cvpr cvpr2013 cvpr2013-88 cvpr2013-88-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Giuseppe Ottaviano, Pushmeet Kohli
Abstract: Traditional video compression methods obtain a compact representation for image frames by computing coarse motion fields defined on patches of pixels called blocks, in order to compensate for the motion in the scene across frames. This piecewise constant approximation makes the motion field efficiently encodable, but it introduces block artifacts in the warped image frame. In this paper, we address the problem of estimating dense motion fields that, while accurately predicting one frame from a given reference frame by warping it with the field, are also compressible. We introduce a representation for motion fields based on wavelet bases, and approximate the compressibility of their coefficients with a piecewise smooth surrogate function that yields an objective function similar to classical optical flow formulations. We then show how to quantize and encode such coefficients with adaptive precision. We demonstrate the effectiveness of our approach by com- paring its performance with a state-of-the-art wavelet video encoder. Experimental results on a number of standard flow and video datasets reveal that our method significantly outperforms both block-based and optical-flow-based motion compensation algorithms.
[1] S. Baker, D. Scharstein, J. P. Lewis, S. Roth, M. J. Black, and R. Szeliski. A database and evaluation methodology for optical flow. International Journal of Computer Vision, 92(1), 2011.
[2] E. Candès, M. Wakin, and S. Boyd. Enhancing sparsity by reweighted ?1 minimization. Journal of Fourier Analysis and Applications, 14, 2008.
[3] M. Chan, Y. Yu, and A. Constantinides. Variable size block matching motion compensation with applications to video coding. Communications, Speech and Vision, IEEE, 137(4), 1990.
[4] T. M. Cover and J. A. Thomas. Elements of information theory. John Wiley and Sons, Inc., 1991 .
[5] I. Daubechies. Orthonormal bases of compactly supported wavelets ii: variations on a theme. SIAM J. Math. Anal., 24(2), 1993.
[6] Dirac codec. http : / / diracvi de o . org/ down l oad/ speci ficat i / dirac-spe c-l at e st .pdf. on
[7] P. Elias. Universal codeword sets and representations of the integers. IEEE Trans. on Information Theory, 21(2), 1975.
[8] S.-C. Han and C. Podilchuk. Video compression with dense motion fields. IEEE Trans. on Image Processing, 10(1 1), 2001.
[9] B. K. Horn and B. G. Schunck. Determining optical flow. Artificial Intelligence, 17(1–3), 1981 .
[10] C.-L. Huang and C.-Y. Hsu. A new motion compensation
[11]
[12]
[13]
[14]
[15]
[16]
[17]
[18]
[19] method for image sequence coding using hierarchical grid interpolation. IEEE Trans. on Circuits and Systems for Video Technology, 4(1), 1994. J. Jain and A. Jain. Displacement measurement and its application in interframe image coding. IEEE Trans. on Communications, 29(12), 1981 . S. Lin, Y. Shi, and Y.-Q. Zhang. An optical flow based motion compensation algorithm for very low bit-rate video coding. In IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1997. S. Mallat. A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way. Academic Press, 2008. D. Marpe, H. Schwarz, and T. Wiegand. Context-based adaptive binary arithmetic coding in the h.264/avc video compression standard. IEEE Trans. on Circuits and Systems for Video Technology, 13(7), 2003. P. Moulin, R. Krishnamurthy, and J. W. Woods. Multiscale modeling and estimation of motion fields for video coding. IEEE Trans. on Image Processing, 6(12), 1997. M. T. Orchard and G. J. Sullivan. Overlapped block motion compensation: an estimation-theoretic approach. IEEE Trans. on Image Processing, 3(5), 1994. G. Sullivan and T. Wiegand. Rate-distortion optimization for video compression. Signal Processing Magazine, IEEE, 15(6), 1998. H. Watanabe and S. Singhal. Windowed motion compensation. In Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, 1991. T. Wiegand, G. Sullivan, G. Bjontegaard, and A. Luthra. Overview of the h.264/avc video coding standard. IEEE Trans. on Circuits and Systems for Video Technology, 13(7), 2003.
[20] Xiph.org video test media. http : / /media .xiph . org/ video / de rf / , 2012.
[21] C. Zach, T. Pock, and H. Bischof. A duality based approach for realtime TV-L1 optical flow. In DAGM-Symposium, 2007. 222222555866