arthur/js/app.js
Your Name 5ac919b9d6 Audio-clocked playback for judging sync
Lip sync cannot be judged silently. extract.sh now pulls the audio track and
writes manifest.json alongside the frames; the page reads the true extraction
rate from it rather than assuming one, since a guessed fps desynchronises
picture from sound - the one thing this view exists to show.

Audio is the clock: frame = floor(currentTime * fps). A slow render loop drops
frames instead of drifting, and half/quarter speed work via playbackRate with
the picture following for free. Scrubbing, stepping and clicking a thumbnail
all seek the audio too.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-24 14:53:09 -04:00

533 lines
19 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import { FaceLandmarker, FilesetResolver } from 'https://cdn.jsdelivr.net/npm/@mediapipe/tasks-vision@1.0.1/vision_bundle.mjs';
import { LIPS_OUTER, LIPS_INNER, FACE_OVAL } from './landmarks.js';
import { stabilize, toRasterRing, smoothContours, suggestPlateFrames, heldFrame } from './pipeline.js';
import { IndexedRaster } from './raster.js';
import { writeTake } from './take.js';
import { synthDense } from './synth.js';
const RW = 320, RH = 200, ZOOM = 2, THUMB = 92;
const PALETTE = [
{ name: 'bg', hex: '#12141c' },
{ name: 'skin_base', hex: '#b07a5a' },
{ name: 'skin_dark', hex: '#7a4f3a' },
{ name: 'mouth_dark', hex: '#24161a' },
{ name: 'skin_lite', hex: '#d9a884' },
];
const IDX = { bg: 0, base: 1, dark: 2, mouth: 3, lite: 4 };
const state = {
dense: null, images: [], stab: null, xform: null,
outer: null, inner: null, plates: null, hidden: null,
keep: new Set(), // frames that get their own plate drawing
frame: 0, playing: false, faceBox: null,
fps: 12, audio: null, // fps comes from manifest.json, never guessed
};
const el = (id) => document.getElementById(id);
const opts = () => ({
verts: +el('verts').value,
smoothWin: +el('smoothWin').value,
contourSmooth: +el('contourSmooth').value,
apertureThresh: +el('apertureThresh').value / 1000,
tol: +el('tol').value / 1000,
});
function status(msg, kind = '') {
el('status').textContent = msg;
el('status').className = kind;
}
/* ---------- loading ---------- */
const loadImage = (src) => new Promise((r) => {
const im = new Image();
im.onload = () => r(im); im.onerror = () => r(null); im.src = src;
});
// The extraction rate is read, not assumed. Guessing it would desynchronise
// audio from picture, which is the one thing this view exists to show.
async function loadManifest() {
try {
const r = await fetch('./manifest.json', { cache: 'no-store' });
if (!r.ok) return null;
return await r.json();
} catch { return null; }
}
function attachAudio(name) {
const a = el('audio');
if (!name) { a.removeAttribute('src'); a.hidden = true; state.audio = null; return; }
a.src = './' + name;
a.hidden = false;
state.audio = a;
}
async function loadFrameSequence() {
const dir = el('framedir').value.replace(/\/$/, '');
const imgs = [];
for (let i = 1; i <= 900; i++) {
const im = await loadImage(`${dir}/${String(i).padStart(4, '0')}.png`);
if (!im) break;
imgs.push(im);
if (i % 10 === 0) status(`loading frames… ${i}`);
}
return imgs;
}
let landmarker = null;
async function initLandmarker() {
if (landmarker) return landmarker;
status('loading MediaPipe wasm…');
const fileset = await FilesetResolver.forVisionTasks(
'https://cdn.jsdelivr.net/npm/@mediapipe/tasks-vision@1.0.1/wasm');
// GPU is faster but unavailable in some contexts; fall back rather than fail.
