Battisti edited section_Datasets_to_follow_up__.tex  about 8 years ago

Commit id: b5db974b712720fe0275316f9571052e6ade207b

deletions | additions      

       

\item Free-Viewpoint synthesized videos with subjective quality measures (ACR-HR): The Free-Viewpoint synthesized videos quality database [15] contains 264 video sequences of 100 frames (around 7 seconds @15fps) in 1024x768 and 1920x1080 pixels resolution. Individual votes and MOS scores obtained by an ACR-HR experiment are provided.  Six different multiview sequences are considered in this database. 2 cameras were chosen to generate 50 intermediate synthesized views. The videos are composed by the visualisation from one original view to the other and come back by displaying all synthesized view on one frame.  From a given MVD sequence, two different view-points at one time instant t (also referred to as key frames in the following) were considered. The associated depth maps were encoded through seven depth map codecs under test. From the decoded depth maps, fifty intermediate viewpoints (equally separated) were generated in-between the two considered viewpoints. A sequence of 100 frames (at 10 fps) was built from the 50 intermediate virtual frames to simulate a smooth camera motion from left to right and from right to left.  \item High-Quality Streamable Free-Viewpoint Video:  \end{itemize}  \begin{center} 

DIBR_Images \cite{DIBRImage} & 96 images & yes & yes \\   DIBR_Videos & 102 video sequences & yes & yes \\   Free-Viewpoint synthesized videos & 264 video sequences & yes & yes\hline  High-Quality Streamable Free-Viewpoint Video & & no & yes  \end{tabular}  \end{center}