This artist is devoted to re-note some information about compressing Images by Artificial Neural Network
Using AI to Super Compress Images
An End-to-End Compression Framework Based onConvolutional Neural Networks
A Neural Network based Technique for Data Compression
Full Resolution Image Compression with RecurrentNeural Networks
Lossless Data Compression with Neural Networks
DeepZip: Lossless Data Compression usingRecurrent Neural Networks
Neuralnetwork and Image compression - Stanford
image-compression-benchmarking - github
https://github.com/Justin-Tan/generative-compression - github
Generative Adversarial Networks for Extreme Learned Image Compression
Image compression is the process of converting an image so that it occupies less space. Simply storing the images would take up a lot of space, so there are codecs, such as JPEG and PNG that aim to reduce the size of the original image.
There are two types of image compression :Lossless and Lossy. As their names suggest, in Lossless compression, it is possible to get back all the data of the original image, while in Lossy, some of the data is lost during the convsersion. (JPG is a lossy algorithm, while PNG is a lossless algorithm. Losless is good, but it ends up taking a lot of space on disk).
There are better ways to compress images without losing much information, but they are quite slow, and many use iterative approaches, which means they cannot be run in parallel over multiple CPU cores , or GPUs. This renders them quite impractical in everyday usage.
If anything needs to be computed and it can be approximated , throw a neural network at it. The authors used a fairly standard Convolutional Neural Network to improve image compression. Their method not only performs at par with the ‘better ways’ (if not even better), it can also leverage parallel computing, resulting in a dramatic speed increase.
The reasoning behind it is that convolution neural networks(CNN) are very good at extracting spatial information from images, which are then represented in a more compact form (e.g. only the ‘important’ bits of an image are stored). The authors wanted to leverage this capability of CNNs to be able to better represent images