Joao Ascenso

Nowadays, image compression solutions are increasingly designed to operate within high-fidelity quality ranges, where preserving even the most subtle details of the original image is essential. In this context, the ability to detect and quantify subtle compression artifacts becomes critically important, as even slight degradations can impact perceptual quality in professional or quality-sensitive applications, such as digital archiving, professional editing and web delivery. However, the performance of current objective image quality assessment metrics in this range has not been thoroughly investigated. In particular, it is not well understood how reliably these metrics estimate distortions at or below the threshold of Just Noticeable Difference (JND). This study directly addresses this issue by proposing evaluation methodologies for assessing the performance of quality metrics and performing a comprehensive evaluation using the JPEG AIC-3 dataset which is designed for high-fidelity image compression. Beyond conventional criteria, the study introduces Z-RMSE to explicitly incorporate subjective score uncertainty and applies novel statistical tests to assess significant differences between metrics. The analysis spans the full JPEG AIC-3 range and its high- and medium-fidelity subsets, and examines the impact of cropping in subjective tests. A public dataset with benchmarks and evaluation tools is released to support further research.

JPEG AI is an emerging learning-based image coding standard developed by Joint Photographic Experts Group (JPEG). The scope of the JPEG AI is the creation of a practical learning-based image coding standard offering a single-stream, compact compressed domain representation, targeting both human visualization and machine consumption. Scheduled for completion in early 2025, the first version of JPEG AI focuses on human vision tasks, demonstrating significant BD-rate reductions compared to existing standards, in terms of MS-SSIM, FSIM, VIF, VMAF, PSNR-HVS, IW-SSIM and NLPD quality metrics. Designed to ensure broad interoperability, JPEG AI incorporates various design features to support deployment across diverse devices and applications. This paper provides an overview of the technical features and characteristics of the JPEG AI standard.

Assessing image quality is crucial in image processing tasks such as compression, super-resolution, and denoising. While subjective assessments involving human evaluators provide the most accurate quality scores, they are impractical for large-scale or continuous evaluations due to their high cost and time requirements. Pairwise comparison subjective assessment tests, which rank image pairs instead of assigning scores, offer more reliability and accuracy but require numerous comparisons, leading to high costs. Although objective quality metrics are more efficient, they lack the precision of subjective tests, which are essential for benchmarking and training learning-based quality metrics. This paper proposes an uncertainty-based sampling method to optimize the pairwise comparison subjective assessment process. By utilizing deep learning models to estimate human preferences and identify pairs that need human labeling, the approach reduces the number of required comparisons while maintaining high accuracy. The key contributions include modeling uncertainty for accurate preference predictions and for pairwise sampling. The experimental results demonstrate superior performance of the proposed approach compared to traditional active sampling methods. An implementation of the pairwise sampling method is publicly available at https://github.com/shimamohammadi/LBPS-EIC

Learning-based image coding is showing improved compression efficiency, while also offering a novel advantage in enabling computer vision tasks directly within the compressed domain. The latent representation created by deep learning methods inherently contains all visual features, without a computationally expensive synthesis process at the decoder. This paper is an invited extension of a previous solution for JPEG AI compressed domain face detection that adapts a RetinaFace-based detector to operate directly on the latent tensor. In addition to a former single-scale bridging solution, this work provides a novel multi-scale bridging architecture to enable a more effective multi-scale compressed domain face detection. The results show a significant performance gain, improving accuracy up to 20% for detection of tiny faces on the WIDER FACE dataset compared to single-scale bridging, and further narrowing the gap when compared to detection on uncompressed or JPEG AI decoded images. Furthermore, since the computationally expensive decoding step is bypassed and since the bridges consist of lower-complexity networks, the overall processing cost is significantly reduced. Single and multi-scale bridging, respectively, have about 10% and 32% the complexity of applying pixel domain face detection on decoded images. The proposed architecture is expected to be extended to other multiscale sensitive vision tasks, as JPEG AI is not specifically designed for any single downstream application.

