KXT
≡
profile photo

Xiangtao Kong (孔祥涛)

I am a Ph.D. student of PolyU supervised by Prof. Lei Zhang. I mainly focus on the Low-level Vision, Super-Resolution, and Interpretability of Deep Learning in the Image Processing field. I obtained my Honors B.Eng. degree from Shandong University in 2020 and my M.S. degree from X-Pixel at SIAT-CAS supervised by Prof. Chao Dong and Prof. Yu Qiao in 2023.

Email  /  Google Scholar  /  GitHub

News

  • 09/2023, One paper accept by NeurIPS, 2023.

  • 06/2023, Join OPPP as a research intern.

  • 03/2023, One paper accept by CVPR (Highlight), 2023.

  • 02/2023, One paper accept by ICASSP (Oral), 2023.

  • 04/2022, Join OpenGV Lab, Shanghai AI Lab as a research intern.

  • 03/2022, One paper accept by CVPR, 2022.

  • 04/2021, Join SenseTime as a research intern, work with Dr. Yu Zhang.

  • 03/2021, One paper accept by CVPR, 2021.

  • 08/2020, One paper accept by ECCV Workshops, 2020.

  • 06/2020, Obtain my Honors B.Eng. degree from Shandong University.

  • 09/2019, Join X-Pixel, supervised by Prof. Chao Dong and Prof. Yu Qiao.

  • 10/2018, Win First Prize of China Undergraduate Mathematical Contest in Modeling (CUMCM).

    • Publications

    profile photo
    Networks are Slacking Off: Understanding Generalization Problem in Image Deraining
    Jinjin Gu, Xianzheng Ma, Xiangtao Kong, Yu Qiao, Chao Dong
    Conference on Neural Information Processing Systems (NeurIPS 2023)
    Paper | |
    profile photo
    DegAE: A New Pretraining Paradigm for Low-Level Vision
    Yihao Liu, Jingwen He, Jinjin Gu, Xiangtao Kong, Yu Qiao, Chao Dong
    Computer Vision and Pattern Recognition (CVPR 2023)
    Paper | Codes | BibTex
    profile photo
    Retiformer: Retinex-Based Enhancement In Transformer For Low-Light Image
    Junxiang Ruan, Xiangtao Kong, Wenqi Huang, Wenming Yang
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)
    Paper
    profile photo
    Reflash Dropout in Image Super-Resolution
    Xiangtao Kong*, Xina Liu*, Jinjin Gu, Yu Qiao, Chao Dong
    Computer Vision and Pattern Recognition (CVPR 2022)
    Paper | Codes | BibTex
    profile photo
    ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic
    Xiangtao Kong, Hengyuan Zhao, Yu Qiao, Chao Dong
    Computer Vision and Pattern Recognition (CVPR 2021)
    Paper(arxiv) | Codes | BibTex
    profile photo
    Efficient Image Super-Resolution Using Pixel Attention
    Hengyuan Zhao, Xiangtao Kong, Jingwen He, Yu Qiao, Chao Dong
    European Conference on Computer Vision Workshops (ECCVW 2020)
    We got fourth place of Efficient Image Super Resolution Challenge in total 150 participants. (The lowest paramters, 272K)
    Paper(arxiv) | Codes | BibTex