Hu Yu

俞虎

PhD Student

University of Science and Technology of China, Anhui, China

Email: yuhu520@mail.ustc.edu.cn


Biography

I am currently a fourth-year PhD studen in University of Science and Technology of China (USTC).
My research interests focus on Computer Vsion, especially diffusion model, auto-regressive model, image generation, low-level vision tasks, and Fourier theory, advised by Feng Zhao and Feng Wu. I am now focusing on new auto-regressive model paradigm for image and video generation.

News

[07/2024] One paper accepted to ACM MM 2024
[07/2024] Two paper accepted to ECCV 2024
[09/2023] One paper accepted to NeurIPS 2023
[09/2022] One paper accepted to NeurIPS 2022
[07/2022] Two paper accepted to ACM MM 2022
[07/2022] Two paper accepted to ECCV 2022

Publications [Google Scholar]

2022

  • Frequency and Spatial Dual Guidance for Image Dehazing
    Hu Yu, Naishan Zheng, Man Zhou, Jie Huang, and Feng Zhao
    European Conference on Computer Vision (ECCV 2022)
    [pdf] [code]

  • Spatial-Frequency Domain Information Integration for Pan-sharpening
    Man Zhou, Jie Huang, Keyu Yan, Hu Yu, Xueyang Fu, Aiping Liu, Xian Wei, and Feng Zhao
    European Conference on Computer Vision (ECCV 2022)
    [pdf] [code]

  • Source-Free Domain Adaptation for Real-world Image Dehazing
    Hu Yu^, Jie Huang^, Yajing Liu, Qi Zhu, Man Zhou, and Feng Zhao
    ACM International Conference on Multimedia (ACM MM 2022)
    [pdf]

  • Adaptively Learning Low-high Frequency Information Integration for Pan-sharpening
    Man Zhou, Jie Huang, Chongyi Li, Hu Yu, Keyu Yan, Naishan Zheng, and Feng Zhao
    ACM International Conference on Multimedia (ACM MM 2022)
    [pdf]

  • Deep Fourier Up-Sampling (Featured Paper)
    Man Zhou^, Hu Yu^ , Jie Huang, Feng Zhao, Jinwei Gu, Chen Change Loy, Deyu Meng, and Chongyi Li
    Neural Information Processing Systems (NeurIPS 2022)
    [pdf] [code]

2023

  • Deep Fractional Fourier Transform (Highlight)
    Hu Yu^, Jie Huang^ , Lingzhi Li, Man Zhou, and Feng Zhao
    Neural Information Processing Systems (NeurIPS 2023)
    [pdf] [code]

  • High-quality Image Dehazing with Diffusion Model
    Hu Yu, Jie Huang, Kaiwen Zheng, Man Zhou, and Feng Zhao
    Arxiv
    [pdf] [code]

  • Ingredient-oriented Multi-degradation Learning for Image Restoration
    Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, and Feng Zhao
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
    [pdf] [code]

  • Visual Recognition-driven Image Restoration for Multiple Degradation with Intrinsic Semantics Recovery
    Zizheng Yang, Jie Huang, Jiahao Chang, Man Zhou, Hu Yu, Jinghao Zhang, and Feng Zhao
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
    [pdf]

  • Efficient Multi-exposure image fusion via filter-dominated fusion and gradient-driven unsupervised learning
    Kaiwen Zheng, Jie Huang, Hu Yu, and Feng Zhao
    CVPR Workshop on Mobile Intelligent Photography and Imaging (CVPRW 2023)
    [pdf] [code]

2024

  • Uncovering the Text Embedding in Text-to-Image Diffusion Models
    Hu Yu, Hao Luo, Fan Wang, and Feng Zhao
    Arxiv
    [pdf] [code]

  • Unmasking Bias in Diffusion Model Training
    Hu Yu, Li Shen, Jie Huang, Hongsheng Li, and Feng Zhao
    European Conference on Computer Vision (ECCV 2024)
    [pdf] [code]

  • Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing
    Zizheng Yang, Hu Yu , Bing Li, Jinghao Zhang, Jie Huang, and Feng Zhao
    European Conference on Computer Vision (ECCV 2024)
    [pdf]

  • FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining
    Zhen Zou, Hu Yu , and Feng Zhao
    ACM International Conference on Multimedia (ACM MM 2024)
    [pdf]

Honors & Awards

  • National Scholarship
    2022
  • First Class Academic Scholarship for Postgraduates of USTC
    2021-2022
  • Scholarship for Outstanding Students of USTC
    2017-2020
  • National Encouragement Scholarship
    2017-2020

Professional Activities

  • Conference Reviews

    Review of NeurIPS, ICLR, ICML, CVPR, ACM MM