demo.git - Vide-coded 64k demo system

Age	Commit message (Collapse)	Author
13 hours	fix(cnn_v3): resize target to albedo dims when sizes differ	skal
	target.png can have a different resolution than albedo.png in simple samples; patch slicing into the smaller target produced 0×0 tensors, crashing torch.stack in the DataLoader collate. handoff(Gemini): target resized in _load_sample (LANCZOS) + note in HOW_TO_CNN §1c.
13 hours	docs(cnn_v3): add full Old House example to HOW_TO_CNN §1b	skal
	handoff(Gemini): added render + batch-pack example commands at end of section 1b
14 hours	fix(cnn_v3): native OPEN_EXR_MULTILAYER + quiet render + flexible channel names	skal
	blender_export.py: - Replace broken compositor FileOutput approach with native OPEN_EXR_MULTILAYER render output; all enabled passes included automatically, no socket wiring needed - Suppress Fra:/Mem: render spam via os.dup2 fd redirect; per-frame progress printed to stderr via render_post handler pack_blender_sample.py: - get_pass_r: try .R/.X/.Y/.Z/'' suffixes + aliases param for Depth→Z fallback - combined_rgba loaded once via ("Combined","Image") loop; shared by transp+target - Remove unused sys import HOW_TO_CNN.md: update channel table to native EXR naming (Depth.Z, IndexOB.X, Shadow.X), fix example command, note Shadow defaults to 255 when absent handoff(Gemini): blender pipeline now produces correct multilayer EXR with all G-buffer passes; pack script handles native channel naming
14 hours	docs(cnn_v3): blender4 alias + Blender 4.5 LTS requirement for training data	skal

16 hours	docs(cnn_v3): clarify --output is a base dir, not a frame_### pattern	skal

