# Subjective Visual Quality Assessment for High-Fidelity Learning-Based Image Compression

arXiv: https://arxiv.org/abs/2504.06301 · HTML: https://mlsanity.com/paper/2504.06301/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 15 of 15)

- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Learning End-to-End Lossy Image Compression: A Benchmark](https://mlsanity.com/paper/2002.03711/) (2020)
- [Deep Convolutional AutoEncoder-based Lossy Image Compression](https://mlsanity.com/paper/1804.09535/) (2018)
- [HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content](https://mlsanity.com/paper/2304.13625/) (2023)
- [ColorVideoVDP: A visual difference predictor for image, video and display distortions](https://mlsanity.com/paper/2401.11485/) (2024)
- [Perceptually Optimized Image Rendering](https://mlsanity.com/paper/1701.06641/) (2017)
- [Perceptual Quality Study on Deep Learning based Image Compression](https://mlsanity.com/paper/1905.03951/) (2019)
- [Versatile Video Coding Standard: A Review from Coding Tools to Consumers Deployment](https://mlsanity.com/paper/2106.14245/) (2021)
- [Relaxed forced choice improves performance of visual quality assessment methods](https://mlsanity.com/paper/2305.00220/) (2023)
- [Evaluating the Practicality of Learned Image Compression](https://mlsanity.com/paper/2207.14524/) (2022)
- [Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model](https://mlsanity.com/paper/2402.17487/) (2024)
- [Fidelity-preserving Learning-Based Image Compression: Loss Function and Subjective Evaluation Methodology](https://mlsanity.com/paper/2403.11241/) (2024)
- [Fine-grained subjective visual quality assessment for high-fidelity compressed images](https://mlsanity.com/paper/2410.09501/) (2024)

## Built on by (most cited first, 3 of 3)

- [How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?](https://mlsanity.com/paper/2605.25940/) (2026)
- [FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs](https://mlsanity.com/paper/2604.24123/) (2026)
- [JPEG AIC2026: A large-scale dataset for fine-grained assessment of image coding](https://mlsanity.com/paper/2607.22783/) (2026)

## Abstract (arXiv)

Learning-based image compression methods have recently emerged as promising alternatives to traditional codecs, offering improved rate-distortion performance and perceptual quality. JPEG AI represents the latest standardized framework in this domain, leveraging deep neural networks for high-fidelity image reconstruction. In this study, we present a comprehensive subjective visual quality assessment of JPEG AI-compressed images using the JPEG AIC-3 methodology, which quantifies perceptual differences in terms of Just Noticeable Difference (JND) units. We generated a dataset of 50 compressed images with fine-grained distortion levels from five diverse sources. A large-scale crowdsourced experiment collected 96,200 triplet responses from 459 participants. We reconstructed JND-based quality scales using a unified model based on boosted and plain triplet comparisons. Additionally, we evaluated the alignment of multiple objective image quality metrics with human perception in the high-fidelity range. The CVVDP metric achieved the overall highest performance; however, most metrics including CVVDP were overly optimistic in predicting the quality of JPEG AI-compressed images. These findings emphasize the necessity for rigorous subjective evaluations in the development and benchmarking of modern image codecs, particularly in the high-fidelity range. Another technical contribution is the introduction of the well-known Meng-Rosenthal-Rubin statistical test to the field of Quality of Experience research. This test can reliably assess the significance of difference in performance of quality metrics in terms of correlation between metrics and ground truth. The complete dataset, including all subjective scores, is publicly available at https://github.com/jpeg-aic/dataset-JPEG-AI-SDR25.