IEEE P3333.1.3 - IEEE Draft Standard for the Deep Learning-Based Assessment of Visual Experience Based on Human Factors

Project

Active

Project Details

Measuring quality of experience (QoE) aims to explore the factors that contribute to a user’s perceptual experience including human, system, and context factors. Since QoE stems from human interaction with various devices, the estimation should be started by investigating the mechanism of human visual perception. Therefore, measuring QoE is still a challenging task. In this standard, QoE assessment is categorized into two subcategories which are perceptual quality and virtual reality (VR) cybersickness. In addition, deep learning models considering human factors for various QoE assessments are covered, along with a reliable subjective test methodology and a database construction procedure.

Sponsor Committee	C/SAB - Standards Activities Board
Par Approval	2017-09-28
Pars	Approved PAR

Working Group Details

Working Group	HFVE_WG - Human Factors for Visual Experiences Working Group
Sponsor Committee	C/SAB - Standards Activities Board
Society	IEEE Computer Society
IEEE Program Manager	Jonathan Goldberg
Active Projects	Active P3333.1.1 - Standard for Quality of Experience (QoE) and Visual-Comfort Assessments of Three-Dimensional (3D) Contents Based on Psychophysical Studies This standard establishes various traditional and deep learning-based methods for visual saliency prediction, visual contents analysis, and subjective assessment for quantifying the visual discomfort and quality of experience (QoE) of 3D image and video.
	Active P3333.1.2 - Standard for the Perceptual Quality Assessment of Three Dimensional (3D), Ultra High Definition (UHD) and High Dynamic Range (HDR) Contents This standard establishes methods for quality assessment of 3D, UHD and HDR contents based on physiological mechanisms such as perceptual quality and visual attention. This standard identifies and quantifies the following: -- Causes and visual attention of perceptual quality degradation for 3D, UHD and HDR image and video contents: -- Compression distortion, such as multi-view image and video compression, -- Interpolation distortion by intermediate view rendering, such as 3D, UHD and HDR warping, view synthesis, -- Structural distortion, such as bit errors on wireless/wired transmission errors, -- Visual attention according to the quality degradation. -- Deep learning based model for saliency detection and QoE assessment. Key items are needed to characterize the 3D, UHD and HDR database in terms of the human visual system. These key factors are constructed in conjunction with the visual factors used to perceptual quality and visual attention.
Existing Standards	Active IEEE 3333.1.1-2015 - IEEE Standard for Quality of Experience (QoE) and Visual-Comfort Assessments of Three-Dimensional (3D) Contents Based on Psychophysical Studies As the demand and supply for 3D technologies grows, the development of accurate quality-assessment techniques shall be used to develop the 3D display device and signal-processing engine industries. The underlying principles and statistical characteristics of 3D contents based on the human visual system (HVS) are described in this standard. In addition, a reliable 3D subjective assessment methodology that covers the characteristics of human perception, display mechanism, and the viewing environment is introduced in this standard.
	Active IEEE 3333.1.2-2017 - IEEE Standard for the Perceptual Quality Assessment of Three-Dimensional (3D) and Ultra-High-Definition (UHD) Contents The world is witnessing a rapid advance in stereoscopic 3D (S3D), and ultra-highdefinition (UHD) technology. As a result, the need for accurate quality and visual-comfort assessment techniques to foster the display device industry as well as signal-processing area. In this standard, thorough assessments with respect to the human visual system (HVS) for S3D and UHD contents shall be presented. Moreover, several image and video databases are also publicly provided for any research purpose.