Blind image quality assessment via vision-language correspondence: A multitask learning perspective
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 …
perception of image quality without any reference information. We develop a general and …
Fovvideovdp: A visible difference predictor for wide field-of-view video
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 …
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
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 …
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
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 …
double for augmented and virtual extended reality (XR) displays, which target high refresh …
Advances and challenges in computational image aesthetics
Computational image aesthetics aims at designing algorithmic approaches to perform
aesthetic decisions, in a similar fashion as humans. In the past fifteen years, computational …
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
Computational models for blind image quality assessment (BIQA) are typically trained in well-
controlled laboratory environments with limited generalizability to realistically distorted …
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 …
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
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 …
the significant influence of stress on individuals physical and mental health, various …
Provable benefits of policy learning from human preferences in contextual bandit problems
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 …
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
Assessing the realism and accuracy of deepfake generators, especially in cross-
reenactment situations, is a major challenge. This challenge is primarily attributed to the …
reenactment situations, is a major challenge. This challenge is primarily attributed to the …