This standard defines a set of tools for efficient coding of immersive visual content, as well as the corresponding decoding and reconstructing procedure. The immersive visual content includes, but is not limited to, panorama video, free-view video, light field, and three-dimensional (3D) model and other kinds of synthetic visual contents. The coding efficiency is measured by counting the data rates under target visual quality of immersive visual content.
This standard defines deep learning-based metrics of content analysis and quality of experience (QoE) assessment for visual contents, which is an extension of the standard for the QoE and visual-comfort assessments of three-dimensional (3D) contents based on psychophysical studies (IEEE Std 3333.1.1) and the standard for the perceptual quality assessment of 3D and ultra-high definition (UHD) contents (IEEE Std 3333.1.2). The scope covers the following. * Deep learning models for QoE assessment (… read more multilayer perceptrons, convolutional neural networks, deep generative models) * Deep metrics of visual experience from High Definition (HD), UHD, 3D, High Dynamic Range (HDR), Virtual Reality (VR) and Mixed Reality (MR) contents * Deep analysis of clinical (electroencephalogram (EEG), electrocardiogram (ECG), electrooculography (EOG), and so on) and psychophysical (subjective test and simulator sickness questionnaire (SSQ)) data for QoE assessment * Deep personalized preference assessment of visual contents * Building image and video databases for performance benchmarking purpose if necessary read less