void cv::remap( InputArray _src, OutputArray _dst,
                InputArray _map1, InputArray _map2,
                int interpolation, int borderType, const Scalar& borderValue )
{
    static RemapNNFunc nn_tab[] =
    {
        remapNearest<uchar>, remapNearest<schar>, remapNearest<ushort>, remapNearest<short>,
        remapNearest<int>, remapNearest<float>, remapNearest<double>, 0
    };

    static RemapFunc linear_tab[] =
    {
        remapBilinear<FixedPtCast<int, uchar, INTER_REMAP_COEF_BITS>, RemapVec_8u, short>, 0,
        remapBilinear<Cast<float, ushort>, RemapNoVec, float>,
        remapBilinear<Cast<float, short>, RemapNoVec, float>, 0,
        remapBilinear<Cast<float, float>, RemapNoVec, float>,
        remapBilinear<Cast<double, double>, RemapNoVec, float>, 0
    };

    static RemapFunc cubic_tab[] =
    {
        remapBicubic<FixedPtCast<int, uchar, INTER_REMAP_COEF_BITS>, short, INTER_REMAP_COEF_SCALE>, 0,
        remapBicubic<Cast<float, ushort>, float, 1>,
        remapBicubic<Cast<float, short>, float, 1>, 0,
        remapBicubic<Cast<float, float>, float, 1>,
        remapBicubic<Cast<double, double>, float, 1>, 0
    };

    static RemapFunc lanczos4_tab[] =
    {
        remapLanczos4<FixedPtCast<int, uchar, INTER_REMAP_COEF_BITS>, short, INTER_REMAP_COEF_SCALE>, 0,
        remapLanczos4<Cast<float, ushort>, float, 1>,
        remapLanczos4<Cast<float, short>, float, 1>, 0,
        remapLanczos4<Cast<float, float>, float, 1>,
        remapLanczos4<Cast<double, double>, float, 1>, 0
    };

    Mat src = _src.getMat(), map1 = _map1.getMat(), map2 = _map2.getMat();

    CV_Assert( map1.size().area() > 0 );
    CV_Assert( !map2.data || (map2.size() == map1.size()));

    _dst.create( map1.size(), src.type() );
    Mat dst = _dst.getMat();
    if( dst.data == src.data )
        src = src.clone();

    int depth = src.depth();
    RemapNNFunc nnfunc = 0;
    RemapFunc ifunc = 0;
    const void* ctab = 0;
    bool fixpt = depth == CV_8U;
    bool planar_input = false;

    if( interpolation == INTER_NEAREST )
    {
        nnfunc = nn_tab[depth];
        CV_Assert( nnfunc != 0 );
    }
    else
    {
        if( interpolation == INTER_AREA )
            interpolation = INTER_LINEAR;

        if( interpolation == INTER_LINEAR )
            ifunc = linear_tab[depth];
        else if( interpolation == INTER_CUBIC )
            ifunc = cubic_tab[depth];
        else if( interpolation == INTER_LANCZOS4 )
            ifunc = lanczos4_tab[depth];
        else
            CV_Error( CV_StsBadArg, "Unknown interpolation method" );
        CV_Assert( ifunc != 0 );
        ctab = initInterTab2D( interpolation, fixpt );
    }

    const Mat *m1 = &map1, *m2 = &map2;

    if( (map1.type() == CV_16SC2 && (map2.type() == CV_16UC1 || map2.type() == CV_16SC1 || !map2.data)) ||
        (map2.type() == CV_16SC2 && (map1.type() == CV_16UC1 || map1.type() == CV_16SC1 || !map1.data)) )
    {
        if( map1.type() != CV_16SC2 )
            std::swap(m1, m2);
    }
    else
    {
        CV_Assert( ((map1.type() == CV_32FC2 || map1.type() == CV_16SC2) && !map2.data) ||
            (map1.type() == CV_32FC1 && map2.type() == CV_32FC1) );
        planar_input = map1.channels() == 1;
    }

    RemapInvoker invoker(src, dst, m1, m2,
                         borderType, borderValue, planar_input, nnfunc, ifunc,
                         ctab);
    parallel_for_(Range(0, dst.rows), invoker, dst.total()/(double)(1<<16));
}