Stereo Picture Quality Estimation Based on a Multiple Channel HVS Model

Shen, Lili; Yang, Jiachen; Zhang, Zhuoyun

doi:10.1109/cisp.2009.5301128

Cited by 13 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results showed that the stereo band limited contrast model performs better than PSNR. In [31], an estimation of stereo image quality was proposed based on a multiple channel HVS model. In [32], Zhu et al proposed a 3D-VQA model by considering depth perception and their experimental results showed that it performs better than MSE and PSNR.…”

Section: B Previous Objective 3d-iqa Studiesmentioning

confidence: 99%

“…In particular, in [5], it was shown that averaging PSNR, SSIM, MS-SSIM, UQI and VIF measurements of left-and rightviews performs equally well or better than the advanced 3D-IQA models [7], [11], [24], [27], [28], [31], [32], [38], and [41] on LIVE 3D Image Quality Database Phase I. Similar results were also observed in [6], where averaging SSIM and MS-SSIM measurements of both views outperformed advanced 3D-IQA models [7], [24], [28], [37], [38], and [41] on LIVE 3D Image Quality Database Phase II.…”

Section: Observationsmentioning

confidence: 99%

See 1 more Smart Citation

Quality Prediction of Asymmetrically Distorted Stereoscopic 3D Images

Wang

Rehman²,

Zeng

et al. 2015

IEEE Trans. on Image Process.

149

View full text Add to dashboard Cite

Objective quality assessment of distorted stereoscopic images is a challenging problem, especially when the distortions in the left and right views are asymmetric. Existing studies suggest that simply averaging the quality of the left and right views well predicts the quality of symmetrically distorted stereoscopic images, but generates substantial prediction bias when applied to asymmetrically distorted stereoscopic images. In this paper, we first build a database that contains both single-view and symmetrically and asymmetrically distorted stereoscopic images. We then carry out a subjective test, where we find that the quality prediction bias of the asymmetrically distorted images could lean toward opposite directions (overestimate or underestimate), depending on the distortion types and levels. Our subjective test also suggests that eye dominance effect does not have strong impact on the visual quality decisions of stereoscopic images. Furthermore, we develop an information content and divisive normalization-based pooling scheme that improves upon structural similarity in estimating the quality of single-view images. Finally, we propose a binocular rivalry-inspired multi-scale model to predict the quality of stereoscopic images from that of the single-view images. Our results show that the proposed model, without explicitly identifying image distortion types, successfully eliminates the prediction bias, leading to significantly improved quality prediction of the stereoscopic images.

show abstract

Section: B Previous Objective 3d-iqa Studiesmentioning

confidence: 99%