Object boundaries inconsistencies detection method for 2D-3D conversion results and depth maps

Stanislav Dolganov, Dmitriy Vatolin

Abstract


The creation of S3D movies by converting 2D captured footage often introduces depth-map inaccuracies. Such artifacts can significantly degrade the viewing experience even if they occur only in unsalient background objects. In this paper we propose a method for detecting foreground objects that are stuck to the background. Our method extracts information about motion in the scene and detects conversion-related discrepancies between motion strength and depth. We demonstrate the performance of the method by applying it to 39 full-length converted 3D movies and by providing the results of our analysis as well as examples of detected problem shots.

Full Text:

PDF (Russian)

References


Depth image-based rendering with advanced texture synthesis for 3-d video / P. Ndjiki-Nya, M. K ̈oppel, D. Doshkov et al. // Multimedia, IEEE Transactions on. — 2011. — Vol. 13, no. 3. —P. 453–465.

Tolstaya E., Pohl P., Rychagov M. Depth propagation for semi-automatic 2d to 3d conversion // IS&T/SPIE Electronic Imaging / International Society for Optics and Photonics. — 2015. —P. 939303–939303.

Is it Real or Fake 3D? —http://www.realorfake3d.com.

Seymour M. Art of stereo conversion: 2D to 3D — 2012. —http://www.fxguide.com/featured/art-of-stereo-conversion-2d-to-3d-2012/. — 2012.

Visual comfort assessment metric based on salient object motion information in stereoscopic video / Y. J. Jung, S. Lee, H. Sohnet al. // Journal of Electronic Imaging. — 2012. — Vol. 21, no. 1. —P. 011008–1.

Li J., Barkowsky M., Callet P. Le. Visual discomfort of stereoscopic 3d videos: Influence of 3d motion // Displays. — 2014. — Vol. 35,no. 1. — P. 49–57.

Fast video super-resolution via classification / K. Simonyan, S. Grishin, D. Vatolin, D. Popov // Image Processing, 2008. ICIP 2008.15th IEEE International Conference on / IEEE. — 2008. — P. 349–352.

Zhang Q., Xu L., Jia J. 100+ times faster weighted median filter (wmf) // Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on / IEEE. — 2014. — P. 2830–2837.

Fecker U., Barkowsky M., Kaup A. Time-constant histogram matching for colour compensation of multi-view video sequences //Proc. 26th Picture Coding Symp.(PCS 2007). — 2007.

Temporal filtering for depth maps generated by kinect depth camera / S. Matyunin, D. Vatolin, Y. Berdnikov, M. Smirnov // 3DTV Conference: The True Vision-Capture, Transmission and Displayof 3D Video (3DTV-CON), 2011 / IEEE. — 2011. — P. 1–4.

He K., Sun J., Tang X. Guided image filtering // Pattern Analysis and Machine Intelligence, IEEE Transactions on. — 2013. —Vol. 35, no. 6. — P. 1397–1409.

Towards automatic stereo-video quality assessment and detection of color and sharpness mismatch / A. Voronov, D. Vatolin, D. Suminet al. // 3D Imaging (IC3D), 2012 International Conference on /IEEE. — 2012. — P. 1–6.

Automatic left-right channel swap detection / D. Akimov,A. Shestov, A. Voronov, D. Vatolin // 3D Imaging (IC3D), 2012 International Conference on / IEEE. — 2012. — P. 1–6.

Automatic detection of artifacts in converted s3d video / A. Bokov, D. Vatolin, A. Zachesov et al. // IS&T/SPIE Electronic Imaging / International Society for Optics and Photonics. — 2014. —P. 901112–901112.

Consistent depth maps recovery from a video sequence / G. Zhang, J. Jia, T. Wong, H. Bao // Pattern Analysis and Machine Intelligence, IEEE Transactions on. — 2009. — Vol. 31, no. 6. — P. 974–988.

Xu C., Liu J., Tang X. 2d shape matching by contour flexibility //Pattern Analysis and Machine Intelligence, IEEE Transactionson. — 2009. — Vol. 31, no. 1. — P. 180–186.

Roerdink Jos BTM, Meijster Arnold. The watershed transform: Definitions, algorithms and parallelization strategies // Fundamenta informaticae. — 2000. — Vol. 41, no. 1, 2. — P. 187–228.

Felzenszwalb P.F., Schwartz J.D. Hierarchical matching of deformable shapes // Computer Vision and Pattern Recognition, 2007.CVPR’07. IEEE Conference on / IEEE. — 2007. — P. 1–8.

Borgefors G. Distance transformations in digital images // Computer vision, graphics, and image processing. — 1986. — Vol. 34,no. 3. — P. 344–371.

Egnal G., Mintz M., Wildes R. P. A stereo confidence metricusing single view imagery with comparison to five alternative approaches // Image and vision computing. — 2004. — Vol. 22,no. 12. — P. 943–957.

J ̈ahne B., Scharr H., K ̈orkel S. Principles of filter design // Handbook of computer vision and applications. — 1999. — Vol. 2. —P. 125–151.

Rolling guidance filter / Q. Zhang, X. Shen, L. Xu, J. Jia //Computer Vision–ECCV 2014. — Springer, 2014. — P. 815–830.

http://compression.ru/download/DFMResults.min/films.html.


Refbacks

  • There are currently no refbacks.


Abava   IEEE FRUCT 2018

ISSN: 2307-8162