16 hours	docs(cnn_v3): update HOW_TO_CNN for Blender 5.x compatibility	skal

16 hours	fix(cnn_v3): blender_export --view-layer flag + fallback to layer[0]	skal
	Fixes KeyError when blend file uses a non-default view layer name. Adds --view-layer NAME arg; pass '?' to list available layers. Defaults to index 0 with a clear error if the name is not found. handoff(Gemini): blender_export.py view layer selection now robust
16 hours	feat(cnn_v3): gen_sample tool + 7 simple training samples	skal
	- pack_photo_sample.py: --target now required (no albedo fallback) - gen_sample.py: bash wrapper with positional args (input target output_dir) - input/photo7.jpg: copy of photo2 (second style target) - target_1: photo2_1_out→photo2_out, photo2_2_out→photo7_out - dataset/simple/sample_001..007: 7 packed photo/target pairs handoff(Gemini): training data ready; next step is train_cnn_v3.py run
37 hours	feat(cnn_v3): HTML WebGPU tool (index.html + shaders.js + tester.js)	skal
	3-file tool, 939 lines total. Implements full U-Net+FiLM inference in the browser: Pack→Enc0→Enc1→Bottleneck→Dec1→Dec0 compute passes, layer visualisation (Feat/Enc0/Enc1/BN/Dec1/Output), FiLM MLP sliders, drag-drop weights + image/video, Save PNG, diff/blend view modes. HOW_TO_CNN.md §7 updated to reflect tool is implemented. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
38 hours	feat(cnn_v3): export script + HOW_TO_CNN.md playbook	skal
	- export_cnn_v3_weights.py: .pth → cnn_v3_weights.bin (f16 packed u32) + cnn_v3_film_mlp.bin (f32) - HOW_TO_CNN.md: full pipeline playbook (data collection, training, export, C++ wiring, parity, HTML tool) - TODO.md: mark export script done Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
38 hours	feat(cnn_v3): Phase 6 — training script (train_cnn_v3.py + cnn_v3_utils.py)	skal
	- train_cnn_v3.py: CNNv3 U-Net+FiLM model, training loop, CLI - cnn_v3_utils.py: image I/O, pyrdown, depth_gradient, assemble_features, apply_channel_dropout, detect_salient_points, CNNv3Dataset - Patch-based training (default 64×64) with salient-point extraction (harris/shi-tomasi/fast/gradient/random detectors, pre-cached at init) - Channel dropout for geometric/context/temporal channels - Random FiLM conditioning per sample for joint MLP+U-Net training - docs: HOWTO.md §3 updated with commands and flag reference - TODO.md: Phase 6 marked done, export script noted as next step Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
38 hours	docs(cnn_v3): update CNN_V3.md + HOWTO.md to reflect Phases 1-5 complete	skal
	- CNN_V3.md: status line, architecture channel counts (8/16→4/8), FiLM MLP output count (96→40 params), size budget table (real implemented values) - HOWTO.md: Phase status table (5→done, add phase 6 training TODO), sections 3-5 rewritten to reflect what exists vs what is still planned
39 hours	feat(cnn_v3): Phase 4 complete — CNNv3Effect C++ + FiLM uniform upload	skal
	- cnn_v3/src/cnn_v3_effect.{h,cc}: full Effect subclass with 5 compute passes (enc0→enc1→bottleneck→dec1→dec0), shared weights storage buffer, per-pass uniform buffers, set_film_params() API - Fixed WGSL/C++ struct alignment: vec3u has align=16, so CnnV3Params4ch is 64 bytes and CnnV3ParamsEnc1 is 96 bytes (not 48/80) - Weight offsets computed as explicit formulas (e.g. 2049+4) for clarity - Registered in CMake, shaders.h/cc, demo_effects.h, test_demo_effects.cc - 35/35 tests pass handoff(Gemini): CNN v3 Phase 5 next — parity validation (Python ref vs WGSL)
40 hours	feat(cnn_v3): Phase 3 complete — WGSL U-Net inference shaders	skal
	5 compute shaders + cnn_v3/common snippet: enc0: Conv(20→4,3×3) + FiLM + ReLU full-res enc1: AvgPool + Conv(4→8,3×3) + FiLM + ReLU half-res bottleneck: AvgPool + Conv(8→8,1×1) + ReLU quarter-res dec1: NearestUp + cat(enc1) + Conv(16→4) + FiLM half-res dec0: NearestUp + cat(enc0) + Conv(8→4) + FiLM + Sigmoid full-res Parity rules: zero-pad conv, AvgPool down, NearestUp, FiLM after conv+bias, skip=concat, OIHW weights+bias layout. Matches PyTorch train_cnn_v3.py forward() exactly. Registered in workspaces/main/assets.txt + src/effects/shaders.cc. Weight layout + Params struct documented in cnn_v3/docs/HOWTO.md §7. Next: Phase 4 — C++ CNNv3Effect + FiLM uniform upload. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
3 days	feat(cnn_v3): Phase 1 complete - GBufferEffect integrated + HOWTO playbook	skal
	- Wire GBufferEffect into demo build: assets.txt, DemoSourceLists.cmake, demo_effects.h, shaders.h/cc. ShaderComposer::Compose() applied to gbuf_raster.wgsl (resolves #include "common_uniforms"). - Add GBufferEffect construction test. 35/35 passing. - Write cnn_v3/docs/HOWTO.md: G-buffer wiring, training data prep, training plan, per-pixel validation workflow, phase status table, troubleshooting guide. - Add project hooks: remind to update HOWTO.md on cnn_v3/ edits; warn on direct str_view(*_wgsl) usage bypassing ShaderComposer. - Update PROJECT_CONTEXT.md and TODO.md: Phase 1 done, Phase 3 (WGSL U-Net shaders) is next active. handoff(Gemini): CNN v3 Phase 3 is next - WGSL enc/dec/bottleneck/FiLM shaders in cnn_v3/shaders/. See cnn_v3/docs/CNN_V3.md Architecture section and cnn_v3/docs/HOWTO.md section 3 for spec. GBufferEffect outputs feat_tex0 + feat_tex1 (rgba32uint, 20ch, 32 bytes/pixel). C++ CNNv3Effect (Phase 4) takes those as input nodes.
3 days	docs(cnn_v3): full design doc — U-Net + FiLM architecture plan	skal
	- CNN_V3.md: complete design document - U-Net enc_channels=[4,8], ~5 KB f16 weights - FiLM conditioning (5D → γ/β per level, CPU-side MLP) - 20-channel feature buffer, 32 bytes/pixel: two rgba32uint textures - feat_tex0: albedo.rgb, normal.xy, depth, depth_grad.xy (f16) - feat_tex1: mat_id, prev.rgb, mip1.rgb, mip2.rgb, shadow, transp (u8) - 4-pass G-buffer: raster MRT + SDF compute + lighting + pack - Per-pixel parity framework: PyTorch / HTML WebGPU / C++ WebGPU (≤1/255) - Training pipelines: Blender full G-buffer + photo-only (channel dropout) - train_cnn_v3_full.sh spec (modelled on v2 script) - HTML tool adaptation plan from cnn_v2/tools/cnn_v2_test/index.html - Binary format v3 header spec - 8-phase ordered implementation checklist - TODO.md: add CNN v3 U-Net+FiLM future task with phases - cnn_v3/README.md: update status to design phase handoff(Gemini): CNN v3 design complete. Phase 0 (stub G-buffer) unblocks all other phases — one compute shader writing feat_tex0+feat_tex1 with synthetic values from the current framebuffer. See cnn_v3/docs/CNN_V3.md Implementation Checklist.