Your Name
d18791e6ad
Smoothing does not literally delay anything - a centred moving average has zero phase lag - but it blurs onsets, so the visually salient moment of a mouth opening moves later even though the mean does not. Animators also draw mouth shapes a frame or two ahead of the sound as standard practice, so this is the normal control rather than a workaround. Only the performance tracks shift; the head and audio stay put, since it is the mouth that should anticipate. In photo-underlay modes the vector mouth will therefore no longer match the frame behind it, which is expected. The lead is baked into the exported take - key f carries the pose from source frame f+lead - so the Animator Pro renderer never needs to know about it. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
765 lines
29 KiB
JavaScript
765 lines
29 KiB
JavaScript
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 { drawRegistered, posterizeInto } from './underlay.js';
|
||
import { extractTeeth } from './interior.js';
|
||
import { applySim } from './mathutil.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: 'teeth', hex: '#d9cfc2' },
|
||
];
|
||
const IDX = { bg: 0, base: 1, dark: 2, mouth: 3, teeth: 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
|
||
aspect: 1, // imgW/imgH; converts MediaPipe's anisotropic space
|
||
interior: null, // per-frame teeth measurement from image content
|
||
teeth: null, // resolved per-frame {show, t} after knobs
|
||
};
|
||
|
||
const el = (id) => {
|
||
const n = document.getElementById(id);
|
||
// A knob present in the code but missing from the markup used to throw during
|
||
// wiring and leave a blank page with nothing in the console worth reading.
|
||
if (!n) throw new Error(`missing element #${id} — knob wired in app.js but not in index.html`);
|
||
return n;
|
||
};
|
||
const opts = () => ({
|
||
verts: +el('verts').value,
|
||
lead: +el('lead').value,
|
||
teethOn: +el('teethOn').value / 100, // minimum Otsu class separation
|
||
teethDwell: +el('teethDwell').value,
|
||
teethSmooth: +el('teethSmooth').value,
|
||
cavityErode: +el('teethErode').value / 100,
|
||
tongueReject: +el('tongueReject').value / 100,
|
||
blobGrow: +el('blobGrow').value,
|
||
topBias: +el('topBias').value / 100,
|
||
verts: +el('teethVerts').value,
|
||
smoothWin: +el('smoothWin').value,
|
||
contourSmooth: +el('contourSmooth').value,
|
||
apertureThresh: +el('apertureThresh').value / 1000,
|
||
tol: +el('tol').value / 1000,
|
||
});
|
||
|
||
function status(msg, kind = '') {
|
||
el('status').textContent = msg;
|
||
el('status').className = kind;
|
||
}
|
||
|
||
/* ---------- loading ---------- */
|
||
|
||
const loadImage = (src) => new Promise((r) => {
|
||
const im = new Image();
|
||
im.onload = () => r(im); im.onerror = () => r(null); im.src = src;
|
||
});
|
||
|
||
// The extraction rate is read, not assumed. Guessing it would desynchronise
|
||
// audio from picture, which is the one thing this view exists to show.
|
||
async function loadManifest() {
|
||
try {
|
||
const r = await fetch('./manifest.json', { cache: 'no-store' });
|
||
if (!r.ok) return null;
|
||
return await r.json();
|
||
} catch { return null; }
|
||
}
|
||
|
||
function attachAudio(name) {
|
||
const a = el('audio');
|
||
if (!name) { a.removeAttribute('src'); a.hidden = true; state.audio = null; return; }
|
||
a.src = './' + name;
|
||
a.hidden = false;
|
||
state.audio = a;
|
||
}
|
||
|
||
async function loadFrameSequence() {
|
||
const dir = el('framedir').value.replace(/\/$/, '');
|
||
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 };
|
||
}
|
||
|
||
// Interior measurement is a function of pixels alone, so it runs once with
|
||
// detection and the knobs re-resolve it instantly afterwards.
|
||
function measureAll(images, dense, o) {
|
||
const ctx = document.createElement('canvas').getContext('2d', { willReadFrequently: true });
|
||
return dense.map((lm, i) =>
|
||
extractTeeth(images[i], LIPS_INNER.map((k) => lm[k]), ctx, o));
|
||
}
|
||
|
||
// Extraction keys on every knob that changes the pixels examined, so the cache
|
||
// is keyed on exactly those and a change to anything else stays instant.
|
||
const extractKey = (o) =>
|
||
[o.cavityErode, o.tongueReject, o.blobGrow, o.topBias, o.verts].join('|');
|
||
|
||
/* ---------- 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, state.aspect);
|
||
|
||
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);
|
||
|
||
if (state.images.length && state.extractKey !== extractKey(o)) {
|
||
state.interior = measureAll(state.images, state.dense, o);
|
||
state.extractKey = extractKey(o);
|
||
}
|
||
state.teeth = resolveTeeth(o);
|
||
|
||
// 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 };
|
||
});
|
||
}
|
||
|
||
// Presence gets hysteresis and a minimum dwell, the same treatment plate
|
||
// selection gets: a teeth block that blinks on and off for single frames is
|
||
// worse than one that is simply absent. Appearing needs a clear signal, staying
|
||
// needs only a weak one.
