No abstract

Empirical studies of the joint statistics of luminance and disparity images (or wavelet coefficients) of natural stereoscopic scenes have resulted in two important findings: a) the marginal statistics are modelled well by the generalized Gaussian distribution (GGD) and b) there exists significant correlation between them. Inspired by these findings, we propose a full-reference image quality assessment algorithm dubbed STeReoscopic Image Quality Evaluator (STRIQE). We show that the parameters of the GGD fits of luminance wavelet coefficients along with correlation values form excellent features. Importantly, we demonstrate that the use of disparity information (via correlation) results in a consistent improvement in the performance of the algorithm. The performance of our algorithm is evaluated over popular datasets and shown to be competitive with the state-of-the-art full-reference algorithms. The efficacy of the algorithm is further highlighted by its near-linear relation with subjective scores, low root mean squared error (RMSE), and consistently good performance over both symmetric and asymmetric distortions. Index TermsNatural scene statistics, stereoscopic images, full-reference image quality assessment.

The human visual system pays attention to salient regions while perceiving an image. When viewing a stereoscopic 3-D (S3D) image, we hypothesize that while most of the contribution to saliency is provided by the 2-D image, a small but significant contribution is provided by the depth component. Further, we claim that only a subset of image edges contribute to depth perception while viewing an S3D image. In this paper, we propose a systematic approach for depth saliency estimation, called salient edges with respect to depth perception (SED) which localizes the depth-salient edges in an S3D image. We demonstrate the utility of SED in full reference stereoscopic image quality assessment. We consider gradient magnitude and inter-gradient maps for predicting structural similarity. A coarse quality map is estimated first by comparing the 2-D saliency and gradient maps of reference and test stereo pairs. We average this quality map to estimate luminance quality and refine this quality map using SED maps for evaluating depth quality. Finally, we combine this luminance and depth quality to obtain an overall stereo image quality. We perform a comprehensive evaluation of our metric on seven publicly available S3D IQA databases. The proposed metric shows competitive performance on all seven databases with state-of-the-art performance on three of them.

In this work, we present a full-reference stereo image quality assessment algorithm that is based on the sparse representations of luminance images and depth maps. The primary challenge lies in dealing with the sparsity of disparity maps in conjunction with the sparsity of luminance images. Although analysing the sparsity of images is sufficient to bring out the quality of luminance images, the effectiveness of sparsity in quantifying depth quality is yet to be fully understood. We present a full reference Sparsity-based Quality Assessment of Stereo Images (SQASI) that is aimed at this understanding.

Stereoscopic image quality typically depends on two factors: i) the quality of the luminance image perception, and ii) the quality of depth perception. The effect of distortion on luminance perception and depth perception is usually different, even though depth is estimated from luminance images.Therefore, we present a full reference stereoscopic image quality assessment (FRSIQA) algorithm that rates stereoscopic images in proportion to the quality of individual luminance image perception and the quality of depth perception. The luminance and depth quality is obtained by applying the robust Multiscale-SSIM (MS-SSIM) index on both luminance and disparity maps respectively. We propose a novel multi-scale approach for combining the luminance and depth scores from the left and right images into a single quality score per stereo image. We also explained that a small amount of distortion does not significantly affect depth perception. Further, heavy distortion in stereo pairs will result in significant loss of depth perception. Our algorithm performs competitively over standard databases and is called the 3D-MS-SSIM index. Index TermsStereoscopic images, full-reference image quality assessment, depth perception, MS-SSIM.