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 three representative IR applications, single image super-resolution, Gaussian image denoising, and image compression artifact reduction. Experiments on benchmark datasets show that our RDN achieves favorable performance against state-of-the-art methods for each IR task.

GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-Based Real-World Noise Modeling

“…From the viewpoint of CNNs, network architectures developed for different image restoration tasks such as image denoising, image deblurring, super-resolution, and compress artifact reduction share similarities. It has been repeatedly demonstrated that one architecture developed for a certain image restoration task also performs well in other restoration tasks [30,32,23]. We thus examined many of the architectures developed for different image restoration tasks, especially super-resolution [7,13,16,17,14,26,33,31,11,18].…”

“…The position of the CBAM block was empirically chosen as in-between the upconvolutional layer and the last convolutional layer. Although GRDN is structurally deeper than RDN [33,32], we used the same number of RDBs. Specifically, 16 RDBs were used in the original RDN for image denoising.…”

“…The network architecture is of course the utmost important. In CNN-based image restoration, dense residual blocks (RDBs) [33,32] have received great attention. In this paper, we propose a new architecture called grouped residual dense network (GRDN).…”

A Dual-Attention Recurrent Neural Network Method for Deep Cone Thickener Underflow Concentration Prediction

“…A single hidden layer neural network composed with learnable input layer (W y , b w ) and hidden layer(v y , b v ) is utilized to produce the final prediction result. The usage of c T in the last prediction phase could be explained from multi-level feature fusion perspective [26]. Because c T is the weight-sum of (h 1 , h 2 , .…”

Nonlinear decoding of natural images from large-scale primate retinal ganglion recordings

“…Specifically, this step represents an unknown combination of super-resolution, deblurring, denoising, and inpainting. With ongoing advances in image restoration networks that can handle more complex blur kernels and noise, it is likely that further improvements in performance are possible[36][37][38][39][40][41][42][43][44].Finally, while our decoding approach helped shed some light on the importance of nonlinear spike temporal correlations and OFF midget cell signals on accurate, high-pass decoding, the specific mechanisms of visual decoding have yet to be fully investigated. Indeed, many other sources of nonlinearity, including nonlinear spatial interactions within RGCs or nonlinear interactions between RGCs or RGC types, are all factors that could help justify nonlinear decoding that we did not explore…”