Abstract
In this paper, we propose a parallel-friendly frame rate up-conversion (FRUC) algorithm based on the patch match. The key points of the algorithm are the generation of self-similarity patch, parallel true motion estimation and motion vectors post-processing dealing with occlusion problem. Our algorithm is fully parallel at each step and can be implemented on GPU. The GPU implementation achieves up to 48 times speedup over its CPU implementation. Compared with the traditional FRUC algorithm based on 3-D Recursive Search, our algorithm has a good performance in handling the fine motion structure and occlusion problem.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
De Haan, G., Biezen, P.W.A.C., Huijgen, H., et al.: True-motion estimation with 3-D recursive search block matching. IEEE Trans. Circ. Syst. Video Technol. 3(5), 368–379, 388 (1993)
Kim, D.Y., Park, H.W.: An efficient motion-compensated frame interpolation method using temporal, information for high-resolution videos. J. Disp. Technol. 11(7), 1 (2015)
Braspenning, R.A.C., Haan, G.D.: True-motion estimation using feature correspondences. In: Proceedings of SPIE - The International Society for Optical Engineering, vol. 5308, pp. 396–407 (2004)
Yu, P., Yang, X., Chen, L.: Parallel-friendly patch match based on jump flooding. In: Zhang, W., Yang, X., Xu, Z., An, P., Liu, Q., Lu, Y. (eds.) IFTC 2012. CCIS, vol. 331, pp. 15–21. Springer, Heidelberg (2012). doi:10.1007/978-3-642-34595-1_3
Rong, G., Tan, T.S.: Jump flooding in GPU with applications to Voronoi diagram and distance transform. In: Symposium on Interactive 3d Graphics, Si3d 2006, Redwood City, California, USA, 14–17 March 2006, pp. 109–116 (2006)
Bao, L., Yang, Q., Jin, H.: Fast edge-preserving patchmatch for large displacement optical flow. IEEE Trans. Image Process. 23(12), 4996–5006 (2014). A Publication of the IEEE Signal Processing Society
Michielin, F., Calvagno, G., Sartor, P., et al.: A parallel true motion estimation method based on binarized cross correlation. In: IEEE Third International Conference on Consumer Electronics, Berlin, pp. 1198–1202 (2013)
Barnes, C., Shechtman, E., Finkelstein, A., et al.: PatchMatch: a randomized correspondence algorithm for structural image editing. Acm Trans. Graph. 28(3), 341–352 (2009). Article 24
Hosni, A., Rhemann, C., Bleyer, M., et al.: Fast cost-volume filtering for visual correspondence and beyond. IEEE Trans. Pattern Anal. Mach. Intell. 35(2), 504–511 (2013)
Guo, Y., Chen, L., Gao, Z., et al.: Frame rate up-conversion method for video processing applications. IEEE Trans. Broadcast. 60(4), 659–669 (2014)
Acknowledgment
This work was supported in part by Chinese National Key S&T Special Program (2013ZX01033001-002-002), National Natural Science Foundation of China (61133009, 61221001, 61301116), the Shanghai Key Laboratory of Digital Media Processing and Transmissions (STCSM 12DZ2272600).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jiang, X., Chen, L., Gao, Z., Zhang, X. (2017). Parallel-Friendly Frame Rate Up-Conversion Algorithm Based on Patch Match. In: Yang, X., Zhai, G. (eds) Digital TV and Wireless Multimedia Communication. IFTC 2016. Communications in Computer and Information Science, vol 685. Springer, Singapore. https://doi.org/10.1007/978-981-10-4211-9_15
Download citation
DOI: https://doi.org/10.1007/978-981-10-4211-9_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-4210-2
Online ISBN: 978-981-10-4211-9
eBook Packages: Computer ScienceComputer Science (R0)