|
||
function resolveTeeth(o) {
|
||
const N = state.dense.length;
|
||
if (!state.interior) return new Array(N).fill({ show: false, pts: null });
|
||
|
||
const raw = state.interior.map((m, f) =>
|
||
(state.hidden[f] || !m.contour ? 0 : m.contrast));
|
||
const on = o.teethOn, off = o.teethOn * 0.7;
|
||
const shown = new Array(N).fill(false);
|
||
let live = false, since = 0;
|
||
for (let f = 0; f < N; f++) {
|
||
const want = live ? raw[f] > off : raw[f] > on;
|
||
if (want !== live && since >= o.teethDwell) { live = want; since = 0; }
|
||
else since++;
|
||
shown[f] = live && !state.hidden[f] && !!state.interior[f].contour;
|
||
}
|
||
|
||
// Into raster space through the same chain the lips take, including the
|
||
// isotropic aspect conversion - a contour in MediaPipe's normalised space is
|
||
// in the same stretched coordinates the landmarks are.
|
||
const toRaster = (pts, f) => {
|
||
const tf = state.stab.transforms[f];
|
||
return pts.map((p) => state.xform(applySim(tf, { x: p.x * state.aspect, y: p.y })));
|
||
};
|
||
const rast = state.interior.map((m, f) => (m.contour ? toRaster(m.contour, f) : null));
|
||
|
||
// Radial sampling makes vertex k mean the same direction on every frame, so
|
||
// smoothing across time is well defined and cannot reorder anything.
|
||
const sm = rast.map((pts, f) => {
|
||
if (!pts || !shown[f]) return pts;
|
||
const acc = pts.map(() => ({ x: 0, y: 0 }));
|
||
let c = 0;
|
||
for (let j = f - o.teethSmooth; j <= f + o.teethSmooth; j++) {
|
||
const k = Math.min(N - 1, Math.max(0, j));
|
||
if (!shown[k] || !rast[k] || rast[k].length !== pts.length) continue;
|
||
for (let v = 0; v < pts.length; v++) { acc[v].x += rast[k][v].x; acc[v].y += rast[k][v].y; }
|
||
c++;
|
||
}
|
||
return c ? acc.map((p) => ({ x: p.x / c, y: p.y / c })) : pts;
|
||
});
|
||
|
||
return shown.map((show, f) => ({ show, pts: sm[f] }));
|
||
}
|
||
|
||
/* ---------- render ---------- */
|
||
|
||
// The plate layer has several representations because its job changes: a flat
|
||
// shape to judge the mouth against, or a registered photograph to draw over.
|
||
// Only the latter is any use as reference art, and the generated oval is only a
|
||
// stand-in until a drawing exists.
|
||
function renderFrame(f, mode = plateMode()) {
|
||
const r = new IndexedRaster(RW, RH);
|
||
const pf = heldFrame(keptSorted(), f); // the plate frame on screen
|
||
|
||
if (mode === 'posterize' && state.images[pf]) {
|
||
posterizeInto(r, state.images[pf], state.stab.transforms[pf], state.xform,
|
||
PALETTE.map((p) => p.hex));
|
||
} else {
|
||
r.clear(IDX.bg);
|
||
if (mode === 'oval' || mode === 'oval+photo') r.fillPoly(state.plates[pf], IDX.base);
|
||
}
|
||
|
||
const mf = leadIndex(f); // performance frame, possibly ahead
|
||
r.fillPoly(state.outer[mf], IDX.dark); // mouth keeps every frame
|
||
if (!state.hidden[mf]) {
|
||
r.fillPoly(state.inner[mf], IDX.mouth);
|
||
const te = state.teeth[mf];
|
||
if (te.show && te.pts && te.pts.length >= 3) r.fillPoly(te.pts, IDX.teeth);
|
||
}
|
||
return r;
|
||
}
|
||
|
||
const plateMode = () => el('plateMode').value;
|
||
|
||
// Photo modes composite under the indexed layer, so the flat shapes stay exactly
|
||
// as they render while the reference sits behind them.
