Image Superresolution using Scale-Recurrent Dense Network

01/28/2022
by   Kuldeep Purohit, et al.
3

Recent advances in the design of convolutional neural network (CNN) have yielded significant improvements in the performance of image super-resolution (SR). The boost in performance can be attributed to the presence of residual or dense connections within the intermediate layers of these networks. The efficient combination of such connections can reduce the number of parameters drastically while maintaining the restoration quality. In this paper, we propose a scale recurrent SR architecture built upon units containing series of dense connections within a residual block (Residual Dense Blocks (RDBs)) that allow extraction of abundant local features from the image. Our scale recurrent design delivers competitive performance for higher scale factors while being parametrically more efficient as compared to current state-of-the-art approaches. To further improve the performance of our network, we employ multiple residual connections in intermediate layers (referred to as Multi-Residual Dense Blocks), which improves gradient propagation in existing layers. Recent works have discovered that conventional loss functions can guide a network to produce results which have high PSNRs but are perceptually inferior. We mitigate this issue by utilizing a Generative Adversarial Network (GAN) based framework and deep feature (VGG) losses to train our network. We experimentally demonstrate that different weighted combinations of the VGG loss and the adversarial loss enable our network outputs to traverse along the perception-distortion curve. The proposed networks perform favorably against existing methods, both perceptually and objectively (PSNR-based) with fewer parameters.

READ FULL TEXT
research
01/28/2022

Deep Networks for Image and Video Super-Resolution

Efficiency of gradient propagation in intermediate layers of convolution...
research
12/31/2021

Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning

Deep convolutional neural networks have been demonstrated to be effectiv...
research
07/14/2021

Multi-Attention Generative Adversarial Network for Remote Sensing Image Super-Resolution

Image super-resolution (SR) methods can generate remote sensing images w...
research
09/02/2020

Real Image Super Resolution Via Heterogeneous Model using GP-NAS

With advancement in deep neural network (DNN), recent state-of-the-art (...
research
11/15/2021

Optimizing Unlicensed Coexistence Network Performance Through Data Learning

Unlicensed LTE-WiFi coexistence networks are undergoing consistent densi...
research
12/15/2019

Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks

Convolutional Recurrent Neural Network (CRNN) is a popular network for r...
research
02/06/2018

Scale-recurrent Network for Deep Image Deblurring

In single image deblurring, the "coarse-to-fine" scheme, i.e. gradually ...

Please sign up or login with your details

Forgot password? Click here to reset