diff options
Diffstat (limited to 'TODO.md')
| -rw-r--r-- | TODO.md | 14 |
1 files changed, 8 insertions, 6 deletions
@@ -60,20 +60,22 @@ Ongoing shader code hygiene for granular, reusable snippets. --- -## Future: CNN v3 — U-Net + FiLM +## CNN v3 — U-Net + FiLM [IN PROGRESS] U-Net architecture with FiLM conditioning. Runtime style control via beat/audio. Richer G-buffer input (normals, depth, material IDs). Per-pixel testability across PyTorch / HTML WebGPU / C++ WebGPU. -**Prerequisites:** G-buffer implementation (GEOM_BUFFER.md) **Design:** `cnn_v3/docs/CNN_V3.md` **Phases:** -1. G-buffer prerequisite -2. Training infrastructure (Blender exporter + photo pipeline) -3. WGSL shaders (enc/dec/bottleneck, deterministic ops) -4. C++ effect class + FiLM uniform upload +1. ✅ G-buffer: `GBufferEffect` (MRT raster + pack compute). SDF/shadow passes TODO. + - New NodeTypes: `GBUF_ALBEDO`, `GBUF_DEPTH32`, `GBUF_R8`, `GBUF_RGBA32UINT` + - Shaders: `cnn_v3/shaders/gbuf_raster.wgsl`, `gbuf_pack.wgsl` + - CMake integration deferred +2. ✅ Training infrastructure: `blender_export.py`, `pack_blender_sample.py`, `pack_photo_sample.py` +3. WGSL shaders (enc/dec/bottleneck, FiLM, deterministic ops) +4. C++ CNNv3Effect + FiLM uniform upload 5. Parity validation (test vectors, ≤1/255 per pixel) ## Future: CNN v2 8-bit Quantization |