# JPEG AI Image Compression Visual Artifacts: Detection Methods and Dataset

arXiv: https://arxiv.org/abs/2411.06810 · HTML: https://mlsanity.com/paper/2411.06810/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 61 references that are in the map.
- First posted on arXiv 11 Nov 2024.

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

- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations](https://mlsanity.com/paper/1704.00648/) (2017)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution](https://mlsanity.com/paper/2203.09195/) (2022)
- [Improving Inference for Neural Image Compression](https://mlsanity.com/paper/2006.04240/) (2020)
- [COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec](https://mlsanity.com/paper/2212.05458/) (2022)
- [EVC: Towards Real-Time Neural Image Compression with Mask Decay](https://mlsanity.com/paper/2302.05071/) (2023)
- [DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models](https://mlsanity.com/paper/2307.02457/) (2023)
- [Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules](https://mlsanity.com/paper/2107.06463/) (2021)
- [Lossy Image Compression with Quantized Hierarchical VAEs](https://mlsanity.com/paper/2208.13056/) (2022)
- [A Comprehensive Benchmark for Single Image Compression Artifacts Reduction](https://mlsanity.com/paper/1909.03647/) (2019)
- [Mitigating Artifacts in Real-World Video Super-Resolution Models](https://mlsanity.com/paper/2212.07339/) (2022)
- [No-Reference Color Image Quality Assessment: From Entropy to Perceptual Quality](https://mlsanity.com/paper/1812.10695/) (2018)
- [Bit Distribution Study and Implementation of Spatial Quality Map in the JPEG-AI Standardization](https://mlsanity.com/paper/2402.17470/) (2024)
- [Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model](https://mlsanity.com/paper/2402.17487/) (2024)

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

- [SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation](https://mlsanity.com/paper/2605.14847/) (2026)
- [NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis](https://mlsanity.com/paper/2506.19051/) (2025)
- [Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution](https://mlsanity.com/paper/2510.16752/) (2025)
- [Three Forensic Cues for JPEG AI Images](https://mlsanity.com/paper/2504.03191/) (2025)

## Abstract (arXiv)

Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce visual artifacts in some images. We therefore propose methods to separately detect three types of artifacts (texture and boundary degradation, color change, and text corruption), to localize the affected regions, and to quantify the artifact strength. We consider only those regions that exhibit distortion due solely to the neural compression but that a traditional codec recovers successfully at a comparable bitrate. We employed our methods to collect artifacts for the JPEG AI verification model with respect to HM-18.0, the H.265 reference software. We processed about 350,000 unique images from the Open Images dataset using different compression-quality parameters; the result is a dataset of 46,440 artifacts validated through crowd-sourced subjective assessment. Our proposed dataset and methods are valuable for testing neural-network-based image codecs, identifying bugs in these codecs, and enhancing their performance. We make source code of the methods and the dataset publicly available.