# Human Perceptual Evaluations for Image Compression

arXiv: https://arxiv.org/abs/1908.04187 · HTML: https://mlsanity.com/paper/1908.04187/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2019.

## Built on by (most cited first, 5 of 5)

- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework](https://mlsanity.com/paper/2206.05279/) (2022)
- [Microdosing: Knowledge Distillation for GAN based Compression](https://mlsanity.com/paper/2201.02624/) (2022)
- [Leveraging progressive model and overfitting for efficient learned image compression](https://mlsanity.com/paper/2210.04112/) (2022)

## Abstract (arXiv)

Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG2000 or BPG). A standard way of comparing image compression schemes today is to use perceptual similarity metrics such as PSNR or MS-SSIM (multi-scale structural similarity). This has led to some deep learning techniques which directly optimize for MS-SSIM by choosing it as a loss function. While this leads to a higher MS-SSIM for such techniques, we demonstrate using user studies that the resulting improvement may be misleading. Deep learning techniques for image compression with a higher MS-SSIM may actually be perceptually worse than engineered compression schemes with a lower MS-SSIM.