-
An Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks
Recent works on single-image super-resolution are concentrated on improv...
read it
-
A Matrix-in-matrix Neural Network for Image Super Resolution
In recent years, deep learning methods have achieved impressive results ...
read it
-
Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution
Traditional single image super-resolution (SISR) methods that focus on s...
read it
-
Multi-Level Feature Fusion Mechanism for Single Image Super-Resolution
Convolution neural network (CNN) has been widely used in Single Image Su...
read it
-
Triple Attention Mixed Link Network for Single Image Super Resolution
Single image super resolution is of great importance as a low-level comp...
read it
-
Gated Fusion Network for Degraded Image Super Resolution
Single image super resolution aims to enhance image quality with respect...
read it
-
Image Super-Resolution Using Attention Based DenseNet with Residual Deconvolution
Image super-resolution is a challenging task and has attracted increasin...
read it
Single Image Super-Resolution via a Holistic Attention Network
Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.
READ FULL TEXT
Comments
There are no comments yet.