Efficient Bicubic filtering code in GLSL?

Question

I\'m wondering if anyone has complete, working, and efficient code to do bicubic texture filtering in glsl. There is this:

http://www.codeproject.com/Articles/236394/Bi-

Answer 1

The missing function cubic() in JAre's answer could look like this:

vec4 cubic(float x)
{
    float x2 = x * x;
    float x3 = x2 * x;
    vec4 w;
    w.x =   -x3 + 3*x2 - 3*x + 1;
    w.y =  3*x3 - 6*x2       + 4;
    w.z = -3*x3 + 3*x2 + 3*x + 1;
    w.w =  x3;
    return w / 6.f;
}

It returns the four weights for cubic B-Spline.

It is all explained in NVidia Gems.

Answer 2

I found this implementation which can be used as a drop-in replacement for texture() (from http://www.java-gaming.org/index.php?topic=35123.0 (one typo fixed)):

// from http://www.java-gaming.org/index.php?topic=35123.0
vec4 cubic(float v){
    vec4 n = vec4(1.0, 2.0, 3.0, 4.0) - v;
    vec4 s = n * n * n;
    float x = s.x;
    float y = s.y - 4.0 * s.x;
    float z = s.z - 4.0 * s.y + 6.0 * s.x;
    float w = 6.0 - x - y - z;
    return vec4(x, y, z, w) * (1.0/6.0);
}

vec4 textureBicubic(sampler2D sampler, vec2 texCoords){

   vec2 texSize = textureSize(sampler, 0);
   vec2 invTexSize = 1.0 / texSize;

   texCoords = texCoords * texSize - 0.5;


    vec2 fxy = fract(texCoords);
    texCoords -= fxy;

    vec4 xcubic = cubic(fxy.x);
    vec4 ycubic = cubic(fxy.y);

    vec4 c = texCoords.xxyy + vec2 (-0.5, +1.5).xyxy;

    vec4 s = vec4(xcubic.xz + xcubic.yw, ycubic.xz + ycubic.yw);
    vec4 offset = c + vec4 (xcubic.yw, ycubic.yw) / s;

    offset *= invTexSize.xxyy;

    vec4 sample0 = texture(sampler, offset.xz);
    vec4 sample1 = texture(sampler, offset.yz);
    vec4 sample2 = texture(sampler, offset.xw);
    vec4 sample3 = texture(sampler, offset.yw);

    float sx = s.x / (s.x + s.y);
    float sy = s.z / (s.z + s.w);

    return mix(
       mix(sample3, sample2, sx), mix(sample1, sample0, sx)
    , sy);
}

Example: Nearest, bilinear, bicubic:

The ImageData of this image is

{{{0.698039, 0.996078, 0.262745}, {0., 0.266667, 1.}, {0.00392157, 
   0.25098, 0.996078}, {1., 0.65098, 0.}}, {{0.996078, 0.823529, 
   0.}, {0.498039, 0., 0.00392157}, {0.831373, 0.00392157, 
   0.00392157}, {0.956863, 0.972549, 0.00784314}}, {{0.909804, 
   0.00784314, 0.}, {0.87451, 0.996078, 0.0862745}, {0.196078, 
   0.992157, 0.760784}, {0.00392157, 0.00392157, 0.498039}}, {{1., 
   0.878431, 0.}, {0.588235, 0.00392157, 0.00392157}, {0.00392157, 
   0.0666667, 0.996078}, {0.996078, 0.517647, 0.}}}

I tried to reproduce this (many other interpolation techniques)

but they have clamped padding, while I have repeating (wrapping) boundaries. Therefore it is not exactly the same.

It seems this bicubic business is not a proper interpolation, i.e. it does not take on the original values at the points where the data is defined.