papers AI Learner
The Github is limit! Click to go to the new site.

Efficient Super Resolution For Large-Scale Images Using Attentional GAN

2019-01-13
Harsh Nilesh Pathak, Xinxin Li, Shervin Minaee, Brooke Cowan

Abstract

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1812.04821

PDF

https://arxiv.org/pdf/1812.04821


Similar Posts

下一篇 Light-Field for RF

Comments