Efficient Image Super-Resolution Using Pixel Attention

10/02/2020
by   Hengyuan Zhao, et al.
0

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introduces fewer additional parameters but generates better SR results. On the basis of PA, we propose two building blocks for the main branch and the reconstruction branch, respectively. The first one - SC-PA block has the same structure as the Self-Calibrated convolution but with our PA layer. This block is much more efficient than conventional residual/dense blocks, for its twobranch architecture and attention scheme. While the second one - UPA block combines the nearest-neighbor upsampling, convolution and PA layers. It improves the final reconstruction quality with little parameter cost. Our final model- PAN could achieve similar performance as the lightweight networks - SRResNet and CARN, but with only 272K parameters (17.92 The effectiveness of each proposed component is also validated by ablation study. The code is available at https://github.com/zhaohengyuan1/PAN.

READ FULL TEXT
research
04/20/2023

Omni Aggregation Networks for Lightweight Image Super-Resolution

While lightweight ViT framework has made tremendous progress in image su...
research
10/12/2022

Efficient Image Super-Resolution using Vast-Receptive-Field Attention

The attention mechanism plays a pivotal role in designing advanced super...
research
05/12/2022

Blueprint Separable Residual Network for Efficient Image Super-Resolution

Recent advances in single image super-resolution (SISR) have achieved ex...
research
06/13/2021

Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution

Recently, deep convolutional neural network methods have achieved an exc...
research
11/30/2022

From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution

Image super-resolution (SR) serves as a fundamental tool for the process...
research
02/06/2022

Learning Features with Parameter-Free Layers

Trainable layers such as convolutional building blocks are the standard ...
research
08/03/2020

Sub-Pixel Back-Projection Network For Lightweight Single Image Super-Resolution

Convolutional neural network (CNN)-based methods have achieved great suc...

Please sign up or login with your details

Forgot password? Click here to reset