• Corpus ID: 237485602

BAM: A Balanced Attention Mechanism for Single Image Super Resolution

  title={BAM: A Balanced Attention Mechanism for Single Image Super Resolution},
  author={Fanyi Wang and Haotian Hu and Cheng Shen},
  • Fanyi Wang, Haotian Hu, Cheng Shen
  • Published 15 April 2021
  • Engineering, Computer Science
Recovering texture information from the aliasing regions has always been a major challenge for Single Image Super Resolution (SISR) task. These regions are often submerged in noise so that we have to restore texture details while suppressing noise. To address this issue, we propose a Balanced Attention Mechanism (BAM), which consists of Avgpool Channel Attention Module (ACAM) and Maxpool Spatial Attention Module (MSAM) in parallel. ACAM is designed to suppress extreme noise in the large scale… 

Figures and Tables from this paper


Efficient Image Super-Resolution Using Pixel Attention
This work designs a lightweight convolutional neural network for image super resolution with a newly proposed pixel attention scheme that could achieve similar performance as the lightweight networks - SRResNet and CARN, but with only 272K parameters.
SRFeat: Single Image Super-Resolution with Feature Discrimination
A novel GAN-based SISR method that overcomes the limitation and produces more realistic results by attaching an additional discriminator that works in the feature domain and design a new generator that utilizes long-range skip connections so that information between distant layers can be transferred more effectively.
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
This work proposes a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections, and proposes a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels.
Lightweight Image Super-Resolution with Information Multi-distillation Network
An adaptive cropping strategy (ACS) is developed to super-resolve block-wise image patches using the same well-trained model and performs favorably against the state-of-the-art SR algorithms in terms of visual quality, memory footprint, and inference time.
s-LWSR: Super Lightweight Super-Resolution Network
This article proposes a flexibly adjustable super-lightweight SISR pipeline, with limited parameters and operations, that can achieve a similar performance to that of other cumbersome but state-of-the-art (SOTA) deep SR methods.
Accelerating the Super-Resolution Convolutional Neural Network
This paper aims at accelerating the current SRCNN, and proposes a compact hourglass-shape CNN structure for faster and better SR, and presents the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance.
Residual Dense Convolutional Neural Network for Image Super-Resolution
This paper introduces a tripartite CNN for multi-color SR enhancement and develops a deconvolution step at the end of the network structure, and mapping is applied to the input LR luminance, used as a reference for the HR image.
Image Super-Resolution Using Dense Skip Connections
A novel single-image super-resolution method is presented by introducing dense skip connections in a very deep network, providing an effective way to combine the low-level features and high- level features to boost the reconstruction performance.
Densely Residual Laplacian Super-Resolution
  • Saeed Anwar, N. Barnes
  • Engineering, Computer Science
    IEEE transactions on pattern analysis and machine intelligence
  • 2020
This work presents a compact and accurate super-resolution algorithm, namely, Densely Residual Laplacian Network (DRLN), which employs cascading residual on the residual structure to allow the flow of low-frequency information to focus on learning high and mid-level features.
Single image super-resolution from transformed self-exemplars
This paper expands the internal patch search space by allowing geometric variations, and proposes a compositional model to simultaneously handle both types of transformations to accommodate local shape variations.