|
||
function compositeRender(canvas, f, zoom) {
|
||
const mode = plateMode();
|
||
const pf = heldFrame(keptSorted(), f);
|
||
const img = state.images[pf];
|
||
const showPhoto = img && (mode === 'photo' || mode === 'photo-dim' || mode === 'oval+photo');
|
||
|
||
canvas.width = RW * zoom; canvas.height = RH * zoom;
|
||
const g = canvas.getContext('2d');
|
||
g.fillStyle = PALETTE[IDX.bg].hex;
|
||
g.fillRect(0, 0, canvas.width, canvas.height);
|
||
|
||
if (showPhoto) {
|
||
drawRegistered(g, img, state.stab.transforms[pf], state.xform, zoom,
|
||
mode === 'photo-dim' ? 0.34 : 1);
|
||
}
|
||
|
||
const r = renderFrame(f, mode === 'oval+photo' ? 'oval' : (showPhoto ? 'off' : mode));
|
||
const img2 = r.toImageData(PALETTE.map((p) => p.hex), zoom);
|
||
if (showPhoto) {
|
||
// Keep the photo visible wherever the indexed layer is background.
|
||
const bg = PALETTE[IDX.bg].hex.replace('#', '');
|
||
const br = parseInt(bg.slice(0, 2), 16), bgn = parseInt(bg.slice(2, 4), 16), bb = parseInt(bg.slice(4, 6), 16);
|
||
const d = img2.data;
|
||
for (let i = 0; i < d.length; i += 4) {
|
||
if (d[i] === br && d[i + 1] === bgn && d[i + 2] === bb) d[i + 3] = 0;
|
||
}
|
||
const tmp = document.createElement('canvas');
|
||
tmp.width = img2.width; tmp.height = img2.height;
|
||
tmp.getContext('2d').putImageData(img2, 0, 0);
|
||
g.drawImage(tmp, 0, 0);
|
||
} else {
|
||
g.putImageData(img2, 0, 0);
|
||
}
|
||
}
|
||
|
||
const keptSorted = () => [...state.keep].sort((a, b) => a - b);
|
||
|
||
// Performance tracks can lead the clock.
|
||
//
|
||
// A centred moving average has no phase lag, so smoothing does not literally
|
||
// delay anything - but it blurs onsets, and the visually salient moment of a
|
||
// mouth opening moves later even though the mean does not. Animators also draw
|
||
// mouth shapes one or two frames ahead of the sound as a matter of course, so
|
||
// this is the normal control rather than a correction.
|
||
//
|
||
// Positive lead = the mouth arrives earlier. Only performance parts shift; the
|
||
// head stays with the audio, because it is the mouth that should anticipate.
|
||
function leadIndex(f) {
|
||
const N = state.dense.length;
|
||
return Math.min(N - 1, Math.max(0, f + opts().lead));
|
||
}
|
||
|
||
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);
|
||
const lead = opts().lead;
|
||
const teethFrames = state.teeth ? state.teeth.filter((t) => t.show).length : 0;
|
||
el('readout').textContent =
|
||
`${state.dense.length} frames → ${kept.length} drawings · ` +
|
||
`teeth on ${teethFrames}f · ` +
|
||
(lead ? `mouth leads ${lead}f (${(lead / state.fps * 1000).toFixed(0)}ms) · ` : '') +
|
||
`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);
|
||
const lead = opts().lead;
|
||
el('framelabel').textContent =
|
||
`f ${f} / ${state.dense.length - 1} · ${(f / state.fps).toFixed(2)}s · plate f${pf}` +
|
||
(lead ? ` · mouth f${leadIndex(f)} (${lead > 0 ? '+' : ''}${lead})` : '') +
|
||
(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 }));
|
||
const mf = leadIndex(f);
|
||
strokePts(g2, z(state.plates[pf]), '#3b4a63');
|
||
strokePts(g2, z(state.outer[mf]), '#4ade80');
|
||
if (!state.hidden[mf]) strokePts(g2, z(state.inner[mf]), '#f87171');
|
||
|
||
compositeRender(el('cv-render'), f, ZOOM);
|
||
drawInteriorDebug(f);
|
||
}
|
||
|
||
// What the teeth measurement actually saw: sampled region, pixels above
|
||
// threshold in green, the resolved line in amber. Recomputed for the current
|
||
// frame only, so it costs nothing to keep on screen.
|
||
function drawInteriorDebug(fRaw) {
|
||
const f = leadIndex(fRaw);
|
||
const host = el('cv-teeth');
|
||
const img = state.images[f];
|
||
if (!img || state.hidden[f]) {
|
||
host.innerHTML = '';
|
||
el('teethinfo').textContent = state.images.length ? 'mouth closed' : 'no source frames';
|
||
return;
|
||
}
|
||
const o = opts();
|
||
const ctx = document.createElement('canvas').getContext('2d', { willReadFrequently: true });
|
||
const m = extractTeeth(img, LIPS_INNER.map((k) => state.dense[f][k]), ctx, o, true);
|
||
host.innerHTML = '';
|
||
if (m.debug) {
|
||
m.debug.style.width = '170px';
|
||
m.debug.style.imageRendering = 'pixelated';
|
||
host.append(m.debug);
|
||
}
|
||
const te = state.teeth[f];
|
||
el('teethinfo').textContent =
|
||
`contrast ${m.contrast.toFixed(3)} / gate ${o.teethOn.toFixed(2)} · ` +
|
||
`area ${m.area}px · ${te.show ? 'SHOWN' : 'hidden'}`;
|
||
}
|
||
|
||
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';
|
||
// Registered, not raw-cropped: the worksheet frame is in raster space, so a
|
||
// drawing traced from it is already aligned to the mouth.
