Procedural Kernel Networks

12/17/2021
by   Bartlomiej Wronski, et al.
19

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.

READ FULL TEXT

page 3

page 4

page 5

page 6

page 7

page 8

page 9

research
07/11/2020

Lightweight Modules for Efficient Deep Learning based Image Restoration

Low level image restoration is an integral component of modern artificia...
research
04/20/2023

Revisiting Implicit Neural Representations in Low-Level Vision

Implicit Neural Representation (INR) has been emerging in computer visio...
research
01/02/2020

A Machine Learning Imaging Core using Separable FIR-IIR Filters

We propose fixed-function neural network hardware that is designed to pe...
research
04/07/2017

Convolutional Neural Pyramid for Image Processing

We propose a principled convolutional neural pyramid (CNP) framework for...
research
03/11/2020

Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks

In Convolutional Neural Network (CNN) based image processing, most of th...
research
03/11/2020

Regularized Adaptation for Stable and Efficient Continuous-Level Learning

In Convolutional Neural Network (CNN) based image processing, most of th...

Please sign up or login with your details

Forgot password? Click here to reset