# One-Step Diffusion for Perceptual Image Compression

arXiv: https://arxiv.org/abs/2602.01570 · HTML: https://mlsanity.com/paper/2602.01570/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models.
- First posted on arXiv 2 Feb 2026.

## Placed in

- Diffusion models / [Diffusion for compression and wireless](https://mlsanity.com/diffusion/diffusion-for-compression-and-wireless/)

## Built on by (most cited first, 1 of 1)

- [SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression](https://mlsanity.com/paper/2605.04560/) (2026)

## Abstract (arXiv)

Diffusion-based image compression methods have achieved notable progress, delivering high perceptual quality at low bitrates. However, their practical deployment is hindered by significant inference latency and heavy computational overhead, primarily due to the large number of denoising steps required during decoding. To address this problem, we propose a diffusion-based image compression method that requires only a single-step diffusion process, significantly improving inference speed. To enhance the perceptual quality of reconstructed images, we introduce a discriminator that operates on compact feature representations instead of raw pixels, leveraging the fact that features better capture high-level texture and structural details. Experimental results show that our method delivers comparable compression performance while offering a 46× faster inference speed compared to recent diffusion-based approaches. The source code and models are available at https://github.com/cheesejiang/OSDiff.