Abstract
In this chapter, the process of converting conventional video sequences to stereo format is considered. Key frame detection, depth assignment, depth propagation, motion vector estimation, background inpainting, and stereo synthesis comprise the stereo conversion pipeline. We also consider several aspects of content production, such as stereo shooting and stereo conversion. The depth propagation algorithm is based on patch matching using patch hash codes, and the results are compared with motion vector-based depth propagation results. Motion vector estimation is an essential algorithm that is used to reveal video clip attributes, and it plays an important role during conversion. We propose an optical flow algorithm based on a primal-dual optimization algorithm. This work is based on the authors’ experience during a large-scale project at the Samsung Research centre in support of newly appearing TVs on the market, which were equipped with a “3D-ready” feature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Appia, V., Batur, U.: Fully automatic 2D to 3D conversion with aid of high-level image features. In: Stereoscopic Displays and Applications XXV, vol. 9011, p. 90110W (2014)
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comp. Vision. 92(1), 1–31 (2011)
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of the 27th Annual Conference on Computer graphics and Interactive Techniques, p. 417 (2000)
Bugeau, A., Piracés, P.G.I., d'Hondt, O., Hervieu, A., Papadakis, N., Caselles, V.: Coherent background video inpainting through Kalman smoothing along trajectories. In: Proceedings of 2010–15th International Workshop on Vision, Modeling, and Visualization, p. 123 (2010)
Butler D.J., Wulff J., Stanley G.B., Black M.J.: A Naturalistic Open Source Movie for Optical Flow Evaluation. In: Fitzgibbon A., Lazebnik S., Perona P., Sato Y., Schmid C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7577. Springer, Berlin, Heidelberg (2012)
Cao, X., Li, Z., Dai, Q.: Semi-automatic 2D-to-3D conversion using disparity propagation. IEEE Trans. Broadcast. 57, 491–499 (2011)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imag. Vision. 40(1), 120–145 (2011)
Criminisi, A., Pérez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)
Feng, J., Ma, H., Hu, J., Cao, L., Zhang, H.: Superpixel based depth propagation for semi-automatic 2D-to-3D video conversion. In: Proceedings of IEEE Third International Conference on Networking and Distributed Computing, pp. 157–160 (2012)
Feng, Z., Chao, Z., Huamin, Y., Yuying, D.: Research on fully automatic 2D to 3D method based on deep learning. In: Proceedings of the IEEE 2nd International Conference on Automation, Electronics and Electrical Engineering, pp. 538–541 (2019)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM. 24(6), 381–395 (1981)
Harman, P.V., Flack, J., Fox, S., Dowley, M.: Rapid 2D-to-3D conversion. In: Stereoscopic displays and virtual reality systems IX International Society for Optics and Photonics, vol. 4660, pp. 78–86 (2002)
Ignatov, A., Bucha, V., Rychagov, M.: Disparity estimation in real-time 3D acquisition and reproduction system. In: Proceedings of the International Conference on Computer Graphics «Graphicon 2009», pp. 61–68 (2009)
Irony, R., Cohen-Or, D., Lischinski, D.: Colorization by example. In: Proceedings of the Sixteenth Eurographics conference on Rendering Techniques, pp. 201–210 (2005)
Korman, S., Avidan, S.: Coherency sensitive hashing. IEEE Trans. Pattern Anal. Mach. Intell. 38(6), 1099–1112 (2015)
Muelle, M., Zill, F., Kauff, P.: Adaptive cross-trilateral depth map filtering. In: Proceedings of the IEEE 3DTV Conference: The True Vision-Capture, Transmission and Display of 3D Video, pp. 1–4 (2010)
Pérez, P., Gangnet, M., Blake, A.: Poisson image editing. In: ACM SIGGRAPH Papers, pp. 313–318 (2003)
Pohl, P., Molchanov, A., Shamsuarov, A., Bucha, V.: Spatio-temporal video background inpainting. Electron. Imaging. 15, 1–5 (2016)
Pohl, P., Sirotenko, M., Tolstaya, E., Bucha, V.: Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. In: Image Processing: Algorithms and Systems XII, 9019, pp. 901–906 (2014)
Shiratori, T., Matsushita, Y., Tang, X., Kang, S.: Video completion by motion field transfer. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, p. 411 (2006)