for (const delegate of ['GPU', 'CPU']) {
try {
landmarker = await FaceLandmarker.createFromOptions(fileset, {
baseOptions: { modelAssetPath: './face_landmarker.task', delegate },
runningMode: 'IMAGE', numFaces: 1,
});
status(`landmarker ready (${delegate})`);
return landmarker;
} catch (e) {
if (delegate === 'CPU') throw e;
console.warn('GPU delegate failed, falling back to CPU:', e.message);
}
}
}
async function detectAll(images) {
const lm = await initLandmarker();
const cv = document.createElement('canvas');
const dense = [], missing = [];
for (let i = 0; i < images.length; i++) {
const im = images[i];
cv.width = im.naturalWidth; cv.height = im.naturalHeight;
cv.getContext('2d').drawImage(im, 0, 0);
const out = lm.detect(cv);
if (out.faceLandmarks && out.faceLandmarks.length) dense.push(out.faceLandmarks[0]);
else { missing.push(i); dense.push(dense.length ? dense[dense.length - 1] : null); }
if (i % 4 === 0) status(`detecting… ${i + 1}/${images.length}`);
}
if (dense[0] === null) throw new Error('no face found in the first frame');
return { dense, missing };
}
/* ---------- build ---------- */
function makeXform(stab, neutral) {
const oval = stab.oval[neutral];
let x0 = Infinity, y0 = Infinity, x1 = -Infinity, y1 = -Infinity;
for (const p of oval) {
x0 = Math.min(x0, p.x); y0 = Math.min(y0, p.y);
x1 = Math.max(x1, p.x); y1 = Math.max(y1, p.y);
}
const s = (RH * 0.80) / (y1 - y0);
const cx = (x0 + x1) / 2, cy = (y0 + y1) / 2;
return (p) => ({ x: (p.x - cx) * s + RW / 2, y: (p.y - cy) * s + RH / 2 });
}
function rebuild(resetKeep) {
if (!state.dense) return;
const o = opts();
const N = state.dense.length;
state.stab = stabilize(state.dense, o.smoothWin);
const ap = state.stab.aperture;
const head = Math.max(1, Math.floor(N / 4));
let neutral = 0;
for (let i = 0; i < head; i++) if (ap[i] < ap[neutral]) neutral = i;
state.neutral = neutral;
state.xform = makeXform(state.stab, neutral);
// Mouth is traced, so it costs nothing: a key on EVERY frame. Only the plate,
// which a human draws, gets decimated.
state.outer = smoothContours(
state.stab.outer.map((r) => toRasterRing(r, LIPS_OUTER, o.verts, state.xform)), o.contourSmooth);
state.inner = smoothContours(
state.stab.inner.map((r) => toRasterRing(r, LIPS_INNER, o.verts, state.xform)), o.contourSmooth);
const apMax = Math.max(...ap);
state.hidden = ap.map((v) => v / apMax < o.apertureThresh);
// Plate outline per frame, so a kept frame shows its own head shape.
state.plates = state.stab.oval.map((r) => r.map(state.xform));
if (resetKeep || !state.keep.size) {
state.keep = new Set(Array.from({ length: N }, (_, i) => i));
}
// Frame 0 must always be kept: something has to be on screen at the start.
state.keep.add(0);
state.faceBox = faceBoxes();
drawAll();
}
// Face bounding box per frame in image space, for legible strip thumbnails.
function faceBoxes() {
return state.dense.map((lm) => {
let x0 = 1, y0 = 1, x1 = 0, y1 = 0;
for (const i of FACE_OVAL) {
x0 = Math.min(x0, lm[i].x); y0 = Math.min(y0, lm[i].y);
x1 = Math.max(x1, lm[i].x); y1 = Math.max(y1, lm[i].y);
}
const mx = (x1 - x0) * 0.18, my = (y1 - y0) * 0.14;
return { x0: x0 - mx, y0: y0 - my, x1: x1 + mx, y1: y1 + my };
});
}
/* ---------- render ---------- */
function renderFrame(f) {
const r = new IndexedRaster(RW, RH);
r.clear(IDX.bg);
const pf = heldFrame(keptSorted(), f); // the plate that is on screen
r.fillPoly(state.plates[pf], IDX.base);
r.fillPoly(state.outer[f], IDX.dark); // mouth at full rate
if (!state.hidden[f]) r.fillPoly(state.inner[f], IDX.mouth);
return r;
}
const keptSorted = () => [...state.keep].sort((a, b) => a - b);
function blit(canvas, raster, zoom) {
canvas.width = RW * zoom; canvas.height = RH * zoom;
canvas.getContext('2d').putImageData(raster.toImageData(PALETTE.map((p) => p.hex), zoom), 0, 0);
}
function drawAll() {
drawPanes();
drawStrip();
drawWorksheet();
drawReadout();
}
function drawReadout() {
