# Pixel Recursive Super Resolution

Source: [Pixel Recursive Super Resolution](<https://www.sota2.com/research/paper/68fa63321e209131ce9fd4d2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:35:17.063Z

Authors: Ryan Dahl, Mohammad Norouzi, Jonathon Shlens

Published: 2017-02-02T18:59:17.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Super-resolution on CelebA standard (val)](<https://www.sota2.com/research/sota/image-super-resolution-on-celeba-standard-val.md>): Image Super-resolution; CelebA standard (val); Fooled Rate: 11.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1702.00783>)

[PDF](<https://arxiv.org/pdf/1702.00783.pdf>)