From 7a05f4d33b611ba1e9b6c68e0d0bd67d6ea011ee Mon Sep 17 00:00:00 2001
From: skal <pascal.massimino@gmail.com>
Date: Tue, 10 Feb 2026 21:11:05 +0100
Subject: refactor: Optimize CNN grayscale computation

Compute gray once per fragment using dot() instead of per-layer.
Pass gray as f32 parameter to conv functions instead of vec4 original.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---
 doc/CNN_EFFECT.md | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

(limited to 'doc/CNN_EFFECT.md')

diff --git a/doc/CNN_EFFECT.md b/doc/CNN_EFFECT.md
index 4659fd3..22cf985 100644
--- a/doc/CNN_EFFECT.md
+++ b/doc/CNN_EFFECT.md
@@ -38,7 +38,7 @@ fn cnn_conv3x3_7to4(
   samp: sampler,
   uv: vec2<f32>,
   resolution: vec2<f32>,
-  original: vec4<f32>,                     # Original RGBD [-1,1]
+  gray: f32,                               # Grayscale [-1,1]
   weights: array<array<f32, 8>, 36>       # 9 pos × 4 out × (7 weights + bias)
 ) -> vec4<f32>
 
@@ -48,7 +48,7 @@ fn cnn_conv3x3_7to1(
   samp: sampler,
   uv: vec2<f32>,
   resolution: vec2<f32>,
-  original: vec4<f32>,
+  gray: f32,
   weights: array<array<f32, 8>, 9>        # 9 pos × (7 weights + bias)
 ) -> f32
 ```
@@ -56,7 +56,7 @@ fn cnn_conv3x3_7to1(
 **Input normalization:**
 - **fs_main** normalizes textures once: `(tex - 0.5) * 2` → [-1,1]
 - **Conv functions** normalize UV coords: `(uv - 0.5) * 2` → [-1,1]
-- **Grayscale** computed from normalized RGBD: `0.2126*R + 0.7152*G + 0.0722*B`
+- **Grayscale** computed once in fs_main using dot product: `dot(original.rgb, vec3(0.2126, 0.7152, 0.0722))`
 - **Inter-layer data** stays in [-1,1] (no denormalization)
 - **Final output** denormalized for display: `(result + 1.0) * 0.5` → [0,1]
 
@@ -250,20 +250,25 @@ Expands to:
 ```wgsl
 @fragment fn fs_main(@builtin(position) p: vec4<f32>) -> @location(0) vec4<f32> {
     let uv = p.xy / uniforms.resolution;
-    let input = textureSample(txt, smplr, uv);               // Layer N-1 output
-    let original = textureSample(original_input, smplr, uv); // Layer 0 input
-
+    let original_raw = textureSample(original_input, smplr, uv);
+    let original = (original_raw - 0.5) * 2.0;  // Normalize to [-1,1]
+    let gray = dot(original.rgb, vec3<f32>(0.2126, 0.7152, 0.0722));
     var result = vec4<f32>(0.0);
 
     if (params.layer_index == 0) {
-        result = cnn_conv3x3_with_coord(txt, smplr, uv, uniforms.resolution,
-                                        rgba_weights_layer0, coord_weights_layer0, bias_layer0);
+        result = cnn_conv3x3_7to4_src(txt, smplr, uv, uniforms.resolution,
+                                      weights_layer0);
+        result = cnn_tanh(result);
+    }
+    else if (params.layer_index == 1) {
+        result = cnn_conv5x5_7to4(txt, smplr, uv, uniforms.resolution,
+                                   gray, weights_layer1);
         result = cnn_tanh(result);
     }
     // ... other layers
 
     // Blend with ORIGINAL input (not previous layer)
-    return mix(original, result, params.blend_amount);
+    return mix(original_raw, result, params.blend_amount);
 }
 ```
 
-- 
cgit v1.2.3