Image Compression

146 papers with code • 11 benchmarks • 10 datasets

Image Compression is an application of data compression for digital images to lower their storage and/or transmission requirements.

Source: Variable Rate Deep Image Compression With a Conditional Autoencoder


Use these libraries to find Image Compression models and implementations

Most implemented papers

End-to-end Optimized Image Compression

tensorflow/models 5 Nov 2016

We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation.

Variational image compression with a scale hyperprior

tensorflow/compression ICLR 2018

We describe an end-to-end trainable model for image compression based on variational autoencoders.

"Zero-Shot" Super-Resolution using Deep Internal Learning

assafshocher/ZSSR 17 Dec 2017

On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods.

Full Resolution Image Compression with Recurrent Neural Networks

tensorflow/models CVPR 2017

As far as we know, this is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.

An End-to-End Compression Framework Based on Convolutional Neural Networks

compression-framework/compression_framwork_for_tesing 2 Aug 2017

The second CNN, named reconstruction convolutional neural network (RecCNN), is used to reconstruct the decoded image with high-quality in the decoding end.

Lossy Image Compression with Compressive Autoencoders

alexandru-dinu/cae 1 Mar 2017

We propose a new approach to the problem of optimizing autoencoders for lossy image compression.

Semantic Perceptual Image Compression using Deep Convolution Networks

iamaaditya/image-compression-cnn 27 Dec 2016

Here, we present a powerful cnn tailored to the specific task of semantic image understanding to achieve higher visual quality in lossy compression.

Efficient Nonlinear Transforms for Lossy Image Compression

tensorflow/compression 31 Jan 2018

We assess the performance of two techniques in the context of nonlinear transform coding with artificial neural networks, Sadam and GDN.

Joint Autoregressive and Hierarchical Priors for Learned Image Compression

InterDigitalInc/CompressAI NeurIPS 2018

While it is well known that autoregressive models come with a significant computational penalty, we find that in terms of compression performance, autoregressive and hierarchical priors are complementary and, together, exploit the probabilistic structure in the latents better than all previous learned models.

Practical Full Resolution Learned Lossless Image Compression

fab-jul/L3C-PyTorch CVPR 2019

We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000.