Multiview videos plus depth (MVD) is a popular 3D video representation where pixel depth information is exploited to generate additional views to provide 3D experience. Quality assessment of MVD data is of paramount importance since the latest research results show that existing 2D quality metrics are not suitable for MVD. This paper focuses on depth quality assessment and presents a novel algorithm to estimate the distortion in depth videos induced by compression. The proposed algorithm is noreference and does not require any prior training or modeling. The proposed method is based solely on the statistical analysis of the compression sensitive pixels of depth images. The experimental results worked out on a standard MVD dataset show that the proposed algorithm exhibits a very high correlation with conventional full-reference metrics.
Blind depth quality assessment using histogram shape analysis
FARID, MUHAMMAD SHAHID;LUCENTEFORTE, Maurizio;GRANGETTO, Marco
2015-01-01
Abstract
Multiview videos plus depth (MVD) is a popular 3D video representation where pixel depth information is exploited to generate additional views to provide 3D experience. Quality assessment of MVD data is of paramount importance since the latest research results show that existing 2D quality metrics are not suitable for MVD. This paper focuses on depth quality assessment and presents a novel algorithm to estimate the distortion in depth videos induced by compression. The proposed algorithm is noreference and does not require any prior training or modeling. The proposed method is based solely on the statistical analysis of the compression sensitive pixels of depth images. The experimental results worked out on a standard MVD dataset show that the proposed algorithm exhibits a very high correlation with conventional full-reference metrics.File | Dimensione | Formato | |
---|---|---|---|
main.pdf
Accesso aperto
Tipo di file:
POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione
1.12 MB
Formato
Adobe PDF
|
1.12 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.