I will be joining Adobe Research London Lab as a research intern this summer.
  • [02/2023] I am serving as a Reviewer for ICCV 2023, SIGGRAPH 2023, IJCAI 2023, UAI 2023.
  • [12/2022] I am visiting Core Lab (Rainbow Graphics & Interaction Group), Department of Computer Science and Technology, University of Cambridge.
  • [12/2022] Two papers are awarded as The Second Shenzhen Excellent Science and Technology Papers 2022 by Shenzhen Association for Artificial Intelligence (SAAI).
  • [07/2022] Two papers are accepted to ECCV 2022.
  • [06/2022] One paper is accepted to T-PAMI.

Selected Publications
  1. DREAM: Visual Decoding from Reversing Human Visual System
    WACV 2024, In IEEE/CVF Winter Conference on Applications of Computer Vision. [Website] [Code]
    Weihao Xia, Raoul Charette, Cengiz Öztireli, and Jing-Hao Xue
  2. DynODE: Modeling Latent Dynamics of StyleGAN using Neural ODEs
    NeurIPS 2023 Workshop, In Neural Information Processing Systems (NeurIPS) Workshop on Deep Learning and Inverse Problems. [Code]
    Weihao Xia, Yujiu Yang, and Jing-Hao Xue
  3. GAN Inversion: A Survey
    TPAMI 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence. [Website]
    Weihao Xia, Yulun Zhang, Yujiu Yang, Jing-Hao Xue, Bolei Zhou, and Ming-Hsuan Yang
  4. High-fidelity GAN Inversion with Padding Space
    ECCV 2022, In European Conference on Computer Vision. [Website] [Code]
    Qingyan Bai, Yinghao Xu, Jiapeng Zhu, Weihao Xia, Yujiu Yang, and Yujun Shen
  5. Learning Quality-Aware Dynamic Memory For Video Object Segmentation
    ECCV 2022, In European Conference on Computer Vision. [Code]
    Yong Liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, and Yujiu Yang
  6. TediGAN: Text-Guided Diverse Face Image Generation and Manipulation
    CVPR 2021, In IEEE/CVF Conference on Computer Vision and Pattern Recognition. [Website] [Code]
    Weihao Xia, Yujiu Yang, Jing-Hao Xue, and Baoyuan Wu
  7. Controllable Continuous Gaze Redirection
    ACM MM 2020, In ACM International Conference on Multimedi. [Code]
    Weihao Xia, Yujiu Yang, Jing-Hao Xue, and Wensen Feng