# Pixel Recursive Super Resolution

## TL;DR

This paper introduces a pixel recursive super resolution model that generates more realistic, detailed high-resolution images from low-resolution inputs by modeling pixel dependencies, outperforming traditional methods in realism.

## Contribution

The paper proposes a novel pixel recursive super resolution approach using PixelCNN architecture to better model multimodal high-res image distributions conditioned on low-res inputs.

## Key findings

- Samples are more photo realistic than L2 regression baseline.
- Model effectively captures multimodal distributions of high-res images.
- Human evaluations favor the proposed model's realism.

## Abstract

We present a pixel recursive super resolution model that synthesizes realistic details into images while enhancing their resolution. A low resolution image may correspond to multiple plausible high resolution images, thus modeling the super resolution process with a pixel independent conditional model often results in averaging different details--hence blurry edges. By contrast, our model is able to represent a multimodal conditional distribution by properly modeling the statistical dependencies among the high resolution image pixels, conditioned on a low resolution input. We employ a PixelCNN architecture to define a strong prior over natural images and jointly optimize this prior with a deep conditioning convolutional network. Human evaluations indicate that samples from our proposed model look more photo realistic than a strong L2 regression baseline.