Residual Non-local Attention Networks for Image Restoration

Abstract

In this paper, we propose a residual non-local attention network for high-quality image restoration. Without considering the uneven distribution of information in the corrupted images, previous methods are restricted by local convolutional operation and equal treatment of spatial- and channel-wise features. To address this issue, we design local and non-local attention blocks to extract features that capture the long-range dependencies between pixels and pay more attention to the challenging parts. Specifically, we design trunk branch and (non-)local mask branch in each (non-)local attention block. The trunk branch is used to extract hierarchical features. Local and non-local mask branches aim to adaptively rescale these hierarchical features with mixed attentions. The local mask branch concentrates on more local structures with convolutional operations, while non-local attention considers more about long-range dependencies in the whole feature map. Furthermore, we propose residual local and non-local attention learning to train the very deep network, which further enhance the representation ability of the network. Our proposed method can be generalized for various image restoration applications, such as image denoising, demosaicing, compression artifacts reduction, and super-resolution. Experiments demonstrate that our method obtains comparable or better results compared with recently leading methods quantitatively and visually.

To appear in ICLR 2019

Cited by in corpus (25)

• Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
• Polarized Self-Attention: Towards High-quality Pixel-wise Regression
• A Two-Stage Attentive Network for Single Image Super-Resolution
• Multi-Stage Progressive Image Restoration
• Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification
• Residual Feature Distillation Network for Lightweight Image Super-Resolution
• NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
• Self-Supervised Fast Adaptation for Denoising via Meta-Learning
• Combinational Class Activation Maps for Weakly Supervised Object Localization
• Learning Context-Based Non-local Entropy Modeling for Image Compression
• Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
• Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model
• Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
• NTIRE 2020 Challenge on Image Demoireing: Methods and Results
• Symmetric Parallax Attention for Stereo Image Super-Resolution
• Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
• Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
• Gated Texture CNN for Efficient and Configurable Image Denoising
• Back-Projection Pipeline
• Low Bitrate Image Compression with Discretized Gaussian Mixture Likelihoods
• Multi-Grid Back-Projection Networks
• Self-Verification in Image Denoising
• In-Orbit Lunar Satellite Image Super Resolution for Selective Data Transmission
• edge-SR: Super-Resolution For The Masses