diff --git a/main.cpp b/main.cpp
index fa9bd7e9..8ce61dda 100644
--- a/main.cpp
+++ b/main.cpp
@@ -18,13 +18,16 @@ Vec3f        up(0,1,0);
 
 struct Shader : public IShader {
     mat<2,3,float> varying_uv;  // triangle uv coordinates, written by the vertex shader, read by the fragment shader
+    mat<4,3,float> varying_tri; // triangle coordinates (clip coordinates), written by VS, read by FS
     mat<3,3,float> varying_nrm; // normal per vertex to be interpolated by FS
+    mat<3,3,float> ndc_tri;     // triangle in normalized device coordinates
 
     virtual Vec4f vertex(int iface, int nthvert) {
         varying_uv.set_col(nthvert, model->uv(iface, nthvert));
         varying_nrm.set_col(nthvert, proj<3>((Projection*ModelView).invert_transpose()*embed<4>(model->normal(iface, nthvert), 0.f)));
         Vec4f gl_Vertex = Projection*ModelView*embed<4>(model->vert(iface, nthvert));
         varying_tri.set_col(nthvert, gl_Vertex);
+        ndc_tri.set_col(nthvert, proj<3>(gl_Vertex/gl_Vertex[3]));
         return gl_Vertex;
     }
 
@@ -32,8 +35,26 @@ struct Shader : public IShader {
         Vec3f bn = (varying_nrm*bar).normalize();
         Vec2f uv = varying_uv*bar;
 
-        float diff = std::max(0.f, bn*light_dir);
+        mat<3,3,float> A;
+        A[0] = ndc_tri.col(1) - ndc_tri.col(0);
+        A[1] = ndc_tri.col(2) - ndc_tri.col(0);
+        A[2] = bn;
+
+        mat<3,3,float> AI = A.invert();
+
+        Vec3f i = AI * Vec3f(varying_uv[0][1] - varying_uv[0][0], varying_uv[0][2] - varying_uv[0][0], 0);
+        Vec3f j = AI * Vec3f(varying_uv[1][1] - varying_uv[1][0], varying_uv[1][2] - varying_uv[1][0], 0);
+
+        mat<3,3,float> B;
+        B.set_col(0, i.normalize());
+        B.set_col(1, j.normalize());
+        B.set_col(2, bn);
+
+        Vec3f n = (B*model->normal(uv)).normalize();
+
+        float diff = std::max(0.f, n*light_dir);
         color = model->diffuse(uv)*diff;
+
         return false;
     }
 };