Kaixuan Wei

M.S. Student @ BIT

Visual Media Computing Lab


I am currently a third-year master student (with four-year research experience) at Beijing Institute of Technology (BIT), under the supervision of Prof. Ying Fu. Previously, I received my B.S. degree of Electronic Engineering (Xu class) from Beijing Institute of Technology in 2018. I was a visiting student at the Cambridge Image Analysis Group (CIA), University of Cambridge during summer 2019 (Host: Dr. Angelica I. Aviles-Rivero). I also work closely with Dr. Jiaolong Yang in Microsoft Research Asia (MSRA).

My research interest lies at the intersection of machine learning, deep learning, variational optimization and statistical modeling/inference with applications for computational photography, computational imaging and low-level computer vision.

I serve as a reviewer for international conferences: WACV, ECCV, CVPR, ICCV, SIGGRAPH Asia, AAAI, NeurIPS, ICLR. Please check my CV For more details.


  • Computational Photography
  • Computational Imaging
  • Low-level Computer Vision


  • M.S. of Computer Science, 2018 - 2021

    Beijing Institute of Technology

  • B.S. of Electronic Engineering, 2014 - 2018

    Beijing Institute of Technology

Recent News

  • [7/2020] We are happy and honoured to receive an Outstanding Paper Award @ ICML2020
  • [6/2020] One paper is accepted by ICML 2020.
  • [3/2020] Our work on extreme low-light denoising has been selected as an Oral presentation in CVPR 2020!
  • [3/2020] The new homepage on line.
  • [2/2020] One paper is accepted by CVPR 2020.
  • [2/2020] One paper is accepted by IEEE Transactions on Neural Network and Learning System (TNNLS) journal.
  • [9/2019] I’m awarded the National Scholarship (Rank 1st in Master track of Computer Science, 1 / 800 students at BIT).
  • [7/2019] I join the Cambridge Image Analysis Group at University of Cambridge as a visiting student, working with Dr. Angelica I. Aviles-Rivero.
  • [3/2019] One paper is accepted by CVPR 2019.
  • [1/2019] One paper is accepted by Elsevier Neurocomputing journal.


Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems

The 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria, Outstanding Paper Award, Acceptance Rate: 0.04%

A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising

The 36th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, USA, Oral Presentation, Acceptance Rate: 5%

3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising

IEEE Transactions on Neural Networks and Learning System, 2020

Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements

The 35th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, USA


I have been fortunate to work with very supportive and inspiring people that made me grow more than I could imagine. Here is a list of my collaborators:

  • Ying Fu (School of Computer Science and Technology, Beijing Institute of Technology)
  • Jiaolong Yang (Visual Computing Group, Microsoft Research)
  • Angelica I. Aviles-Rivero (Department of Pure Mathematics and Mathematical Statistics, University of Cambridge)