Sun, J., Xie, J., Li, J., Liu, W.: A key-frame selection method for semi-automatic 2D-to-3D vonversion. In: Zhang, W., Yang, X., Xu, Z., An, P., Liu, Q., Lu, Y. (eds.) Advances on Digital Television and Wireless Multimedia Communications. Communications in Computer and Information Science, vol. 331. Springer, Berlin, Heidelberg (2012)
Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2432–2439 (2010a)
Sun, D., Sudderth, E., Black, M.: Layered image motion with explicit occlusions, temporal consistency, and depth ordering. In: Proceedings of the 24th Annual Conference on Neural Information Processing Systems, pp. 2226–2234 (2010b)
Teed, Z., Deng, J.: Raft: Recurrent all-pairs field transforms for optical flow. In: Proceedings of the European Conference on Computer Vision, pp. 402–419 (2020)
Telea, A.: An image inpainting technique based on the fast marching method. J. Graph. Tools. 9(1) (2004)
Tolstaya E.: Implementation of Coherency Sensitive Hashing algorithm. (2020). Accessed on 03 October 2020. https://github.com/ktolstaya/PyCSH
Tolstaya, E., Hahn, S.-H.: Method and system for selecting key frames from video sequences. RU Patent 2,493,602 (in Russian) (2012)
Tolstaya, E., Pohl, P., Rychagov, M.: Depth propagation for semi-automatic 2d to 3d conversion. In: Proceedings of SPIE Three-Dimensional Image Processing, Measurement, and Applications, vol. 9393, p. 939303 (2015)
Varekamp, C., Barenbrug, B.: Improved depth propagation for 2D to 3D video conversion using key-frames. In: Proceedings of the 4th European Conference on Visual Media Production (2007)
Vatolin, D.: Why Does 3D Lead to the Headache? / Part 8: Defocus and Future of 3D (in Russian) (2019). Accessed on 03 October 2020. https://habr.com/ru/post/472782/
Vatolin, D., Bokov, A., Erofeev, M., Napadovsky, V.: Trends in S3D-movie quality evaluated on 105 films using 10 metrics. Electron. Imaging. 2016(5), 1–10 (2016)
Vatolin, D.: Why Does 3D Lead to the Headache? / Part 2: Discomfort because of Video Quality (in Russian) (2015a). Accessed on 03 October 2020. https://habr.com/en/post/377709/
Vatolin, D.: Why Does 3D Lead to the Headache? / Part 4: Parallax (in Russian) (2015b). Accessed on 03 October 2020. https://habr.com/en/post/378387/
Voronov, A., Vatolin, D., Sumin, D., Napadovsky, V., Borisov, A.: Methodology for stereoscopic motion-picture quality assessment. In: Proceedings of SPIE Stereoscopic Displays and Applications XXIV, vol. 8648, p. 864810 (2013)
Wang, D., Liu, J., Sun, J., Liu, W., Li, Y.: A novel key-frame extraction method for semi-automatic 2D-to-3D video conversion. In: Proceedings of the IEEE international Symposium on Broadband Multimedia Systems and Broadcasting, pp. 1–5 (2012)
Werlberger, M., Pock, T., Bischof, H.: Motion estimation with non-local total variation regularization. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2464–2471 (2010)
Wexler, Y., Shechtman, E., Irani, M.: Space-time completion of video. IEEE Trans. Pattern Anal. Mach. Intell. 29(3), 463–476 (2007)
Xie, J., Girshick, R., Farhadi, A.: Deep3d: Fully automatic 2d-to-3d video conversion with deep convolutional neural networks. In: Proceedings of the European Conference on Computer Vision, pp. 842–857 (2016)
Yuan, H.: Robust semi-automatic 2D-to-3D image conversion via residual-driven optimization. EURASIP J. Image Video Proc. 1, 66 (2018)
Zhao, S., Sheng, Y., Dong, Y., Chang, E., Xu, Y.: MaskFlownet: asymmetric feature matching with learnable occlusion mask. In: Proceedings of the CVPR, vol. 1, pp. 6277–6286 (2020)
Zitnick, C.L., Kang, S.B., Uyttendaele, M., Winder, S., Szeliski, R.: High-quality video view interpolation using a layered representation. ACM Transactions on Graphics. 23(3) (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Pohl, P., Tolstaya, E.V. (2021). Semi-Automatic 2D to 3D Video Conversion. In: Rychagov, M.N., Tolstaya, E.V., Sirotenko, M.Y. (eds) Smart Algorithms for Multimedia and Imaging. Signals and Communication Technology. Springer, Cham. https://doi.org/10.1007/978-3-030-66741-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-66741-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66740-5
Online ISBN: 978-3-030-66741-2
eBook Packages: EngineeringEngineering (R0)