Residual Dense Network for Image Restoration

Abstract

Convolutional neural network has recently achieved great success for image restoration (IR) and also offered hierarchical features. However, most deep CNN based IR models do not make full use of the hierarchical features from the original low-quality images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in IR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via densely connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory mechanism. To adaptively learn more effective features from preceding and current local features and stabilize the training of wider network, we proposed local feature fusion in RDB. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. We demonstrate the effectiveness of RDN with several representative IR applications, single image super-resolution, Gaussian image denoising, image compression artifact reduction, and image deblurring. Experiments on benchmark and real-world datasets show that our RDN achieves favorable performance against state-of-the-art methods for each IR task quantitatively and visually.

arXiv commentTo appear in TPAMI. arXiv admin note: substantial text overlap with arXiv:1802.08797

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Sketch-based Manga Retrieval using Manga109 Dataset
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Denoising Prior Driven Deep Neural Network for Image Restoration
• Residual Dense Network for Image Super-Resolution
• Tell Me Where to Look: Guided Attention Inference Network

Cited by in corpus (10)

• Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction
• Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
• LIDIA: Lightweight Learned Image Denoising with Instance Adaptation
• High-Quality Self-Supervised Deep Image Denoising
• Lightweight Residual Densely Connected Convolutional Neural Network
• Distributed Learning and Inference with Compressed Images
• GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling
• GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• Back-Projection Pipeline