MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation

Kim et al. "MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I4.32452

[Kim et al. "MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/kim2025aaai-moditalker/) doi:10.1609/AAAI.V39I4.32452

@inproceedings{kim2025aaai-moditalker,
  title     = {{MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation}},
  author    = {Kim, Seyeon and Jin, Siyoon and Park, Jihye and Kim, Kihong and Kim, Jiyoung and Nam, Jisu and Kim, Seungryong},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {4302-4310},
  doi       = {10.1609/AAAI.V39I4.32452},
  url       = {https://mlanthology.org/aaai/2025/kim2025aaai-moditalker/}
}