No-Reference Stereoscopic Video Quality Assessment Algorithm Using Joint Motion and Depth Statistics

Abstract

We present a no-reference (NR) quality assessment algorithm for assessing the perceptual quality of natural stereoscopic 3D (S3D) videos. This work is inspired by our finding that the joint statistics of the subband coefficients of motion (optical flow or motion vector magnitude) and depth (disparity map) of natural S3D videos possess a unique signature. Specifically, we empirically show that the joint statistics of the motion and depth subband coefficients of S3D video frames can be modeled accurately using a Bivariate Generalized Gaussian Distribution (BGGD). We then demonstrate that the parameters of the BGGD model possess the ability to discern quality variations in S3D videos. Therefore, the BGGD model parameters are employed as motion and depth quality features. In addition to these features, we rely on a frame-level spatial quality feature that is computed using a robust off-the-shelf NR image quality assessment (IQA) algorithm. These frame-level motion, depth and spatial features are consolidated and used with the corresponding S3D video's difference mean opinion score (DMOS) labels for supervised learning using support vector regression (SVR). The overall quality of an S3D video is computed by averaging the frame-level quality predictions of the constituent video frames. The proposed algorithm, dubbed Video QUality Evaluation using MOtion and DEpth Statistics (VQUEMODES) is shown to outperform the state-of-the-art methods when evaluated over the IRCCYN and LFOVIA S3D subjective quality assessment databases.

Jomodevi: A joint motion and depth visibility prediction algorithm for perceived stereoscopic 3D quality

“…The model finds the visualization regions by computing the edge strength, and the quality score is achieved by calculating the energy error of similarity scores of the visualized regions of the left and right views. Appina et al [40,41,42,43] proposed a series of FR and NR S3D VQA models by performing statistical analysis on the motion and depth components of S3D scenes. These algorithms use the Bivariate Generalized Gaussian Distribution (BGGD) model to fit motion and depth subband coefficients, and well-known 2D IQA models are applied on each frame to estimate the quality of S3D videos.…”

“…The findings indicate that the subband coefficients of luminance and disparity have sharp peaks and heavy tails, and these coefficients can be accurately modeled with Univariate GGD (UGGD). Furthermore, Su et al [56] and Appina et al [41,42,43,57,58] performed several scene statistical experiments on spatial, temporal and depth components of S3D contents, and modeled the joint dependencies among these components with a BGGD. Our work is motivated by the aforementioned psychovisual studies and statistical experiments to explore the interrelations (i.e., correlations) between the motion and depth components of S3D scenes.…”

A full-reference laparoscopic video quality assessment algorithm

“…An earlier work of Appina et al 2 highlighted that the Mean Opinion Score (MOS) of a video highly correlates with the frame-level perceptual opinion score during short temporal durations. We are motivated by this finding to use video-level MOS score as the ground truth quality representative of a frame.…”

Stereoscopic Video Quality Assessment Using Oriented Local Gravitational Force Statistics

“…Galkandage et al [12] considered binocular suppression and used an IQA method to evaluate the quality of each frame, and proposed an optimized pooling method to evaluate stereoscopic video quality. Appina et al [13] proposed an NR SVQA algorithm using binocular disparity and motion component joint statistical modeling. Wang et al [14] considered the binocular spatio-temporal internal mechanism and the free-energy theory to compute binocular difference maps, and use the multi-channel natural statistics to evalute 3D video quality.…”