Hierarchical Back Projection Network for Image Super-Resolution

06/17/2019
by   Zhi-Song Liu, et al.
2

Deep learning based single image super-resolution methods use a large number of training datasets and have recently achieved great quality progress both quantitatively and qualitatively. Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual learning without exploring the feature abstraction and analysis. We propose a Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best representation for reconstruction. We adopt the back projection blocks in our proposed network to provide the error correlated up and down-sampling process to replace simple deconvolution and pooling process for better estimation. A new Softmax based Weighted Reconstruction (WR) process is used to combine the outputs of HG modules to further improve super-resolution. Experimental results on various datasets (including the validation dataset, NTIRE2019, of the Real Image Super-resolution Challenge) show that our proposed approach can achieve and improve the performance of the state-of-the-art methods for different scaling factors.

READ FULL TEXT

page 3

page 6

page 8

research
09/07/2020

Deep Iterative Residual Convolutional Network for Single Image Super-Resolution

Deep convolutional neural networks (CNNs) have recently achieved great s...
research
03/07/2018

Deep Back-Projection Networks For Super-Resolution

The feed-forward architectures of recently proposed deep super-resolutio...
research
11/20/2019

Dual Reconstruction with Densely Connected Residual Network for Single Image Super-Resolution

Deep learning-based single image super-resolution enables very fast and ...
research
02/15/2019

Lightweight Feature Fusion Network for Single Image Super-Resolution

Single image super-resolution(SISR) has witnessed great progress as conv...
research
06/02/2022

Super-resolving 2D stress tensor field conserving equilibrium constraints using physics informed U-Net

In a finite element analysis, using a large number of grids is important...
research
04/21/2023

Ultra Sharp : Study of Single Image Super Resolution using Residual Dense Network

For years, Single Image Super Resolution (SISR) has been an interesting ...
research
10/15/2018

Channel Splitting Network for Single MR Image Super-Resolution

High resolution magnetic resonance (MR) imaging is desirable in many cli...

Please sign up or login with your details

Forgot password? Click here to reset