Yuekun Dai

MMLab@NTU
Singapore

Welcome to my homepage!

About Me

I am currently a second-year PhD student in MMLab@NTU supervised by Prof. Chen Change Loy. I obtained M.S. degree in Artifical Intelligence in Nanyang Technological University, advised by Prof. Chen Change Loy and Prof. Chongyi Li. Before this, I obtained B.S. degree in Intelligence Science and Technology from Peking University in 2020, supervised by Prof. Zhouchen Lin and luckily had chance to visit the University of Michigan working with Prof. Qiaozhu Mei and Prof. Ji Zhu.

I am interested in computational photography and computer graphics, and anime-related research. My current research mainly focus on image decomposition, AI for animation, and layered image editting.

Experiences

Visual perception Engineer | Unitree Robotics
Time: Mar 2021 - Aug 2021.

Publications [Google Scholar]

Paint Bucket Colorization Using Anime Character Color Design Sheets
Arxiv Preprint  
Yuekun Dai, Qinyue Li, Shangchen Zhou, Qinyue Li, Chongyi Li, and Chen Change Loy.
[Paper] [Code] [Video]

Learning Inclusion Matching for Animation Paint Bucket Colorization
Computer Vision and Pattern Recognition, CVPR 2024  
Yuekun Dai, Shangchen Zhou, Qinyue Li, Chongyi Li, and Chen Change Loy.
[Paper] [Project Page] [Code] [Video] [Dataset]

Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond
Transactions on Pattern Analysis and Machine Intelligence, TPAMI 2024
Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Yihang Luo, and Chen Change Loy.
[Paper] [Arxiv] [Code] [Dataset]

Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
Computer Vision and Pattern Recognition, CVPR 2023  
Highlight (top 2.5%, 3 top ratings)
Yuekun Dai, Yihang Luo, Shangchen Zhou, Chongyi Li, and Chen Change Loy.
[Paper] [Project Page] [Video] [Code]

BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer
Computer Vision and Pattern Recognition Workshop, CVPRW 2023  
Qixin Yan, Chunle Guo, Jixin Zhao, Yuekun Dai, Chen Change Loy, and Chongyi Li.
[Paper] [Project Page] [Code]

Flare7K: A Phenomenological Nighttime Flare Removal Dataset
Neural Information Processing Systems, NeurIPS 2022  
Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, and Chen Change Loy.
[Paper] [Project Page] [Code] [Video] [Dataset]

Awards

  • Outstanding Reviewer, BMVC. 2022
  • Outstanding Freshman Scholarship of School of Electronics Engineering and Computer Science, Peking University, 2016
  • First Prize in the 32nd National level Chinese Physics Olympiad (CPHO) (Rank 16), 2015
  • First Prize in 32nd Chinese Physics Olympiad (CPHO) in Hubei province (Rank 1), 2015
  • First Prize in 31st Chinese Physics Olympiad (CPHO) in Hubei province, 2014

Services

Conference and Workshop Committee Conference Reviewer:
  • CVPR 2024
  • AAAI 2022
  • MIPI@ECCV 2022,2023
  • NeurIPS 2022,2023
  • BMVC2022
Journal Reviewer:
  • Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • International Journal of Computer Vision (IJCV)
  • Transactions on Image Processing (TIP)
  • Transactions on Visualization and Computer Graphics (TVCG)
  • Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Transactions on Automation Science and Engineering (TASE)
  • Transactions on Multimedia Computing Communications and Applications (TOMM)
  • Signal, Image and Video Processing (SIVP)
  • Journal of Oceanic Engineering (JOE)

Interests

Physics: I have a deep interest in Physics and participated in the Chinese Physics Olympiad (CPHO) during high school. If you're interested in CPHO, feel free to check out my notes for the physics competition (in Chinese): [Google Drive/Baidu Netdisk]. The notes are divided into five volumes, covering the following topics:

  • Volume 1: Challenging topics in high school physics, Mechanics, Thermodynamics, Electromagnetism, Geometric Optics, Calculus.
  • Volume 2: Physical Optics, Theoretical Mechanics, Statistical Thermodynamics (1), Common Mathematical Tools in Physics, Linear Algebra.
  • Volume 3: Methods of Mathematical Physics, Vector Calculus, Statistical Thermodynamics (2), Tensor Calculus, Electrodynamics (1).
  • Volume 4: Electrodynamics (2), Quantum Mechanics, Calculus of Variations.
  • Volume 5: Atomic Physics.
Video Editting: In my free time, I enjoy creating motion graphics and music videos using Adobe After Effects, Blender, and Cinema 4D. I created the opening movie for the game Snowdome. You can view the playlist of my videos here. I have recently been actively incorporating generative AI into my workflow.