const kept = keptSorted();
const runs = kept.map((k, i) => (i + 1 < kept.length ? kept[i + 1] : state.dense.length) - k);
el('readout').textContent =
`${state.dense.length} frames → ${kept.length} drawings · ` +
`holds ${Math.min(...runs)}–${Math.max(...runs)} frames · ` +
`neutral f${state.neutral} · residual ` +
`${(state.stab.residual.reduce((a, b) => a + b, 0) / state.dense.length).toFixed(4)}`;
}
function drawPanes() {
const f = state.frame, kept = keptSorted();
const pf = heldFrame(kept, f);
el('framelabel').textContent =
`f ${f} / ${state.dense.length - 1} · ${(f / state.fps).toFixed(2)}s · plate f${pf}` +
(state.keep.has(f) ? ' · KEPT' : ' · held');
const c1 = el('cv-source'), g1 = c1.getContext('2d');
c1.width = RW * ZOOM; c1.height = RH * ZOOM;
g1.fillStyle = '#000'; g1.fillRect(0, 0, c1.width, c1.height);
const im = state.images[f];
if (im) {
const b = state.faceBox[f];
const sx = b.x0 * im.naturalWidth, sy = b.y0 * im.naturalHeight;
const sw = (b.x1 - b.x0) * im.naturalWidth, sh = (b.y1 - b.y0) * im.naturalHeight;
const s = Math.min(c1.width / sw, c1.height / sh);
const dw = sw * s, dh = sh * s, dx = (c1.width - dw) / 2, dy = (c1.height - dh) / 2;
g1.drawImage(im, sx, sy, sw, sh, dx, dy, dw, dh);
const map = (p) => ({ x: dx + (p.x * im.naturalWidth - sx) * s, y: dy + (p.y * im.naturalHeight - sy) * s });
strokePts(g1, LIPS_OUTER.map((i) => map(state.dense[f][i])), '#4ade80');
strokePts(g1, LIPS_INNER.map((i) => map(state.dense[f][i])), '#f87171');
} else {
g1.fillStyle = '#555'; g1.font = '13px system-ui';
g1.fillText('synthetic — no source frames', 14, 24);
const sc = (p) => ({ x: p.x * c1.width, y: p.y * c1.height });
strokePts(g1, LIPS_OUTER.map((i) => sc(state.dense[f][i])), '#4ade80');
strokePts(g1, LIPS_INNER.map((i) => sc(state.dense[f][i])), '#f87171');
}
const c2 = el('cv-stab'), g2 = c2.getContext('2d');
c2.width = RW * ZOOM; c2.height = RH * ZOOM;
g2.fillStyle = '#0d0f16'; g2.fillRect(0, 0, c2.width, c2.height);
g2.strokeStyle = '#2a2f3e'; g2.lineWidth = 1; g2.beginPath();
g2.moveTo(c2.width / 2, 0); g2.lineTo(c2.width / 2, c2.height);
g2.moveTo(0, c2.height / 2); g2.lineTo(c2.width, c2.height / 2); g2.stroke();
const z = (pts) => pts.map((p) => ({ x: p.x * ZOOM, y: p.y * ZOOM }));
strokePts(g2, z(state.plates[pf]), '#3b4a63');
strokePts(g2, z(state.outer[f]), '#4ade80');
if (!state.hidden[f]) strokePts(g2, z(state.inner[f]), '#f87171');
blit(el('cv-render'), renderFrame(f), ZOOM);
}
function strokePts(g, pts, color, lw = 1) {
g.strokeStyle = color; g.lineWidth = lw;
g.beginPath();
pts.forEach((p, i) => (i ? g.lineTo(p.x, p.y) : g.moveTo(p.x, p.y)));
g.closePath(); g.stroke();
}
/* ---------- the frame strip: this is the editing surface ---------- */
function drawStrip() {
const host = el('strip');
host.innerHTML = '';
const N = state.dense.length;
for (let f = 0; f < N; f++) {
const cell = document.createElement('div');
cell.className = 'fr' + (state.keep.has(f) ? ' keep' : ' drop') + (f === state.frame ? ' cur' : '');
cell.dataset.f = f;
const cv = document.createElement('canvas');
const im = state.images[f];
cv.width = THUMB; cv.height = THUMB;
const g = cv.getContext('2d');
g.fillStyle = '#0d0f16'; g.fillRect(0, 0, THUMB, THUMB);
if (im) {
const b = state.faceBox[f];
const sx = b.x0 * im.naturalWidth, sy = b.y0 * im.naturalHeight;
const sw = (b.x1 - b.x0) * im.naturalWidth, sh = (b.y1 - b.y0) * im.naturalHeight;
const s = Math.min(THUMB / sw, THUMB / sh);
g.drawImage(im, sx, sy, sw, sh, (THUMB - sw * s) / 2, (THUMB - sh * s) / 2, sw * s, sh * s);
} else {
const r = new IndexedRaster(RW, RH);
r.clear(IDX.bg); r.fillPoly(state.plates[f], IDX.base);
const tmp = document.createElement('canvas');
blit(tmp, r, 1);
g.drawImage(tmp, 0, 0, RW, RH, 0, 0, THUMB, THUMB * (RH / RW));
}
const tag = document.createElement('span');
tag.textContent = f;
cell.append(cv, tag);
cell.onclick = (ev) => {
seekTo(f);
