# SODiff: Semantic-Oriented Diffusion Model for JPEG Compression Artifacts Removal

arXiv: https://arxiv.org/abs/2508.07346 · HTML: https://mlsanity.com/paper/2508.07346/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 7 of its 47 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 7 of 7)

- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [PromptCIR: Blind Compressed Image Restoration with Prompt Learning](https://mlsanity.com/paper/2404.17433/) (2024)
- [Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator](https://mlsanity.com/paper/2410.04224/) (2024)
- [Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal](https://mlsanity.com/paper/2502.09873/) (2025)
- [Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors](https://mlsanity.com/paper/2412.07152/) (2024)

## Built on by (most cited first, 2 of 2)

- [Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration](https://mlsanity.com/paper/2601.19506/) (2026)
- [LCUDiff: Latent Capacity Upgrade Diffusion for Faithful Human Body Restoration](https://mlsanity.com/paper/2602.04406/) (2026)

## Abstract (arXiv)

JPEG, as a widely used image compression standard, often introduces severe visual artifacts when achieving high compression ratios. Although existing deep learning-based restoration methods have made considerable progress, they often struggle to recover complex texture details, resulting in over-smoothed outputs. To overcome these limitations, we propose SODiff, a novel and efficient semantic-oriented one-step diffusion model for JPEG artifacts removal. Our core idea is that effective restoration hinges on providing semantic-oriented guidance to the pre-trained diffusion model, thereby fully leveraging its powerful generative prior. To this end, SODiff incorporates a semantic-aligned image prompt extractor (SAIPE). SAIPE extracts rich features from low-quality (LQ) images and projects them into an embedding space semantically aligned with that of the text encoder. Simultaneously, it preserves crucial information for faithful reconstruction. Furthermore, we propose a quality factor-aware time predictor that implicitly learns the compression quality factor (QF) of the LQ image and adaptively selects the optimal denoising start timestep for the diffusion process. Extensive experimental results show that our SODiff outperforms recent leading methods in both visual quality and quantitative metrics. Code is available at: https://github.com/frakenation/SODiff