High dynamic range (HDR) and wide color gamut (WCG) technologies significantly improve color reproduction compared to standard dynamic range (SDR) and standard color gamuts, resulting in more accurate, richer, and more immersive images. However, HDR increases data demands, posing challenges for bandwidth efficiency and compression techniques. Advances in compression and display technologies require more precise image quality assessment, particularly in the high-fidelity range where perceptual differences are subtle. To address this gap, we introduce AIC-HDR2025, the first such HDR dataset, comprising 100 test images generated from five HDR sources, each compressed using four codecs at five compression levels. It covers the high-fidelity range, from visible distortions to compression levels below the visually lossless threshold. A subjective study was conducted using the JPEG AIC-3 test methodology, combining plain and boosted triplet comparisons. In total, 34,560 ratings were collected from 151 participants across four fully controlled labs. The results confirm that AIC-3 enables precise HDR quality estimation, with 95\% confidence intervals averaging a width of 0.27 at 1 JND. In addition, several recently proposed objective metrics were evaluated based on their correlation with subjective ratings. The dataset is publicly available.

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.

In recent years, visual sensors have been quickly improving towards mimicking the visual information acquisition process of human brain by responding to illumination changes as they occur in time rather than at fixed time intervals. In this context, the so-called neuromorphic vision sensors depart from the conventional frame-based image sensors by adopting a paradigm shift in the way visual information is acquired. This new way of visual information acquisition enables faster and asynchronous per-pixel responses/recordings driven by the scene dynamics with a very high dynamic range and low power consumption. However, the huge amount of data outputted by the emerging neuromorphic vision sensors critically demands highly efficient coding solutions in order applications may take full advantage of these new, attractive sensors’ capabilities. For this reason, considerable research efforts have been invested in recent years towards developing increasingly efficient neuromorphic vision data coding (NVDC) solutions. In this context, the main objective of this paper is to provide a comprehensive overview of NVDC solutions in the literature, guided by a novel classification taxonomy, which allows better organizing this emerging field. In this way, more solid conclusions can be drawn about the current NVDC status quo , thus allowing to better drive future research and standardization developments in this emerging technical area.

Neural radiance fields (NeRF) are a groundbreaking computer vision technology that enables the generation of high-quality, immersive visual content from multiple viewpoints. This capability has significant advantages for applications such as virtual/augmented reality, 3D modelling, and content creation for the film and entertainment industry. However, the evaluation of NeRF methods poses several challenges, including a lack of comprehensive datasets, reliable assessment methodologies, and objective quality metrics. This paper addresses the problem of NeRF view synthesis (NVS) quality assessment thoroughly, by conducting a rigorous subjective quality assessment test that considers several scene classes and recently proposed NVS methods. Additionally, the performance of a wide range of state-of-the-art conventional and learning-based full-reference 2D image and video quality assessment metrics is evaluated against the subjective scores of the subjective study. This study found that errors in camera pose estimation can result in spatial misalignments between synthesized and reference images, which need to be corrected before applying an objective quality metric. The experimental results are analyzed in depth, providing a comparative evaluation of several NVS methods and objective quality metrics, across different classes of visual scenes, including real and synthetic content for front-face and 360° camera trajectories.

In 2019, the JPEG Standardization Committee initiated JPEG AI to define the first image coding specifications, taking advantage of an end-to-end learning-based coding approach. The JPEG AI specifications will be soon published as an international standard in early 2025. JPEG AI exploits the current state of the art in deep learning while taking into account considerations for a deployment in the near future. Therefore, JPEG AI design was refined in several iterations to reach the level of maturity and feasibility to both encode and decode images on mobile devices. JPEG AI offers several benefits when compared to previous conventional coding systems, namely the following: 1) superior rate-distortion performance for perceptual visual quality; 2) much faster coding capability; and 3) the possibility of multipurpose optimization, such as coding for both humans and machines. JPEG AI is based on a learning-based image coding algorithm that can generate a single-stream, compact compressed domain representation, targeting both human visualization, with significant compression efficiency improvement over image coding standards, and effective performance for image processing and computer vision tasks, with the goal of supporting a royalty-free baseline. This article describes how such an objective was achieved in version 1 of the JPEG AI standard by providing technical principles behind its design while giving insights on future steps planned for future extensions of JPEG AI.