Here´s the code. It does not have any magic numbers or parameters so it should be pretty "plug and play".
-View space position is reconstructed from depth using texture coordinates of the fullscreen quad, no frustum corners required.
-Depth buffer is expected to be linear. So do not use the opengl one, create your own depth shader.
uniform sampler2D gnormals;
uniform sampler2D gdepth;
uniform sampler2D gdiffuse;
uniform sampler2D grandom;
vec3 readNormal(in vec2 coord)
{
return normalize(texture2D(gnormals, coord).xyz*2.0 - 1.0);
}
vec3 posFromDepth(vec2 coord){
float d = texture2D(gdepth, coord).r;
vec3 tray = mat3x3(gl_ProjectionMatrixInverse)*vec3((coord.x-0.5)*2.0,(coord.y-0.5)*2.0,1.0);
return tray*d;
}
float aoFF(in vec3 ddiff,in vec3 cnorm, in float c1, in float c2){
vec3 vv = normalize(ddiff);
float rd = length(ddiff);
return (1.0-clamp(dot(readNormal(gl_TexCoord[0]+vec2(c1,c2)),-vv),0.0,1.0)) *
clamp(dot( cnorm,vv ),0.0,1.0)*
(1.0 - 1.0/sqrt(1.0/(rd*rd) + 1.0));
}
float giFF(in vec3 ddiff,in vec3 cnorm, in float c1, in float c2){
vec3 vv = normalize(ddiff);
float rd = length(ddiff);
return 1.0*clamp(dot(readNormal(gl_TexCoord[0]+vec2(c1,c2)),-vv),0.0,1.0)*
clamp(dot( cnorm,vv ),0.0,1.0)/
(rd*rd+1.0);
}
void main()
{
vec3 n = readNormal(gl_TexCoord[0].st);
vec3 p = posFromDepth(gl_TexCoord[0].st);
vec3 col = texture2D(gdiffuse, gl_TexCoord[0]).rgb;
vec2 fres = vec2(800.0/128.0*5,600.0/128.0*5);
vec3 random = texture2D(grandom, gl_TexCoord[0].st*fres.xy);
random = random*2.0-vec3(1.0);
float ao = 0.0;
vec3 gi = vec3(0.0,0.0,0.0);
float incx = 1.0/800.0*0.1;
float incy = 1.0/600.0*0.1;
float pw = incx;
float ph = incy;
float cdepth = texture2D(gdepth, gl_TexCoord[0]).r;
for(float i=0.0; i<3.0; ++i)
{
float npw = (pw+0.0007*random.x)/cdepth;
float nph = (ph+0.0007*random.y)/cdepth;
vec3 ddiff = posFromDepth(gl_TexCoord[0].st+vec2(npw,nph))-p;
vec3 ddiff2 = posFromDepth(gl_TexCoord[0].st+vec2(npw,-nph))-p;
vec3 ddiff3 = posFromDepth(gl_TexCoord[0].st+vec2(-npw,nph))-p;
vec3 ddiff4 = posFromDepth(gl_TexCoord[0].st+vec2(-npw,-nph))-p;
vec3 ddiff5 = posFromDepth(gl_TexCoord[0].st+vec2(0,nph))-p;
vec3 ddiff6 = posFromDepth(gl_TexCoord[0].st+vec2(0,-nph))-p;
vec3 ddiff7 = posFromDepth(gl_TexCoord[0].st+vec2(npw,0))-p;
vec3 ddiff8 = posFromDepth(gl_TexCoord[0].st+vec2(-npw,0))-p;
ao+= aoFF(ddiff,n,npw,nph);
ao+= aoFF(ddiff2,n,npw,-nph);
ao+= aoFF(ddiff3,n,-npw,nph);
ao+= aoFF(ddiff4,n,-npw,-nph);
ao+= aoFF(ddiff5,n,0,nph);
ao+= aoFF(ddiff6,n,0,-nph);
ao+= aoFF(ddiff7,n,npw,0);
ao+= aoFF(ddiff8,n,-npw,0);
gi+= giFF(ddiff,n,npw,nph)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(npw,nph)).rgb;
gi+= giFF(ddiff2,n,npw,-nph)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(npw,-nph)).rgb;
gi+= giFF(ddiff3,n,-npw,nph)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(-npw,nph)).rgb;
gi+= giFF(ddiff4,n,-npw,-nph)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(-npw,-nph)).rgb;
gi+= giFF(ddiff5,n,0,nph)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(0,nph)).rgb;
gi+= giFF(ddiff6,n,0,-nph)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(0,-nph)).rgb;
gi+= giFF(ddiff7,n,npw,0)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(npw,0)).rgb;
gi+= giFF(ddiff8,n,-npw,0)*texture2D(gdiffuse, gl_TexCoord[0]+vec2(-npw,0)).rgb;
pw += incx;
ph += incy;
}
ao/=24.0;
gi/=24.0;
gl_FragColor = vec4(col-vec3(ao)+gi*5.0,1.0);
}
EDIT: there was a bug in the code, now it´s fixed.
5
With contrast increased, so you can see artifacts & granularity:
None of the screens have any blurring applied, just ssao output. The banding you can see at some places is due to precision problems in my gbuffer, bear with me. Otherwise, it looks incredibly good, consistent when you move the camera, very little haloing (but haloing anyway) and no gray flat surfaces, captures well fine details. Plus you get one bounce local GI, like in the last two screens. Speed wise, without GI it is as fast as every other ssao implementation, maybe a bit slower. With GI, more or less 30-35% speed decrease.
I´m going to post full glsl code soon, together with some speed comparisons. To implement it you´ll need to have a gbuffer set up, or at least normal, diffuse+directlight and depth buffers.
