pith:NFHYJS42
MMTalker: Multiresolution 3D Talking Head Synthesis with Multimodal Feature Fusion
MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features.
arxiv:2604.02941 v2 · 2026-04-03 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NFHYJS42ST2NTUCPUZOEWLJOEA}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
MMTalker can accurately reconstruct the rich details of 3D facial motion and achieves significant improvements over state-of-the-art methods, especially in the synchronization accuracy of lip and eye movements.
That the combination of non-uniform differentiable sampling on UV-parameterized meshes and dual cross-attention fusion will resolve the ill-posed speech-to-3D-motion mapping without introducing artifacts or requiring extensive post-processing.
MMTalker combines multi-resolution mesh sampling with residual graph convolutions and dual cross-attention to synthesize accurate 3D talking head motions from audio.
Formal links
Receipt and verification
| First computed | 2026-06-02T01:04:16.215262Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
694f84cb9a94f4d9d04fa65c4b2d2e200e69030fa3eddad2fa4dd17e7654451b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 694f84cb9a94f4d9d04fa65c4b2d2e200e69030fa3eddad2fa4dd17e7654451b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "7ff1551469e95218086981257d5d647316731dc1b2b69fac3eb5fcd995f6d2b1",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-03T10:17:39Z",
"title_canon_sha256": "ae428a3e486aa52d15511d0ca7e4b51e935db6a5bf027e5ec89dc779a6f94065"
},
"schema_version": "1.0",
"source": {
"id": "2604.02941",
"kind": "arxiv",
"version": 2
}
}