Efficient Super Resolution For Large-Scale Image Using Attentional GAN

by   Harsh Nilesh Pathak, et al.

Single Image Super Resolution (SISR) is a well-researched problem with broad commercial relevance. However, most of the SISR literature focuses on small-size images under 500px, whereas business needs can mandate the generation of very high resolution images. At Expedia Group, we were tasked with generating images of at least 2000px for display on the website, four times greater than the sizes typically reported in the literature. This requirement poses a challenge that state-of-the-art models, validated on small images, have not been proven to handle. In this paper, we investigate solutions to the problem of generating high-quality images for large-scale super resolution in a commercial setting. We find that training a generative adversarial network (GAN) with attention from scratch using a large-scale lodging image data set generates images with high PSNR and SSIM scores. We describe a novel attentional SISR model for large-scale images, A-SRGAN, that uses a Flexible Self Attention layer to enable processing of large-scale images. We also describe a distributed algorithm which speeds up training by around a factor of five.


page 1

page 5

page 6

page 7

page 11


Efficient Super Resolution For Large-Scale Images Using Attentional GAN

Single Image Super Resolution (SISR) is a well-researched problem with b...

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the AIM 2020 challenge on efficient single image supe...

TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation

Deep generative models have been successfully applied to many applicatio...

A Bayesian Nonparametric Approach to Image Super-resolution

Super-resolution methods form high-resolution images from low-resolution...

A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancement

Deep neural networks for image quality enhancement typically need large ...

Image Tranformer

Image generation has been successfully cast as an autoregressive sequenc...

Please sign up or login with your details

Forgot password? Click here to reset