I am currently a PhD student in the Department of Computing Science at the University of Alberta advised by Prof. Herb Yang. I am mainly interested in 3D Reconstruction/Generaton/Editing, Generative AI, and Computational Photography.

Here is my CV

Email: dhuo [!at!] ualberta [!dot!] ca

Publications

• Learning to Recover Spectral Reflectance from RGB Images
  Dong Huo, Jian Wang, Yiming Qian, Yee-Hong Yang
  IEEE Transactions on Image Processing (TIP), 2024
  [Paper], [Code], [Dataset]


• Blind Image Deconvolution Using Variational Deep Image Prior
  Dong Huo, Abbas Masoumzadeh, Rafsanjany Kushol, Yee-Hong Yang
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
  [Paper], [Code]


• Glass Segmentation with RGB-Thermal Image Pairs
  Dong Huo, Jian Wang, Yiming Qian, Yee-Hong Yang
  IEEE Transactions on Image Processing (TIP), 2023
  [Paper], [Code], [Dataset]


• Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency
  Dong Huo, Abbas Masoumzadeh, Yee-Hong Yang
  New Trends in Image Restoration and Enhancement Workshop and Challenges at CVPR (CVPRW), 2022
  [Paper], [Code]


• Addformer: Alzheimer’s Disease Detection from Structural Mri Using Fusion Transformer
  Rafsanjany Kushol, Abbas Masoumzadeh, Dong Huo, Sanjay Kalra, Yee-Hong Yang
  International Symposium on Biomedical Imaging (ISBI), 2022
  [Paper], [Code]


• Structured Light with Redundancy Codes
  Zhanghao Sun, Yu Zhang, Yicheng Wu, Dong Huo, Yiming Qian, Jian Wang
  Technical Report, 2022
  [Paper]


• Blind Image Super-Resolution with Spatial Context Hallucination
  Dong Huo, Yee-Hong Yang
  Technical Report, 2020
  [Paper]

Patents

• A kind of mark extracting method for the medical image lesion that can improve doctor's efficiency
  Tonghua Su, Bin Li, Dong Huo
  China patent CN109003269A
  [Google Patent]


• Method for automatically generating medical image diagnosis report based on deep learning method
  Tonghua Su, Lijuan Yu, Dong Huo
  China patent CN109065110B
  [Google Patent]