Metraipolis › archive › dc_407b08674dce

CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation — arXiv:2608.15110

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15110
License (as archived)
CC0-1.0
Archived
2026-10-18T17:57:55.174Z
SHA-256 of the archived text
8153fd6f66b5de72d27e74aa0845f92234c5e2684b90eb0fb2c741066b81ee59
Stable URL of this page
https://metraipolis.com/documento/dc_407b08674dce

How to cite

CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation — arXiv:2608.15110 — arXiv (en), https://arxiv.org/abs/2608.15110 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_407b08674dce (Metraipolis archive dc_407b08674dce, sha256 8153fd6f66b5de72d27e74aa0845f92234c5e2684b90eb0fb2c741066b81ee59)
BibTeX
@misc{dc407b08674dce,
  title = {CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation — arXiv:2608.15110},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15110},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_407b08674dce; sha256 8153fd6f66b5de72d27e74aa0845f92234c5e2684b90eb0fb2c741066b81ee59},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15110. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Emotional 3D talking head generation aims to synthesize expressive facial animations with accurate lip synchronization. However, existing methods often rely on discrete emotion categories, which fail to capture the continuous evolution of affect. They also overlook the temporal frequency mismatch between audio articulation and emotional expression. In this paper, we propose CETalk, an audio-driven 3D facial animation framework conditioned on continuous Valence--Arousal (VA) representations for fine-grained emotion control. CETalk predicts a sequence of FLAME parameters through three key components: a Dynamic Emotion Modulation Module that adaptively scales emotional intensity using audio-derived cues; a Multi-Scale Temporal Modeling mechanism that employs parallel branches to decouple high-frequency articulatory movements from low-frequency emotional dynamics; and a Dynamic Fusion Mechanism that integrates these multi-scale features via an adaptive gating network. To support training and evaluation, we construct 3D-VA-MEAD, a large-scale dataset with automatically estimated VA annotations and reconstructed 3D facial motions. Extensive experiments demonstrate that CETalk outperforms state-of-the-art methods in both lip-sync accuracy and emotional expressiveness, while enabling smooth and controllable emotion transitions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15110 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.986Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).