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

Multi-Scale Recursive and Perception-Distortion Controllable Image Super-Resolution

2019-01-29
Pablo Navarrete Michelini, Dan Zhu, Hanwen Liu

Abstract

We describe our solution for the PIRM Super-Resolution Challenge 2018 where we achieved the 2nd best perceptual quality for average RMSE<=16, 5th best for RMSE<=12.5, and 7th best for RMSE<=11.5. We modify a recently proposed Multi-Grid Back-Projection (MGBP) architecture to work as a generative system with an input parameter that can control the amount of artificial details in the output. We propose a discriminator for adversarial training with the following novel properties: it is multi-scale that resembles a progressive-GAN; it is recursive that balances the architecture of the generator; and it includes a new layer to capture significant statistics of natural images. Finally, we propose a training strategy that avoids conflicts between reconstruction and perceptual losses. Our configuration uses only 281k parameters and upscales each image of the competition in 0.2s in average.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1809.10711

PDF

http://arxiv.org/pdf/1809.10711


Similar Posts

Comments