Skip to content

we1314love/Neural-Networks-for-Low-Level-Image-Processing

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 

Repository files navigation

Neural Networks for Low Level Image Processing

Until recently, machine learning (ML) and neural network (NN) have been mainly used in high level vision tasks, such as image segmentation, classification and object detection. Low level image processing tasks such as denoising, demosaicing, white balance still mainly rely on signal processing based methods which need a lot of expert knowledge to desige the filters. There are usually a long list of filters in a complete image processing pipeline running on a dedicated image signal processor(ISP). Designing and optimizing a list of filters require a lot of effort. Apple has a patent with more than 500 pages covering only a part of the full ISP pipeline!

In the past few years, two new developments are changing the image processing field. One trend is that more and more neural network based methods have been proposed to handle a part or the whole image processing pipeline and achieved fascinating performance in term of image quality and processing speed. The other trend is that neural network chip becomes more and more popular at various mobile platform, such as the latest Apple A11 Bionic chip and Huawei Kirin 970 chip. I believe in the near future, neural network based methods will play important roles at low level image processing tasks, and neural network computing units will become an integrated part of the image signal processor.

This is a personal collection of research works using neural network for low level image processing. I will try to keep it up to date. You are welcome to contribute to this list. Papers of significance are marked in bold. My comments are marked in italic.

Table of Contents

Review and comments

Color constancy

Denoising

Demosaicing

Automatic adjustment

From the publications, we can find that Adobe has done a lot of work pushing the usage of machine learning in low-level image processing especially automatic photo adjustment.

Superresolution

Super-resolution is one of the areas that NN has been applied extensively and achieved great success.

Artefacts removal

Pipeline

Image quality evaluation

Others

About

This is a collection of works on neural networks for low level image processing.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published