 HEVC Compression Distortion	      Estimation in Depth Maps
HEVC 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