Battisti edited section_Datasets_to_follow_up__.tex  about 8 years ago

Commit id: 148c57a8191262bee5ab2f80e7c1d52959ac90eb

deletions | additions      

       

\item DIBR Videos \cite{DIBRVideo}: 102 video sequences of length 6s with 1024x768 pixel resolution frame rate between 15 and 30 frames per second are created. The original sequences are three multiview plus depth videos processed with 7 DIBR algorithms to generate 4 new viewpoints for each sequence. ACR-HR has been used for MOS collection;  \item MCL 3D Database \cite{Song_2014} \cite{Song_2014}: the dataset contains 693 stereoscopic image pairs. Nine image-plus-depth sources are first selected, and a DIBR technique is used to render stereoscopic image pairs. Distortions applied to either the texture  image or the depth image before stereoscopic image rendering include: Gaussian blur, additive white noise, downsampling  blur, JPEG and JPEG-2000 (JP2K) compression and transmission error;  \item SIAT Synthesized Video Quality Database \cite{Liu_2015}: Database:  10 MVD sequences and for each sequence, 14 different texture/depth quantization combinations were used to generate the texture/depth view pairs with compression distortion; \item Free-Viewpoint synthesized videos: 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 multiview sequences are considered and, from a given MVD sequence, two different view-points at one time instant t were considered. The associated depth maps were encoded through seven depth map codecs. 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 \cite{Collet_2015}: Video:  a dense set of RGB and IR video cameras is used to record videos that are compressed into a streamable 3D video format. \end{itemize}