Zongsheng Yue

Zongsheng Yue
Nanyang Technological University | ntu · School of Science and Engineering

PhD

About

12
Publications
1,333
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
273
Citations
Citations since 2016
12 Research Items
273 Citations
2016201720182019202020212022020406080100120
2016201720182019202020212022020406080100120
2016201720182019202020212022020406080100120
2016201720182019202020212022020406080100120
Introduction
I'm interested in the low-level vision tasks, such as image super-resolution, deblurring, denoising and so on. I mainly focus on developing more interpretable image restoration algorithm based on Bayesian methods.
Additional affiliations
October 2018 - June 2019
The Hong Kong Polytechnic University
Position
  • Research Assistant
February 2017 - September 2017
The Chinese University of Hong Kong
Position
  • Research Assistant
Education
March 2017 - June 2021
Xi'an Jiaotong University
Field of study
  • Applied Mathematics
September 2015 - March 2017
Xi'an Jiaotong University
Field of study
  • Applied Mathematics
September 2011 - June 2015
Xin Jiang University
Field of study
  • Applied Mathematics

Publications

Publications (12)
Preprint
Full-text available
While the researches on single image super-resolution (SISR), especially equipped with deep neural networks (DNNs), have achieved tremendous successes recently, they still suffer from two major limitations. Firstly, the real image degradation is usually unknown and highly variant from one to another, making it extremely hard to train a single model...
Preprint
Full-text available
Blind image deblurring is an important yet very challenging problem in low-level vision. Traditional optimization based methods generally formulate this task as a maximum-a-posteriori estimation or variational inference problem, whose performance highly relies on the handcraft priors for both the latent image and the blur kernel. In contrast, recen...
Preprint
Full-text available
Deep neural networks (DNNs) have achieved significant success in image restoration tasks by directly learning a powerful non-linear mapping from corrupted images to their latent clean ones. However, there still exist two major limitations for these deep learning (DL)-based methods. Firstly, the noises contained in real corrupted images are very com...
Conference Paper
Full-text available
Real-world image noise removal is a long-standing yet very challenging task in computer vision. The success of deep neural network in denoising stimulates the research of noise generation, aiming at synthesizing more clean-noisy image pairs to facilitate the training of deep denoisers. In this work, we propose a novel unified framework to simultane...
Article
Full-text available
Blind image denoising is an important yet very challenging problem in computer vision due to the complicated acquisition process of real images. In this work we propose a new variational inference method, which integrates both noise estimation and image denoising into a unique Bayesian framework, for blind image denoising. Specifically, an approxim...
Article
Full-text available
Multiview Subspace Learning (MSL), which aims at obtaining a low-dimensional latent subspace from multiview data, has been widely used in practical applications. Most recent MSL approaches, however, only assume a simple independent identically distributed (i.i.d.) Gaussian or Laplacian noise for all views of data, which largely underestimates the n...
Article
Full-text available
Hyperspectral images (HSIs) are always corrupted by complicated forms of noise during the acquisition process, such as Gaussian noise, impulse noise, stripes, deadlines and so on. Specifically, different bands of the practical HSIs generally contain different noises of evidently distinct type and extent. While current HSI restoration methods give l...
Article
Graph-based semi-supervised learning (GSSL) attracts considerable attention in recent years. The performance of a general GSSL method relies on the quality of Laplacian weighted graph (LWR) composed of the similarity imposed on input examples. A key for constructing an effective LWR is on the proper selection of the neighborhood size K or ε on the...

Network

Cited By