if (ev.shiftKey) toggle(f);
drawAll();
};
cell.ondblclick = () => { toggle(f); drawAll(); };
host.append(cell);
}
}
function toggle(f) {
if (f === 0) return; // frame 0 always has a drawing
if (state.keep.has(f)) state.keep.delete(f); else state.keep.add(f);
}
/* ---------- worksheet: the frames a human must draw ---------- */
function drawWorksheet() {
const host = el('sheet');
host.innerHTML = '';
const kept = keptSorted();
kept.forEach((f, i) => {
const until = (i + 1 < kept.length ? kept[i + 1] : state.dense.length) - 1;
const cell = document.createElement('div');
cell.className = 'cell';
const cv = document.createElement('canvas');
const im = state.images[f];
if (im) {
const b = state.faceBox[f];
const sx = b.x0 * im.naturalWidth, sy = b.y0 * im.naturalHeight;
const sw = (b.x1 - b.x0) * im.naturalWidth, sh = (b.y1 - b.y0) * im.naturalHeight;
cv.width = 150; cv.height = Math.round(150 * (sh / sw));
cv.getContext('2d').drawImage(im, sx, sy, sw, sh, 0, 0, cv.width, cv.height);
} else {
blit(cv, renderFrame(f), 1);
cv.style.width = '150px';
}
const cap = document.createElement('span');
cap.textContent = `f${f}` + (until > f ? ` → ${until}` : '') + ` (${until - f + 1}f)`;
cell.append(cv, cap);
cell.onclick = () => { seekTo(f); drawAll(); };
host.append(cell);
});
}
/* ---------- export ---------- */
function exportTake() {
const kept = keptSorted();
const N = state.dense.length;
const take = {
name: el('takename').value || 'line_01',
frames: N, width: RW, height: RH, exposure: 1, fps: state.fps,
palette: PALETTE,
slot: { x: RW / 2, y: RH / 2 },
parts: [
// Sparse: one plate key per frame a human draws.
{ name: 'head', kind: 'plate', z: 0, interp: 'hold',
keys: kept.map((f, i) => ({ f: i, plate: i, src: f })) },
// Dense: the traced mouth keeps every frame.
{ name: 'mouth', kind: 'poly', z: 30, color: 'skin_dark', interp: 'hold',
keys: state.outer.map((pts, f) => ({ f, src: f, pts })) },
{ name: 'mouth_in', kind: 'poly', z: 31, color: 'mouth_dark', interp: 'hold', parent: 'mouth',
keys: state.inner.map((pts, f) => (state.hidden[f] ? { f, hidden: true } : { f, src: f, pts })) },
],
};
const text = writeTake(take)
+ `\n# plate drawings needed: ${kept.length} of ${N} frames\n`
+ kept.map((f, i) => {
const until = (i + 1 < kept.length ? kept[i + 1] : N) - 1;
return `# plate ${i} = source frame ${f}, holds f${f}..${until}`;
}).join('\n') + '\n';
const a = document.createElement('a');
a.href = URL.createObjectURL(new Blob([text], { type: 'text/plain' }));
a.download = `${take.name}.take`;
a.click();
status(`exported — ${kept.length} plate drawings, ${N} mouth frames`, 'ok');
}
/* ---------- wiring ---------- */
async function runFrames() {
try {
const man = await loadManifest();
if (man) {
state.fps = man.fps;
el('framedir').value = man.dir || 'frames';
attachAudio(man.audio);
} else {
attachAudio(null);
status('no manifest.json — assuming 12fps, no audio. Re-run extract.sh', 'warn');
}
const images = await loadFrameSequence();
if (!images.length) {
status(`no frames in ${el('framedir').value}/ — run extract.sh first`, 'err');
return;
}
const { dense, missing } = await detectAll(images);
state.images = images; state.dense = dense;
el('scrub').max = dense.length - 1;
state.frame = 0;
rebuild(true);
const dur = (dense.length / state.fps).toFixed(2);
status(`${images.length} frames · ${state.fps}fps · ${dur}s` +
(state.audio ? ' · audio loaded' : ' · no audio') +
(missing.length ? ` · no face on ${missing.length} (held previous)` : ''),
missing.length ? 'warn' : 'ok');
} catch (e) { status(e.message, 'err'); console.error(e); }
}
function runSynthetic() {
state.images = [];
attachAudio(null);
state.fps = 12;
state.dense = synthDense(72);
el('scrub').max = 71;
state.frame = 0;
rebuild(true);
status('synthetic — exercises everything below detection', 'ok');
}
for (const id of ['verts', 'smoothWin', 'contourSmooth', 'apertureThresh', 'tol']) {
