Multilayer solution to semitransparent edge processing problem in stereoscopic imagery generation

Mikhail Erofeev, Dmitriy Vatolin

Abstract


Due to wide usage of 2D to 3D conversion in movie production industry, the problem of stereoscopic view synthesis has extremely high importance. One of stereoscopic view synthesis main challenges is processing of semitransparent edges near depth map discontinuities. The existing approaches either can deal only with simple cases when background behind the object does not change significantly or try to segment input image in two layers (that is impossible in some cases). The proposed method does not have the above mentioned limits and outperforms competitors in the comparison of synthesized views' visual quality.

Full Text:

PDF (Russian)

References


Real 3D or Fake 3D. http://realorfake3d.com/. Data obrashhenija: 2016-05-23.

Vatolin D. S., Bokov A. A., Fedorov A. A. Tendencii izmenenija tehnicheskogo kachestva stereokino - 5 let posle «Avatara» // Mir tehniki kino. 2015. T. 37, # 3. S. 17–28.

Lie W. N., Chen C. Y., Chen W. C. 2d to 3d video conversion with keyframe depth propagation and trilateral filtering // Electronics Letters. 2011. March. Vol. 47, no. 5. P. 319–321.

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

Akimov Dmitry, Vatolin Dmitry, Smirnov Maxim. Single-image depth map estimation using blur information // Proceedings of the 21st International Conference on Computer Graphics and Vision GraphiCon’2011. GraphiCon. Moscow, Russia, 2011. P. 12–15.

Eigen David, Puhrsch Christian, Fergus Rob. Depth map prediction from a single image using a multi-scale deep network // Advances in neural information processing systems. 2014. P. 2366–2374.

Zachesov A. A., Erofeev M. V., Vatolin D. S. Ispol'zovanie kart glubiny pri vosstanovlenii fona v videoposledovatel'nostjah //Novye informacionnye tehnologii v avtomatizirovannyh sistemah: materialy nauchno-prakticheskogo seminara. M.: MIJeM NIU VShJe, 2015.

Video inpainting of complex scenes / Alasdair Newson, Andrés Almansa, Matthieu Fradet et al. // SIAM Journal on Imaging Sciences. 2014. Vol. 7, no. 4. P. 1993–2019.

Furnace. https://www.thefoundry.co.uk/products/plugins/furnace/. Data obrashhenija: 2016-05-23.

Ahn Yangkeun, Hong Jiman. Application of dibr algorithm in realtime image // Proceedings of the 2012 ACM Research in Applied Computation Symposium / ACM. 2012. P. 169–171.

High-quality video view interpolation using a layered representation / C Lawrence Zitnick, Sing Bing Kang, Matthew Uyttendaele et al. // ACM Transactions on Graphics (TOG) / ACM. Vol. 23. 2004. P. 600–608.

A bayesian approach to digital matting / Yung-Yu Chuang, Brian Curless, David H. Salesin, Richard Szeliski // Computer Vision Pattern Recognition (CVPR). Vol. 2. 2001. P. II–264–II–271.

Kodera Naoki, Fukushima Norishige, Ishibashi Yutaka. Filter based alpha matting for depth image based rendering // Visual Communications and Image Processing (VCIP), 2013 / IEEE. 2013. P. 1–6.

He Kaiming, Sun Jian, Tang Xiaoou. Guided image filtering // Computer Vision–ECCV 2010. Springer, 2010. P. 1–14.

Lie Wen-Nung, Yeh Chun-Cheng, Lin Guo-Shiang. Improving dibr technique to resolve foreground color/depth edge misalignment //Multimedia & Expo Workshops (ICMEW), 2015 IEEE International Conference on / IEEE. 2015. P. 1–5.

Comparison between blur transfer and blur re-generation in depth image based rendering / Norishige Fukushima, Naoki Kodera, Yutaka Ishibashi, Masahiro Tanimoto // 3DTV-Conference: The True

Vision-Capture, Transmission and Display of 3D Video (3DTV-CON), 2014 / IEEE. 2014. P. 1–4.

Layered depth images / Jonathan Shade, Steven Gortler, Li-wei He, Richard Szeliski // Proceedings of the 25th annual conference on Computer graphics and interactive techniques / ACM. 1998. P. 231–242.

Kodera Naoki, Fukushima Norishige, Ishibashi Yutaka. Filter based alpha matting for depth image based rendering // Visual Communications and Image Processing (VCIP), 2013 / IEEE. 2013. P. 1–6.

Zheng Yuanjie, Kambhamettu C. Learning based digital matting //International Conference on Computer Vision (ICCV). 2009. P. 889–896.

Levin Anat, Lischinski Dani, Weiss Yair. A closed-form solution to natural image matting // IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2008. Vol. 30, no. 2. P. 228–242.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность FRUCT 2024

ISSN: 2307-8162