Similar articles

Abstract: In this paper, a novel motion texture approach is presented for synthesizing long character motion (e.g., kungfu) that is similar to the original short input motion. First, a new motion with repeated frames is generated by exploiting the symmetric properties of the frames and reversing the motion sequence playback in a given motion sequence. Then, the order of the above motion sequence is rearranged by putting the start and the end frames together. The graphcut algorithm is used to seamlessly synthesize the transition between the start and the end frames, which is noted as graphcut-based motion-texton. Finally, we utilize the motion-textons to synthesize long motion texture, which can be patched together like the image texture synthesis method using graphcut algorithm, and automatically form a long motion texture endlessly. Our approach is demonstrated by synthesizing the long kungfu motion texture without visual artifacts, together with post-processing including our new developed graphcut-based motion blending and Poisson-based motion smoothing techniques.

[1] Agrawal, A., Raskar, R., Nayar, S., Li, Y., 2005. Removing flash artifacts using gradient analysis. ACM Transactions on Graphics, 24(3):828-835.

[2] Arikan, O., Forsyth, D.A., 2002. Interactive motion generation from examples. ACM Transactions on Graphics, 21(3):483-490.

[3] Chun, J.S., Kim, M.K., Jung, H.K., 1997. Shape optimization of electromagnetic devices using immune algorithm. IEEE Transactions on Magnetics, 33(2):1876-1879.

[4] Fattal, R., Lischinski, D., Werman, M., 2002. Gradient domain high dynamic range compression. ACM Transactions on Graphics, 21(3):249-256.

[5] Haevre, W.V., Reeth, F.V., 2005. Video Textures Exploiting Symmetric Movements. EUROGRAPHICS Short Presentations, p.489-498.

[6] Hastie, T., Tibshirani, R., Friedman, J., 2002. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer-Verlag, New York, Berlin, Paris.

[7] Hsu, E., Pulli, K., Popovic, J., 2005. Style translation for human motion. ACM Transactions on Graphics, 24(3):1082-1089.

[8] Kwatra, V., Schödl, A., Essa, I.A., Turk, G., Bobick, A.F., 2003. Graphcut textures: Image and video synthesis using graph cuts. ACM Transactions on Graphics, 22(3):277-286.

[9] Li, Y., Wang, T., Shum, H.Y., 2002. Motion texture: A two-level statistical model for character motion synthesis. ACM Transactions on Graphics, 21(3):465-472.

[10] Lucas, K., Schreiner, J., Gleicher, M., 2002a. Footskate cleanup for motion capture editing. Proceedings of ACM SIGGRAPH’02 Symposium on Computer Animation, 21(3):97-104.

[11] Lucas, K., Gleicher, M., Pighin, F., 2002b. Motion graphs. ACM Transactions on Graphics, 21(3):473-482.

[12] Moradoff, S., Lischinski, D., 2004. Constrained synthesis of textural motion for articulated characters. The Visual Computer, 20(4):253-265.

[13] Pullen, K., Bregler, C., 2002. Motion capture assisted animation: texturing and synthesis. ACM Transactions on Graphics, 21(3):501-508.

[14] Schödl, A., Szeliski, R., Salesin, D., Essa, I.A., 2000. Video textures. ACM Transactions on Graphics, 19(3):489-498.

[15] Wexler, Y., Shechtman, E., Irani, M., 2004. Space-time Video Completion. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition’04, p.120-127.