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.

arXiv commentTo appear in ICLR 2019

Cited by in corpus (53)

• Neural Image Compression via Non-Local Attention Optimization and Improved Context Modeling
• Non-local Attention Optimized Deep Image Compression
• Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
• Restormer: Efficient Transformer for High-Resolution Image Restoration
• Polarized Self-Attention: Towards High-quality Pixel-wise Regression
• Cross-Scale Internal Graph Neural Network for Image Super-Resolution
• Uformer: A General U-Shaped Transformer for Image Restoration
• A Two-Stage Attentive Network for Single Image Super-Resolution
• Deep Learning for Image Super-resolution: A Survey
• Pyramid Attention Networks for Image Restoration
• Learning Enriched Features for Real Image Restoration and Enhancement
• Attention in Attention Network for Image Super-Resolution
• Multi-Stage Progressive Image Restoration
• Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
• Joint Transmission Map Estimation and Dehazing using Deep Networks
• Relation-Aware Global Attention for Person Re-identification
• Residual Feature Distillation Network for Lightweight Image Super-Resolution
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification
• NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
• NL-LinkNet: Toward Lighter but More Accurate Road Extraction with Non-Local Operations
• Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
• Self-Supervised Fast Adaptation for Denoising via Meta-Learning
• Progressive Perception-Oriented Network for Single Image Super-Resolution
• Local-Selective Feature Distillation for Single Image Super-Resolution
• Combinational Class Activation Maps for Weakly Supervised Object Localization
• Spatial-Adaptive Network for Single Image Denoising
• Learning Context-Based Non-local Entropy Modeling for Image Compression
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model
• Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
• 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
• BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
• Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution
• Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
• SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
• EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration
• Restore from Restored: Single Image Denoising with Pseudo Clean Image
• Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
• Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline
• Super-resolving Compressed Images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement
• Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
• Gated Texture CNN for Efficient and Configurable Image Denoising
• Robust Regression via Deep Negative Correlation Learning
• edge-SR: Super-Resolution For The Masses
• Image-specific Convolutional Kernel Modulation for Single Image Super-resolution
• Self-Verification in Image Denoising
• In-Orbit Lunar Satellite Image Super Resolution for Selective Data Transmission
• Low Bitrate Image Compression with Discretized Gaussian Mixture Likelihoods
• Back-Projection Pipeline
• Enhancing and Learning Denoiser without Clean Reference
• Multi-Grid Back-Projection Networks