el(id).addEventListener('input', () => {
el(id + 'v').textContent = id === 'apertureThresh' || id === 'tol'
? (+el(id).value / 1000).toFixed(3) : el(id).value;
if (id === 'tol') return; // tol only matters when you ask for a suggestion
rebuild(false);
});
el(id + 'v').textContent = el(id).value;
}
function seekTo(f) {
state.frame = f;
if (state.audio) state.audio.currentTime = f / state.fps;
el('scrub').value = f;
}
el('scrub').addEventListener('input', (e) => { seekTo(+e.target.value); drawAll(); });
el('btn-frames').onclick = runFrames;
el('btn-synth').onclick = runSynthetic;
el('btn-export').onclick = exportTake;
el('btn-keepall').onclick = () => { if (state.dense) { rebuild(true); } };
el('btn-suggest').onclick = () => {
if (!state.dense) return;
const kept = suggestPlateFrames(state.stab.rigid, opts().tol);
state.keep = new Set(kept);
drawAll();
status(`suggested ${kept.length} drawings at tolerance ${opts().tol.toFixed(3)} — now hand-correct`, 'ok');
};
el('btn-play').onclick = () => {
if (!state.dense) return;
state.playing = !state.playing;
el('btn-play').textContent = state.playing ? 'Stop' : 'Play';
if (state.playing) {
if (state.audio) {
state.audio.playbackRate = +el('speed').value;
// Restart from the top if we are sitting at the end.
if (state.frame >= state.dense.length - 1) state.frame = 0;
state.audio.currentTime = state.frame / state.fps;
state.audio.play().catch((e) => status('audio blocked: ' + e.message, 'warn'));
}
last = 0;
tick();
} else if (state.audio) {
state.audio.pause();
}
};
el('speed').addEventListener('change', () => {
// playbackRate retimes the clock, and the picture follows it for free.
if (state.audio) state.audio.playbackRate = +el('speed').value;
});
// Keyboard is the point: stepping and deleting 37 frames by mouse is miserable.
window.addEventListener('keydown', (e) => {
if (!state.dense || e.target.tagName === 'INPUT') return;
const N = state.dense.length;
if (e.key === 'ArrowRight') { seekTo(Math.min(N - 1, state.frame + 1)); drawAll(); }
else if (e.key === 'ArrowLeft') { seekTo(Math.max(0, state.frame - 1)); drawAll(); }
else if (e.key === 'Backspace' || e.key === 'Delete' || e.key === 'x') {
state.keep.delete(state.frame === 0 ? -1 : state.frame); drawAll();
} else if (e.key === 'k' || e.key === ' ') {
if (state.frame !== 0) state.keep.add(state.frame);
drawAll();
} else return;
e.preventDefault();
});
let last = 0;
function tick(ts = 0) {
if (!state.playing) return;
const N = state.dense.length;
let f;
if (state.audio) {
// Audio is the clock. Deriving the frame from currentTime rather than
// counting means a slow render loop drops frames instead of drifting out
// of sync, which is the behaviour you want when judging lip sync.
f = Math.floor(state.audio.currentTime * state.fps);
if (f >= N || state.audio.ended) {
state.audio.currentTime = 0;
state.audio.play().catch(() => {});
f = 0;
}
} else {
const rate = state.fps * +el('speed').value;
if (ts - last < 1000 / rate) { requestAnimationFrame(tick); return; }
last = ts;
f = (state.frame + 1) % N;
}
if (f !== state.frame) {
state.frame = f;
el('scrub').value = f;
drawPanes(); drawStrip();
}
requestAnimationFrame(tick);
}
PALETTE.forEach((p) => {
const sw = document.createElement('label');
sw.className = 'sw';
const inp = document.createElement('input');
inp.type = 'color'; inp.value = p.hex;
inp.oninput = () => { p.hex = inp.value; if (state.dense) drawAll(); };
sw.append(inp, document.createTextNode(p.name));
el('palette').append(sw);
});
// #synth / #frames autorun, so the tool can be driven headlessly for smoke tests
// and deep-linked. Detection needs WebGL; the synthetic path does not.
if (location.hash === '#synth') runSynthetic();
else if (location.hash === '#frames') runFrames();
else status('ready — Load frames, then step with \u2190 \u2192 and delete with X');
window.__roto = state; // headless smoke test reads this