Z
Zengfu Wang
Researcher at University of Science and Technology of China
Publications - 8
Citations - 186
Zengfu Wang is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Sparse approximation & Motion compensation. The author has an hindex of 6, co-authored 8 publications receiving 135 citations. Previous affiliations of Zengfu Wang include Chinese Academy of Sciences.
Papers
More filters
Journal ArticleDOI
Video Superresolution via Motion Compensation and Deep Residual Learning
Dingyi Li,Zengfu Wang +1 more
TL;DR: A new method for video SR named motion compensation and residual net (MCResNet) is proposed, which employs a novel deep residual convolutional neural network (CNN) to predict a high-resolution image using multiple motion compensated observations.
Journal ArticleDOI
Video Super-Resolution Using Non-Simultaneous Fully Recurrent Convolutional Network
Dingyi Li,Yu Liu,Zengfu Wang +2 more
TL;DR: A very deep non-simultaneous fully recurrent convolutional network for video SR is proposed and results demonstrate that the proposed method is better than that of the state-of-the-art SR methods on quantitative visual quality assessment.
Proceedings ArticleDOI
A practical pan-sharpening method with wavelet transform and sparse representation
Yu Liu,Zengfu Wang +1 more
TL;DR: A new pan-sharpening method with sparse representation (SR) under the framework of wavelet transform that gives more spatial details and less spectral distortion compared with some conventional methods in terms of both visual quality and objective measurements.
Book ChapterDOI
Medical Image Fusion by Combining Nonsubsampled Contourlet Transform and Sparse Representation
TL;DR: Experimental results demonstrate that the proposed fusion method owns clear advantages over the fusion method based on NSCT or SR individually in terms of both visual quality and objective assessments.
Proceedings ArticleDOI
Multi-focus Image Fusion Based on Sparse Representation with Adaptive Sparse Domain Selection
Yu Liu,Zengfu Wang +1 more
TL;DR: This paper proposes a multi-focus image fusion method based on SR with adaptive sparse domain selection (SR-ASDS) that outperforms the fusion methods which use a single dictionary, in terms of several popular objective evaluation criteria.