# Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compression

arXiv: https://arxiv.org/abs/1807.00270 · HTML: https://mlsanity.com/paper/1807.00270/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2018.

## Built on by (most cited first, 6 of 6)

- [Just Noticeable Difference for Deep Machine Vision](https://mlsanity.com/paper/2102.08168/) (2021)
- [Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusion](https://mlsanity.com/paper/2311.16168/) (2023)
- [Image Compression with Encoder-Decoder Matched Semantic Segmentation](https://mlsanity.com/paper/2101.09642/) (2021)
- [Full RGB Just Noticeable Difference (JND) Modelling](https://mlsanity.com/paper/2203.00629/) (2022)
- [The First Comprehensive Dataset with Multiple Distortion Types for Visual Just-Noticeable Differences](https://mlsanity.com/paper/2303.02562/) (2023)
- [Image Compression and Actionable Intelligence With Deep Neural Networks](https://mlsanity.com/paper/2203.13686/) (2022)

## Abstract (arXiv)

Image compression has been investigated for many decades. Recently, deep learning approaches have achieved a great success in many computer vision tasks, and are gradually used in image compression. In this paper, we develop three overall compression architectures based on convolutional autoencoders (CAEs), generative adversarial networks (GANs) as well as super-resolution (SR), and present a comprehensive performance comparison. According to experimental results, CAEs achieve better coding efficiency than JPEG by extracting compact features. GANs show potential advantages on large compression ratio and high subjective quality reconstruction. Super-resolution achieves the best rate-distortion (RD) performance among them, which is comparable to BPG.