“NRT-based Texture Replacement in Real Videos”

  • ©Wen-Chieh Lin and Yanxi Liu

  • ©Wen-Chieh Lin and Yanxi Liu

  • ©Wen-Chieh Lin and Yanxi Liu




    NRT-based Texture Replacement in Real Videos



    As the acquisition of video data becomes easier and easier, it is desirable to have effective computational tools to edit video data. We develop a video editing algorithm that produces the effect of near-regular texture(NRT) replacement [Liu et al. 2004] on a moving curved surface or a surface transformed by lens of unknown parameters (e.g., moving water). Our technique provides novel ap- plications for video editing, e.g., virtual fitting room and fashion design preview.


    Agarwala, A., Hertzmann, A., Salesin, D. H., and Seitz, S. M. 2004. Keyframe-based tracking for rotoscoping and animation. In ACM SIGGRAPH, 584–591.]]
    Liu, Y., Lin, W.-C., and Hays, J. 2004. Near-regular texture analysis and manipulation. In ACM SIGGRAPH, 368–376.]]
    Tsin, Y., Liu, Y., and Ramesh, V. 2001. Texture replacement in real images. In IEEE Conference on Computer Vision and Pattern Recognition, 539–544.]]


    This research is supported in part by an NSF grant IIS-0099597. We thank Aseem Agarwala for providing their code.

ACM Digital Library Publication:

Overview Page: