Blind image quality assessment via vision-language correspondence: A multitask learning perspective

W Zhang, G Zhai, Y Wei, X Yang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We aim at advancing blind image quality assessment (BIQA), which predicts the human
perception of image quality without any reference information. We develop a general and …

Fovvideovdp: A visible difference predictor for wide field-of-view video

RK Mantiuk, G Denes, A Chapiro, A Kaplanyan… - ACM Transactions on …, 2021 - dl.acm.org
FovVideoVDP is a video difference metric that models the spatial, temporal, and peripheral
aspects of perception. While many other metrics are available, our work provides the first …

HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content

RK Mantiuk, D Hammou, P Hanji - arxiv preprint arxiv:2304.13625, 2023 - arxiv.org
High-Dynamic-Range Visual-Difference-Predictor version 3, or HDR-VDP-3, is a visual
metric that can fulfill several tasks, such as full-reference image/video quality assessment …

Pea-pods: Perceptual evaluation of algorithms for power optimization in xr displays

K Chen, T Wan, N Matsuda, A Ninan… - ACM Transactions on …, 2024 - dl.acm.org
Display power consumption is an emerging concern for untethered devices. This goes
double for augmented and virtual extended reality (XR) displays, which target high refresh …

Advances and challenges in computational image aesthetics

G Valenzise, C Kang, F Dufaux - Human perception of visual information …, 2022 - Springer
Computational image aesthetics aims at designing algorithmic approaches to perform
aesthetic decisions, in a similar fashion as humans. In the past fifteen years, computational …

Learning to blindly assess image quality in the laboratory and wild

W Zhang, K Ma, G Zhai, X Yang - 2020 IEEE International …, 2020 - ieeexplore.ieee.org
Computational models for blind image quality assessment (BIQA) are typically trained in well-
controlled laboratory environments with limited generalizability to realistically distorted …

An image quality assessment dataset for portraits

N Chahine, S Calarasanu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Year after year, the demand for ever-better smartphone photos continues to grow, in
particular in the domain of portrait photography. Manufacturers thus use perceptual quality …

Sensing perceived urban stress using space syntactical and urban building density data: A machine learning-based approach

QH Le, N Kwon, TH Nguyen, B Kim, Y Ahn - Building and Environment, 2024 - Elsevier
Human well-being is an essential criterion in achieving smart and sustainable cities. Given
the significant influence of stress on individuals physical and mental health, various …

Provable benefits of policy learning from human preferences in contextual bandit problems

X Ji, H Wang, M Chen, T Zhao, M Wang - arxiv preprint arxiv:2307.12975, 2023 - arxiv.org
A crucial task in decision-making problems is reward engineering. It is common in practice
that no obvious choice of reward function exists. Thus, a popular approach is to introduce …

A comprehensive framework for evaluating deepfake generators: Dataset, metrics performance, and comparative analysis

S Husseini, JL Dugelay - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Assessing the realism and accuracy of deepfake generators, especially in cross-
reenactment situations, is a major challenge. This challenge is primarily attributed to the …