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

arXiv: https://arxiv.org/abs/1809.10711 · HTML: https://mlsanity.com/paper/1809.10711/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2018.

## Built on by (most cited first, 4 of 4)

- [A Theory of the Distortion-Perception Tradeoff in Wasserstein Space](https://mlsanity.com/paper/2107.02555/) (2021)
- [Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution](https://mlsanity.com/paper/2208.03324/) (2022)
- [DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluator](https://mlsanity.com/paper/2211.04927/) (2022)
- [Multi-Grid Back-Projection Networks](https://mlsanity.com/paper/2101.00150/) (2021)

## Abstract (arXiv)

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.