Objective image quality assessment of 3D synthesized views

Battisti, Federica; Bosc, Emilie; Carli, Marco; Callet, Patrick Le; Perugia, Simone

doi:10.1016/j.image.2014.10.005

Cited by 141 publications

(89 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performances of the the selected proposed metrics, the commonly used 2D image quality assessment metrics and the metric dedicated to synthesis-related artefacts, 3DswIM [3], are presented in Table 3. The considered commonly used 2D metrics are: PSNR, universal quality index UQI [27], structural similarity index SSIM [28], multi-scale structural similarity MS-SSIM [5], information weighted IW-PSNR [6] and IW-SSIM [6].…”

Section: The Results Summarymentioning

confidence: 99%

“…In the expand filtering, up-sampling is performed before each filtering step, before filtering by rows and before filtering by columns. For morphological reduce filtering of the image with N K pixels, using operator erosion with SE of size P × 1 by columns and 1 × P by rows, 3 2 (P − 1)N K comparisons (C) are needed. The same number of comparisons are needed for interpolation expand filtering by morphological operator dilation.…”

Section: Computational Complexity Of the Reduced Mp-psnrmentioning

confidence: 99%

“…This metric achieves the gain of 17.8 % over SSIM in correlation with subjective measurements. 3DswIM [3] synthesized view image quality metric relies on a comparison of statistical features of wavelet sub-bands of the original and DIBR-synthesized images. Only horizontal detail sub-bands from the first level of Haar wavelet decomposition are used.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi–Scale Synthesized View Assessment Based on Morphological Pyramids

Sandic-Stankovic¹,

Kukolj

Callet

2016

Journal of Electrical Engineering

Self Cite

View full text Add to dashboard Cite

The Depth-Image-Based-Rendering (DIBR) algorithms used for 3D video applications introduce geometric distortions affecting the edge coherency in the synthesized images. In order to better deal with specific geometric distortions in the DIBR synthesized images, we propose full-reference metric based on multi-scale pyramid decompositions using morphological filters. The non-linear morphological filters used in multi-scale image decompositions maintain important geometric information such as edges across different resolution levels. We show that PSNR has particularly good agreement with human judgment when it is calculated between detailed images at higher scales of morphological pyramids. Consequently, we propose reduced morphological pyramid peak signal-to-noise ratio metric (MP-PSNR), taking into account only mean squared errors between pyramids' images at higher scales. Proposed computationally efficient metric achieves significantly higher correlation with human judgment compared to the state-of-the-art image quality assessment metrics and compared to the tested metric dedicated to synthesis-related artifacts.

show abstract

Section: The Results Summarymentioning

confidence: 99%

Section: Computational Complexity Of the Reduced Mp-psnrmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi–Scale Synthesized View Assessment Based on Morphological Pyramids

Sandic-Stankovic¹,

Kukolj

Callet

2016

Journal of Electrical Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…RMP-PSNR [7] and 3DSwIM [8]. Table 1 summarizes the experiment results, where the best results are marked in boldface.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…The reduced version of MP-PSNR (RMP-PSNR) [7] was also presented, which only used MSEs on higher scales. In [8], the blocks in reference and synthesized images were first registered. Then Kolmogorov-Smirnov distance between the matched blocks in wavelet domain was computed to obtain the quality score.…”

Section: Introductionmentioning

confidence: 99%

DIBR-Synthesized Image Quality Assessment via Statistics of Edge Intensity and Orientation

Zhou

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYDepth-image-based-rendering (DIBR) is a popular technique for view synthesis. The rendering process mainly introduces artifacts around edges, which leads to degraded quality. This letter proposes a DIBR-synthesized image quality metric by measuring the Statistics of both Edge Intensity and Orientation (SEIO). The Canny operator is first used to detect edges. Then the gradient maps are calculated, based on which the intensity and orientation of the edge pixels are computed for both the reference and synthesized images. The distance between the two intensity histograms and that between the two orientation histograms are computed. Finally, the two distances are pooled to obtain the overall quality score. Experimental results demonstrate the advantages of the presented method.

show abstract