# Procedural Kernel Networks

arXiv: https://arxiv.org/abs/2112.09318 · HTML: https://mlsanity.com/paper/2112.09318/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 20 of 20)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Burst Denoising with Kernel Prediction Networks](https://mlsanity.com/paper/1712.02327/) (2017)
- [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021)
- [Handheld Multi-Frame Super-Resolution](https://mlsanity.com/paper/1905.03277/) (2019)
- [A General Decoupled Learning Framework for Parameterized Image Operators](https://mlsanity.com/paper/1907.05852/) (2019)
- [Synthetic Depth-of-Field with a Single-Camera Mobile Phone](https://mlsanity.com/paper/1806.04171/) (2018)
- [Fast End-to-End Trainable Guided Filter](https://mlsanity.com/paper/1803.05619/) (2018)
- [Basis Prediction Networks for Effective Burst Denoising with Large Kernels](https://mlsanity.com/paper/1912.04421/) (2019)
- [Spatially-Adaptive Pixelwise Networks for Fast Image Translation](https://mlsanity.com/paper/2012.02992/) (2020)
- [Unrolled Optimization with Deep Priors](https://mlsanity.com/paper/1705.08041/) (2017)
- [DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring](https://mlsanity.com/paper/2103.09962/) (2021)
- [RAISR: Rapid and Accurate Image Super Resolution](https://mlsanity.com/paper/1606.01299/) (2016)
- [Polyblur: Removing mild blur by polynomial reblurring](https://mlsanity.com/paper/2012.09322/) (2020)
- [BLADE: Filter Learning for General Purpose Computational Photography](https://mlsanity.com/paper/1711.10700/) (2017)
- [Non-uniform Blur Kernel Estimation via Adaptive Basis Decomposition](https://mlsanity.com/paper/2102.01026/) (2021)
- [Pixel Adaptive Filtering Units](https://mlsanity.com/paper/1911.10581/) (2019)

## Built on by (most cited first, 2 of 2)

- [Discovering Multiple Algorithm Configurations](https://mlsanity.com/paper/2303.07434/) (2023)
- [LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation](https://mlsanity.com/paper/2407.09935/) (2024)

## Abstract (arXiv)

In the last decade Convolutional Neural Networks (CNNs) have defined the state of the art for many low level image processing and restoration tasks such as denoising, demosaicking, upscaling, or inpainting. However, on-device mobile photography is still dominated by traditional image processing techniques, and uses mostly simple machine learning techniques or limits the neural network processing to producing low resolution masks. High computational and memory requirements of CNNs, limited processing power and thermal constraints of mobile devices, combined with large output image resolutions (typically 8--12 MPix) prevent their wider application. In this work, we introduce Procedural Kernel Networks (PKNs), a family of machine learning models which generate parameters of image filter kernels or other traditional algorithms. A lightweight CNN processes the input image at a lower resolution, which yields a significant speedup compared to other kernel-based machine learning methods and allows for new applications. The architecture is learned end-to-end and is especially well suited for a wide range of low-level image processing tasks, where it improves the performance of many traditional algorithms. We also describe how this framework unifies some previous work applying machine learning for common image restoration tasks.