|
||
const cv = document.createElement('canvas');
|
||
compositeRender(cv, f, 1);
|
||
cv.style.width = '176px';
|
||
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. The lead is baked in here -
|
||
// key f carries the pose from source frame f+lead - so the renderer never
|
||
// needs to know about it.
|
||
{ name: 'mouth', kind: 'poly', z: 30, color: 'skin_dark', interp: 'hold',
|
||
keys: state.outer.map((_, f) => ({ f, src: leadIndex(f), pts: state.outer[leadIndex(f)] })) },
|
||
{ name: 'mouth_in', kind: 'poly', z: 31, color: 'mouth_dark', interp: 'hold', parent: 'mouth',
|
||
keys: state.inner.map((_, f) => {
|
||
const m = leadIndex(f);
|
||
return state.hidden[m] ? { f, hidden: true } : { f, src: m, pts: state.inner[m] };
|
||
}) },
|
||
{ name: 'teeth', kind: 'poly', z: 32, color: 'teeth', interp: 'hold', parent: 'mouth_in',
|
||
keys: state.teeth.map((_, f) => {
|
||
const m = leadIndex(f), te = state.teeth[m];
|
||
return te.show && te.pts ? { f, src: m, pts: te.pts } : { f, hidden: true };
|
||
}) },
|
||
],
|
||
};
|
||
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 ${el('framedir').value}/ — run extract.sh first`, 'err');
|
||
return;
|
||
}
|
||
const { dense, missing } = await detectAll(images);
|
||
state.images = images; state.dense = dense;
|
||
state.aspect = images[0].naturalWidth / images[0].naturalHeight;
|
||
status('measuring mouth interiors…');
|
||
state.interior = measureAll(images, dense, opts());
|
||
el('scrub').max = dense.length - 1;
|
||
state.frame = 0;
|
||
rebuild(true);
|
||
const dur = (dense.length / state.fps).toFixed(2);
|
||
status(`${images.length} frames · ${images[0].naturalWidth}x${images[0].naturalHeight} · ` +
|
||
`${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.aspect = 1; // synthetic landmarks are generated square
|
||
state.interior = null; // no pixels, so no teeth
|
||
|
||
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',
|
||
'teethOn', 'teethDwell', 'teethErode', 'tongueReject', 'blobGrow',
|
||
'topBias', 'teethVerts', 'teethSmooth', 'lead']) {
|
||
el(id).addEventListener('input', () => {
|
||
el(id + 'v').textContent = id === 'apertureThresh' || id === 'tol'
|
||
? (+el(id).value / 1000).toFixed(3)
|
||
: ['teethOn', 'teethErode', 'tongueReject', 'topBias'].includes(id)
|
||
? (+el(id).value / 100).toFixed(2)
|
||
: 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('plateMode').addEventListener('change', () => { if (state.dense) drawAll(); });
|
||
el('btn-saveframe').onclick = () => {
|
||
if (!state.dense) return;
|
||
const cv = document.createElement('canvas');
|
||
compositeRender(cv, state.frame, 4); // 1280x800: enough to draw on
|
||
const a = document.createElement('a');
|
||
a.href = cv.toDataURL('image/png');
|
||
a.download = `${el('takename').value || 'take'}_f${String(state.frame).padStart(4, '0')}.png`;
|
||
a.click();
|
||
status(`saved registered frame f${state.frame} at 4x`, 'ok');
|
||
};
|
||
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 === '[' || e.key === ']') {
|
||
const n = el('lead');
|
||
n.value = Math.max(+n.min, Math.min(+n.max, +n.value + (e.key === ']' ? 1 : -1)));
|
||
el('leadv').textContent = n.value;
|
||
drawAll();
|
||
} else if (e.key === 'b') {
|
||
const sel = el('plateMode');
|
||
sel.selectedIndex = (sel.selectedIndex + 1) % sel.options.length;
|
||
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.
|
||
window.addEventListener('error', (e) => {
|
||
const s = document.getElementById('status');
|
||
if (s) { s.textContent = e.message; s.className = 'err'; }
|
||
});
|
||
|
||
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
|