Learning Enriched Features for Fast Image Restoration and Enhancement

  title={Learning Enriched Features for Fast Image Restoration and Enhancement},
  author={Syed Waqas Zamir and Aditya Arora and Salman Khan and Hayat Munawar and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},
  journal={IEEE transactions on pattern analysis and machine intelligence},
Given a degraded image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous vehicles, and remote sensing. Significant advances in image restoration have been made in recent years, dominated by convolutional neural networks (CNNs). The widely-used CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations… 


Learning Enriched Features for Real Image Restoration and Enhancement
This paper presents a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network and receiving strong contextual information from the low- resolution representations, named as MIRNet.
Restormer: Efficient Transformer for High-Resolution Image Restoration
This work proposes an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images.
Self-Guided Network for Fast Image Denoising
A self-guided network (SGN), which adopts a top-down self-guidance architecture to better exploit image multi-scale information and extract good local features to recover noisy images.
Residual Dense Network for Image Restoration
This work proposes residual dense block (RDB) to extract abundant local features via densely connected convolutional layers and proposes local feature fusion in RDB to adaptively learn more effective features from preceding and current local features and stabilize the training of wider network.
Multi-Stage Progressive Image Restoration
This paper proposes a novel synergistic design that can optimally balance these competing goals in image restoration tasks, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps.
HighEr-Resolution Network for Image Demosaicing and Enhancing
A HighEr-Resolution Network (HERN) to fully learning global information in high-resolution image patches by combining global-aware features and multi-scale features, which achieves state-of-the-art performance on the AIM2019 RAW to RGB mapping challenge.
Deep bilateral learning for real-time image enhancement
This work introduces a new neural network architecture inspired by bilateral grid processing and local affine color transforms that processes high-resolution images on a smartphone in milliseconds, provides a real-time viewfinder at 1080p resolution, and matches the quality of state-of theart approximation techniques on a large class of image operators.
Fast and Accurate Single Image Super-Resolution via Information Distillation Network
This work proposes a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image and demonstrates that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance.
Spatial-Adaptive Network for Single Image Denoising
A novel spatial-adaptive denoising network (SADNet) for efficient single image blind noise removal and can surpass the state-of-the-art denoised methods both quantitatively and visually.
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.