First generated-footage clip proven through the full chain: Wan2.1 T2V (m3ultra, prompt-engineered to CAPTURE.md rules) -> ./mocap -> wan_walk_t1.fbx -> merge_anims bank (49 tracks). PROGRESS.md bug closed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
PROGRESS.md: Lane B checked off with the session-5 outcome; SESSION 5 DONE block
(all 6 orders) + explicit Lane C handoff (BVH axes, skel_to_mixamorig map, camera
root_space, --from-params). B_ENGINE_SETUP.md: pose_engine.py usage + the engine
facts learned (SKEL 46-q, rest-aware FK ~4cm, Y-down camera fix, mobilenet detector).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
motion.json sidecar gains REQUIRED root_space in {camera, world}. HSMR is
per-frame -> emits camera; Lane C reads it and derives a world root from foot
contacts for locomotion clips. PLAN treaty + Lane C task updated. v1 quality bar:
in-place clips first-class, traveling best-effort until a grounding pass exists.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The pose engine (HSMR) runs on ultra, so nothing was consuming the m3ultra queue
ingest.py shipped to. ingest.py now delivers to a local queue/ dir by default;
--remote-queue [user@host:/path] restores the m3ultra rsync path for when a real
throughput need appears (ponytail marker + PLAN Ground-rule-1 deviation noted).
CAPTURE.md updated. Verified: inbox drop -> local queue/, ledger row, selfcheck green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Ready-to-send draft in docs/DECISIONS.md for John to send to ps-license@tue.mpg.de
(indie AU dev, in-pipeline use, SKEL files not redistributed — only retargeted
motion ships). Path B continues; a grant converts B->A with zero pipeline rework.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The torchvision detector drop-in, headless pyrender/OpenGL shims, and the
detector+smoke tests existed only on ultra's disk inside gitignored .engine/.
Captured byte-identical copies into engine_patches/ (mirrors the HSMR subtree)
and moved setup_hsmr.sh to the repo root (tracked, path-relative) with a
--patch step that overlays them onto the clone.
Acceptance PASSED: fresh shallow clone of HSMR in a temp dir + './setup_hsmr.sh
--patch' + validated venv -> test_detector.py green (7/7 demo imgs, 15 patches),
no hand edits. A re-clone can no longer silently drop the ARM fixes.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
B1's MoCapAnything pick reversed (animal model, wrong for human capture);
license analysis recorded in LICENSES.md. John chose Path B: run HSMR->SKEL
locally on ultra (MPS), ship rig-motion only, accept the non-commercial
licence risk as interim until a commercial SKEL licence request goes out
(Path A, the clean upgrade).
Engine installed under .engine/ (gitignored): uv venv py3.10, torch 2.13
MPS-green, ungated weights, smoke_test.py with Apple-Silicon bypasses
(detectron2 stubbed with full-frame bbox, headless pyrender stubbed -> QC in
Blender) -- see docs/B_ENGINE_SETUP.md.
Remaining before B ships: John's gated SKEL v1.1.1 download, then the
forward-pass smoke test (MPS end-to-end, timing, pose sanity). Known caveat:
HSMR is per-frame so root is camera-space cam_t, NOT world-grounded -> Lane C
derives root from foot-contact.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Confirmed prune. Space pinned by OS-update snapshots (macOS 26.5.2
staged); realizes on next reboot. Updated DECISIONS.md Decision 2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Fresh SOTA survey (per PLAN — distrust the snapshot). Findings:
- MoCapAnything V2 (MIT code+weights, no SMPL, BVH-direct onto arbitrary
rig) is the pick — sidesteps the SMPL commercial-license hard-stop and
collapses the SMPL->mixamorig mapper + most of Lane C retarget.
- GVHMR: best accuracy but non-commercial code license -> reference only.
- GEM-X: commercial-clean + perfect output but CUDA-only -> off-fleet.
Stopped at the John-decision gate (docs/DECISIONS.md): confirm engine,
clear m3ultra disk (97% full), supply test footage. Inference eyeball,
B2 service-ize, B3 jitter remain.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
docs/CAPTURE.md — one-page filming protocol (landscape, feet in frame, T-pose
bookends, 5-30s takes, AirDrop to capture/inbox/).
ingest.py — scans capture/inbox/, probes each clip (ffprobe, display-orientation
aware so phone rotation tags are respected), rejects portrait/malformed to
capture/rejected/ with a reason, normalizes the rest to 30fps h264 (audio
stripped), renames YYYYMMDD_<name>.mp4, rsyncs to the m3ultra pose queue, and
logs every disposition to capture/LEDGER.tsv. Failed ships keep the normalized
file in capture/staged/ so a re-run retries without re-encoding.
--selfcheck exercises probe+validate on synthesized landscape/portrait clips.
Verified end-to-end: inbox drop -> one command -> clip in m3ultra queue, portrait
rejected with clear error, ledger rows written.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
git init + .gitignore (weights/capture/queue/out/media excluded), docs/LICENSES.md
skeleton with the SMPL gate, PROGRESS.md ledger, and spec/mixamorig_bones.json —
65 mixamorig bones (colon-prefixed) dumped from character_kit/female/female_game.glb
via headless Blender. This bone file is the retarget ground truth for Lane C.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
