# Perceptual Quality Study on Deep Learning based Image Compression

arXiv: https://arxiv.org/abs/1905.03951 · HTML: https://mlsanity.com/paper/1905.03951/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 4 of 4)

- [Evaluating the Practicality of Learned Image Compression](https://mlsanity.com/paper/2207.14524/) (2022)
- [Subjective Visual Quality Assessment for High-Fidelity Learning-Based Image Compression](https://mlsanity.com/paper/2504.06301/) (2025)
- [Quality and Complexity Assessment of Learning-Based Image Compression Solutions](https://mlsanity.com/paper/2107.09136/) (2021)
- [Image Compression and Actionable Intelligence With Deep Neural Networks](https://mlsanity.com/paper/2203.13686/) (2022)

## Abstract (arXiv)

Recently deep learning based image compression has made rapid advances with promising results based on objective quality metrics. However, a rigorous subjective quality evaluation on such compression schemes have rarely been reported. This paper aims at perceptual quality studies on learned compression. First, we build a general learned compression approach, and optimize the model. In total six compression algorithms are considered for this study. Then, we perform subjective quality tests in a controlled environment using high-resolution images. Results demonstrate learned compression optimized by MS-SSIM yields competitive results that approach the efficiency of state-of-the-art compression. The results obtained can provide a useful benchmark for future developments in learned image compression.