提高Shader Model 2.0 蒙皮骨骼动画的骨骼限制

传统的蒙皮骨骼动画混合方法易于理解,但是在SM 2.0的256常量限制下,骨骼数保守计算最多50根骨头,因此对美术的工作流程以及模型渲染方法造成了很大的障碍

float4x4 matBoneArray[40]; //  这是传输的瓶颈

VS_OUTPUT vs_main( SkinnedVS_INPUT In )

{

    VS_OUTPUT Out = (VS_OUTPUT)0;

    float4x4 skinTransform = 0;

    skinTransform += matBoneArray[In.BoneIndices.x] * In.BoneWeights.x;

    skinTransform += matBoneArray[In.BoneIndices.y] * In.BoneWeights.y;

    skinTransform += matBoneArray[In.BoneIndices.z] * In.BoneWeights.z;

    skinTransform += matBoneArray[In.BoneIndices.w] * In.BoneWeights.w;

    float4 localpos = mul(In.Position, skinTransform);

    Out.Position = mul( localpos, matViewProj ); 

    Out.TexCoord = In.TexCoord;

    return Out;

}

matBoneArray这个数组是骨骼的LocalRot和LocalTranslation 通过以下函数build出来

    Matrix4& Matrix4::FromTranslationRotation( const Vector3& translation, const Quaternion& rotation )

    {

        float xx = rotation.x * rotation.x * 2.0f, yy = rotation.y * rotation.y * 2.0f, zz = rotation.z * rotation.z * 2.0f;

        float xy = rotation.x * rotation.y * 2.0f, zw = rotation.z * rotation.w * 2.0f, xz = rotation.x * rotation.z * 2.0f;

        float yw = rotation.y * rotation.w * 2.0f, yz = rotation.y * rotation.z * 2.0f, xw = rotation.x * rotation.w * 2.0f;

        m[0][0] = 1.0f - yy - zz; m[0][1] =        xy + zw; m[0][2] =        xz - yw; m[0][3] = 0.0f;

        m[1][0] =        xy - zw; m[1][1] = 1.0f - xx - zz; m[1][2] =        yz + xw; m[1][3] = 0.0f;

        m[2][0] =        xz + yw; m[2][1] =        yz - xw; m[2][2] = 1.0f - xx - yy; m[2][3] = 0.0f;

        m[3][0] =  translation.x; m[3][1] =  translation.y; m[3][2] =  translation.z; m[3][3] = 1.0f;

        return *this;

    }

从这里你可以发现, 本来每根骨头只需要2个float4 传递变换信息的,现在却需要4个float4,也就是一个矩阵来传递,矩阵中还有很多不使用的变量也被传输到GPU中,这里就是优化的点.

重新调整后的Shader代码:

float4x4 BuildFromTransRot( float4 translation, float4 rot )

{

    float4 rotation = rot;

    float xx = rotation.x * rotation.x * 2.0f, yy = rotation.y * rotation.y * 2.0f, zz = rotation.z * rotation.z * 2.0f;

    float xy = rotation.x * rotation.y * 2.0f, zw = rotation.z * rotation.w * 2.0f, xz = rotation.x * rotation.z * 2.0f;

    float yw = rotation.y * rotation.w * 2.0f, yz = rotation.y * rotation.z * 2.0f, xw = rotation.x * rotation.w * 2.0f;

    float4x4 m = { 

    {1.0f - yy - zz,             xy + zw,             xz - yw,         0},

    {xy - zw,              1.0f - xx - zz,             yz + xw,         0},

    {xz + yw,                      yz - xw,     1.0f - xx - yy,         0},

    {translation.x,       translation.y,       translation.z,         1}

    };

    return m;

}

float4x4 GetBoneElement( float index )

{

    return BuildFromTransRot( vecBoneLocalTrans[index], vecBoneLocalRot[index] );

}

VS_OUTPUT vs_main( SkinnedVS_INPUT In )

{

    VS_OUTPUT Out = (VS_OUTPUT)0;

    float4x4 skinTransform = 0;

    skinTransform += GetBoneElement(In.BoneIndices.x) * In.BoneWeights.x;

    skinTransform += GetBoneElement(In.BoneIndices.y) * In.BoneWeights.y;

    skinTransform += GetBoneElement(In.BoneIndices.z) * In.BoneWeights.z;

    skinTransform += GetBoneElement(In.BoneIndices.w) * In.BoneWeights.w;

    float4 localpos = mul(In.Position, skinTransform);

    Out.Position = mul( localpos, matViewProj ); 

    Out.TexCoord = In.TexCoord;

    return Out;

}

我们将骨头的local旋转及偏移传递至GPU,然后在GPU内重组,虽然对GPU性能计算有部分损耗,但是骨骼数量就能保守提高到100个.

 

http://www.cppblog.com/sunicdavy/archive/2010/04/26/113578.html