icona researchHEVC Compression Distortion Estimation in Depth Maps

 

No-Reference Quality Metric for HEVC Compression Distortion Estimation in Depth Maps


Muhammad Shahid Farid1, Maurizio Lucenteforte2 and Marco Grangetto2

1Punjab University College of Information Technology, University of the Punjab, Lahore, Pakistan.
2Dipartimento di Informatica, UniversittĂ  degli Studi di Torino, Torino, Italy.

 

Abstract: Multiview video plus depth (MVD) is the most popular 3D video format due to its efficient compression and provision for novel view generation enabling the free-viewpoint applications. In addition to color images, MVD format provides depth maps which are exploited to generate intermediate virtual views using the depth image based rendering (DIBR) techniques. Compression affects the quality of the depth maps which in turn may introduce various structural and textural distortions in the DIBR synthesized images. Estimation of the compression related distortion in depth maps is very important for a high quality 3D experience. The task becomes challenging when the corresponding reference depth maps are unavailable e.g., when evaluating the quality on the decoder side. In this paper, we present a no-reference quality assessment algorithm to estimate the distortion in the depth maps induced by compression. The proposed algorithm exploits the depth saliency and local statistical characteristics of the depth maps to predict the compression distortion. The proposed 'depth distortion evaluator' (DDE) is evaluated on depth videos from standard MVD database compressed with the state-of-the-art high efficiency video coding (HEVC) at various quality levels. The results demonstrate that DDE can be used to effectively estimate the compression distortion in depth videos.

Download

 

Table 1. Performance comparison in terms of Pearson linear correlation coefficient (PLCC). The values in bold represents the best performing metric.

Sequence
BDQM
mBDQM
DDE
mDDE
Kendo
0.9027
0.8901
0.9147
0.9040
Ballons
0.8453
0.8375
0.9355
0.9076
Book Arrival
0.9227
0.8869
0.9832
0.8902
Overall
0.8902
0.8715
0.9445
0.9006

 

Table 2. Performance comparison in terms of Root Mean Square Error (RMSE). The values in bold represents the best performing metric.

Sequence
BDQM
mBDQM
DDE
mDDE
Kendo
3.6697
3.8876
3.4463
3.6467
Ballons
4.2190
4.3145
2.7901
3.3144
Book Arrival
2.2630
2.7124
1.0714
2.6741
Overall
3.3839
3.6382
2.4359
3.2117

 

 

 

Last updated: April 30, 2019