nAlthough the interest of
3D content service has increased, the lack of high quality 3D contents
(e.g., without visual discomfort) has been still a relevant obstacle
preventing the proliferation of stereoscopic 3D services into the mass
market.
nTechniques that analyze
and ameliorate the visual discomfort of 3D contents could enable to produce
high quality 3D contents and to reuse ordinary contents. Hence, the
technique can be one of solution to the lack of high quality 3D contents.
nThe developed 3D quality
analyzer presents the results of video quality analysis according to
various visual discomfort causes. Also, the advanced depth controller
enhances the visual comfort by automatic disparity control taking account
to discomfort causes.
2. Method
Fig.
1. Overview of quality analyzer and quality enhancer for stereoscopic 3D
video
2.1. 3D quality analyzer
nMost of 3D quality
analysis techniques are based on 2D quality analysis technique. Hence,
these techniques are not proper to 3D quality since 3D quality of
experience consists multiple factors such as
visual discomfort, depth quality, picture quality and so on. In addition,
previous techniques cannot provide the detailed analysis results that
indicate the problematic discomfort cause, which leads to the increase of
3D contents production cost.
n“3D Quality Analyzer” can provide the comfort analysis results with respect to
various discomfort causes, and quantify the overall 3D quality.
Fig.
2. Overall process of “3D Quality Analyzer”
nDemo video
2.2. Advanced depth controller
nMost of conventional
techniques for improving visual comfort use the global linear disparity
adjustment, which could lead to the side effects such as the reduced depth impression
and depth distortion due to excessive disparity adjustment.
n“Advanced Depth Control”
adaptively (linear/non-linear) adjusts the disparity of stereoscopic image
according to discomfort causes based on the comfort analysis results in
order to improve visual comfort.
Fig. 3. Example of
“Advanced depth control”
nDemo video
3. Applications
nSmart stereo image analyzer to assist the production of high quality (i.e.,
comfortable) 3D movie and broadcasting contents
nBest Comfort Shot 3D camera to automatically control the capturing of comfortable
stereo image
nBest Comfort Picture 3D
display to automatically assess and reduce
the visual discomfort
nComfortable 3D contents
search/recommendation services
based on the automatic classification of comfort
Y. J. Jung, H. Sohn, S. Lee,
and Y. M. Ro, “Visual comfort improvement in stereoscopic 3D displays
using perceptually plausible assessment metric of visual comfort,” IEEE
Transactions on Consumer Electronics, vol. 60, no. 1, pp. 1-9, 2014
S. Lee, Y. J. Jung, H. Sohn,
and Y. M. Ro, “Experimental investigation of discomfort combination:
Towards visual discomfort prediction for stereoscopic videos,” Journal
of Electronic Imaging, vol. 23, no. 1, p. 011003, 2014
H. Sohn, Y. J. Jung, S. Lee,
F. Speranza, and Y. M. Ro, “Visual comfort amelioration technique for stereoscopic
image: Disparity remapping to mitigate global and local discomfort causes,” IEEE Transactions on Circuits and Systems for Video
Technology, vol. 24, no. 5, pp. 745-758, 2014.
Y. J. Jung, H. Sohn, S. Lee,
H. W. Park, and Y. M. Ro, “Predicting visual
discomfort of stereoscopic images using human attention model,” IEEE Transactions on Circuits and Systems for Video
Technology, vol. 23, no. 12, pp. 2077-2082, 2013.
H. Sohn, Y. J. Jung, S. Lee,
and Y. M. Ro, “Predicting visual
discomfort using object size and disparity information in stereoscopic
images,” IEEE Transactions on Broadcasting, vol. 59, no. 1, pp.
28-37, 2013.
Y. J. Jung, S. Lee, H. Sohn,
H. W. Park, and Y. M. Ro, “Visual comfort
assessment metric based on salient object motion information in
stereoscopic video,” Journal of Electronic
Imaging, Vol. 21, No. 1, p. 011008, 2012.
