Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining

  title={Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining},
  author={Yiqun Mei and Yuchen Fan and Yuqian Zhou and Lichao Huang and Thomas S. Huang and Humphrey Shi},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Yiqun Mei, Yuchen Fan, Humphrey Shi
  • Published 1 June 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Deep convolution-based single image super-resolution (SISR) networks embrace the benefits of learning from large-scale external image resources for local recovery, yet most existing works have ignored the long-range feature-wise similarities in natural images. Some recent works have successfully leveraged this intrinsic feature correlation by exploring non-local attention modules. However, none of the current deep models have studied another inherent property of images: cross-scale feature… 

Figures and Tables from this paper

Single Image Super-Resolution Network Based on Multiple- Scale Self-Similarity Module

A multiple-scale self-similarity module (MSSS) that can be flexibly inserted into existing various super-resolution networks, and the result is significantly improved.

Single MR image super-resolution via mixed self-similarity attention network

A mixed self-similarity attention network (MSAN) to explore the long-range dependencies of different regions fully and achieves significantly superior results on MR images SR while outperforming state-of-the-art methods by a large margin quantitatively and visually.

NL-FFC: Non-Local Fast Fourier Convolution for Image Super Resolution

This work proposes an architecture that learns both local and global features, and fuses them together to generate high quality images, and investigates the role of non-local attention, and the ratio of local andglobal features to maximize the performance gain in the ablation study.

Residual deep attention mechanism and adaptive reconstruction network for single image super-resolution

To discriminate between large and small gray changes in adjacent areas in LR images, a novel spatial and channel attention processing module (SCAM) is developed that incorporates non-local operations to capture long-distance dependencies between pixels in the spatial domain, and automatically rescales hierarchical features with different weights.

Pyramid Orthogonal Attention Network based on Dual Self-Similarity for Accurate Mr Image Super-Resolution

This work proposes a pyramid orthogonal attention network (POAN) based on dual self-similarity, which reconstructs the MR image under the guidance of pyramid orthOGonal attention and obtains the best results compared with state-of-the-art MR image SR methods quantitatively and visually.

Cross-Dimension Attention Guided Self-Supervised Remote Sensing Single-Image Super-Resolution

This paper proposes a cross-dimension attention guided self-supervised remote sensing single-image super-resolution method (CASSISR), which does not require pre-training on a dataset, only utilizes the internal information reproducibility of a single image, and uses the lower-resolution image downsampled from the input image to train the cross- dimension attention network (CDAN).

Attention-based Multi-Reference Learning for Image Super-Resolution

This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple

Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution

A dynamic high-pass filtering module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals and a matrix multi-spectral channel attention module that predicts the attention map of features decomposed in the frequency domain.

Pyramid Attention Networks for Image Restoration

A novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid, and is designed to be able to borrow clean signals from their "clean" correspondences at the coarser levels.

Attention Network with Information Distillation for Super-Resolution

Comprehensive quantitative and qualitative evaluations demonstrate that the proposed attention network with information distillation (AIDN) outperforms state-of-the-art models in terms of reconstruction performance and visual quality.



Second-Order Attention Network for Single Image Super-Resolution

Experimental results demonstrate the superiority of the SAN network over state-of-the-art SISR methods in terms of both quantitative metrics and visual quality.

Non-Local Recurrent Network for Image Restoration

A non- local recurrent network (NLRN) is proposed as the first attempt to incorporate non-local operations into a recurrent neural network (RNN) for image restoration and achieves superior results to state-of-the-art methods with much fewer parameters.

Fast Image Super-Resolution Based on In-Place Example Regression

We propose a fast regression model for practical single image super-resolution based on in-place examples, by leveraging two fundamental super-resolution approaches- learning from an external

Residual Dense Network for Image Super-Resolution

This paper proposes residual dense block (RDB) to extract abundant local features via dense connected convolutional layers and uses global feature fusion in RDB to jointly and adaptively learn global hierarchical features in a holistic way.

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.

Residual Non-local Attention Networks for Image Restoration

The proposed residual local and non-local attention learning to train the very deep network is generalized for various image restoration applications, such as image denoising, demosaicing, compression artifacts reduction, and super-resolution.

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

This paper proposes the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images and generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications.

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

Extensive experimental results show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.

Feedback Network for Image Super-Resolution

An image super-resolution feedback network (SRFBN) is proposed to refine low-level representations with high-level information by using hidden states in a recurrent neural network (RNN) with constraints to achieve such feedback manner.

ODE-Inspired Network Design for Single Image Super-Resolution

This paper proposes to adopt an ordinary differential equation (ODE)-inspired design scheme for single image super-resolution, and derives two types of network structures: LF-block and RK-block, which correspond to the Leapfrog method and Runge-Kutta method in numerical ordinary differential equations.