Image Compression
226 papers with code • 11 benchmarks • 11 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
Benchmarks
These leaderboards are used to track progress in Image Compression
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Image Compression models and implementationsDatasets
CIFAR-10
STL-10
Food-101
BSDS500
FER2013
ImageNet-32
PCam
Oxford-IIIT Pet Dataset
Oxford-IIIT Pets
Subtasks
Most implemented papers
Variational image compression with a scale hyperprior
InterDigitalInc/CompressAI
•
•
ICLR 2018
We describe an end-to-end trainable model for image compression based on variational autoencoders.
End-to-end Optimized Image Compression
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation.
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.
"Zero-Shot" Super-Resolution using Deep Internal Learning
On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods.
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
bytedance/qraf
•
•
In this paper, we present a Quantization-error-aware Variable Rate Framework (QVRF) that utilizes a univariate quantization regulator a to achieve wide-range variable rates within a single model.
An End-to-End Compression Framework Based on Convolutional Neural Networks
The second CNN, named reconstruction convolutional neural network (RecCNN), is used to reconstruct the decoded image with high-quality in the decoding end.
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
VincentChandelier/ELiC-ReImplemetation
•
•
CVPR 2022
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders.
Lossy Image Compression with Compressive Autoencoders
We propose a new approach to the problem of optimizing autoencoders for lossy image compression.
High-Fidelity Generative Image Compression
tensorflow/compression
•
•
NeurIPS 2020
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system.
Semantic Perceptual Image Compression using Deep Convolution Networks
iamaaditya/image-compression-cnn
•
•
Here, we present a powerful cnn tailored to the specific task of semantic image understanding to achieve higher visual quality in lossy compression.
