# Spatially-Adaptive Pixelwise Networks for Fast Image Translation

Source: [Spatially-Adaptive Pixelwise Networks for Fast Image Translation](<https://www.sota2.com/research/paper/68fa68e01e209131cea1ee27>)

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

Data updated: 2025-10-25T22:48:52.480Z

Authors: Tamar Rott Shaham, Michael Gharbi, Richard Zhang, Eli Shechtman, Tomer Michaeli

Published: 2020-12-05T10:02:03.000Z

## Abstract

We introduce a new generator architecture, aimed at fast and efficient high-resolution image-to-image translation. We design the generator to be an extremely lightweight function of the full-resolution image. In fact, we use pixel-wise networks; that is, each pixel is processed independently of others, through a composition of simple affine transformations and nonlinearities. We take three important steps to equip such a seemingly simple function with adequate expressivity. First, the parameters of the pixel-wise networks are spatially varying so they can represent a broader function class than simple 1x1 convolutions. Second, these parameters are predicted by a fast convolutional network that processes an aggressively low-resolution representation of the input; Third, we augment the input image with a sinusoidal encoding of spatial coordinates, which provides an effective inductive bias for generating realistic novel high-frequency image content. As a result, our model is up to 18x faster than state-of-the-art baselines. We achieve this speedup while generating comparable visual quality across different image resolutions and translation domains.

## 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.

- [Wide-gamut color recovery on ProPhoto 1.0 (test)](<https://www.sota2.com/research/sota/wide-gamut-color-recovery-on-prophoto-1-0-test.md>): Wide-gamut color recovery; ProPhoto 1.0 (test); RMSE: 0.0518.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.02992>)

[PDF](<https://arxiv.org/pdf/2012.02992.pdf>)