# High-Perceptual Quality JPEG Decoding via Posterior Sampling

arXiv: https://arxiv.org/abs/2211.11827 · HTML: https://mlsanity.com/paper/2211.11827/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 64 references that are in the map.
- First posted on arXiv 21 Nov 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [Any-resolution Training for High-resolution Image Synthesis](https://mlsanity.com/paper/2204.07156/) (2022)
- [Quantization Guided JPEG Artifact Correction](https://mlsanity.com/paper/2004.09320/) (2020)
- [CAS-CNN: A Deep Convolutional Neural Network for Image Compression Artifact Suppression](https://mlsanity.com/paper/1611.07233/) (2016)
- [High Perceptual Quality Image Denoising with a Posterior Sampling CGAN](https://mlsanity.com/paper/2103.04192/) (2021)
- [D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images](https://mlsanity.com/paper/1601.04149/) (2016)
- [The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study](https://mlsanity.com/paper/2008.00605/) (2020)
- [DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal](https://mlsanity.com/paper/1806.03275/) (2018)
- [One-to-Many Network for Visually Pleasing Compression Artifacts Reduction](https://mlsanity.com/paper/1611.04994/) (2016)
- [Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality](https://mlsanity.com/paper/2211.08944/) (2022)
- [Better Compression with Deep Pre-Editing](https://mlsanity.com/paper/2002.00113/) (2020)

## Built on by (most cited first, 8 of 8)

- [Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration](https://mlsanity.com/paper/2410.00418/) (2024)
- [SILO: Solving Inverse Problems with Latent Operators](https://mlsanity.com/paper/2501.11746/) (2025)
- [PSC: Posterior Sampling-Based Compression](https://mlsanity.com/paper/2407.09896/) (2024)
- [The Perception-Robustness Tradeoff in Deterministic Image Restoration](https://mlsanity.com/paper/2311.09253/) (2023)
- [Estimating Uncertainty in PET Image Reconstruction via Deep Posterior Sampling](https://mlsanity.com/paper/2306.04664/) (2023)
- [Perceptual Fairness in Image Restoration](https://mlsanity.com/paper/2405.13805/) (2024)
- [pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization](https://mlsanity.com/paper/2411.00605/) (2024)
- [SP3: Spherical Priors for Plug-and-Play Restoration](https://mlsanity.com/paper/2606.16396/) (2026)

## Abstract (arXiv)

JPEG is arguably the most popular image coding format, achieving high compression ratios via lossy quantization that may create visual artifacts degradation. Numerous attempts to remove these artifacts were conceived over the years, and common to most of these is the use of deterministic post-processing algorithms that optimize some distortion measure (e.g., PSNR, SSIM). In this paper we propose a different paradigm for JPEG artifact correction: Our method is stochastic, and the objective we target is high perceptual quality -- striving to obtain sharp, detailed and visually pleasing reconstructed images, while being consistent with the compressed input. These goals are achieved by training a stochastic conditional generator (conditioned on the compressed input), accompanied by a theoretically well-founded loss term, resulting in a sampler from the posterior distribution. Our solution offers a diverse set of plausible and fast reconstructions for a given input with perfect consistency. We demonstrate our scheme's unique properties and its superiority to a variety of alternative methods on the FFHQ and ImageNet datasets.