| Title |
Motion-disentangled Diffusion Model for High-fidelity Talking Head Generation |
| Authors |
김세연(Se-yeon Kim) ; 박상헌(Seong-hyun Park) ; 김해문(Hae-moon Kim) ; 이태영(Tae-young Lee) ; 김승룡(Seung-ryong Kim) |
| DOI |
https://doi.org/10.5573/ieie.2024.61.11.92 |
| Keywords |
Talking head generation; Video generation; Diffusion based generative model |
| Abstract |
Conventional GAN-based models for talking head generation often suffer from limited quality and unstable training. Recent approaches based on diffusion models aim to address these limitations and improve fidelity. However, they still face challenges, including extensive sampling time and difficulties in maintaining temporal consistency due to the high stochasticity of diffusion models. To overcome these challenges, we propose a novel motion-disentangled diffusion model for high-quality talking head generation, dubbed MoDiTalker. We introduce two modules: the audio-to-motion (AToM), designed to generate synchronized lip motions from audio, and the motion-to-video (MToV), designed to produce high-quality talking head video following the generated motion. AToM excels in capturing subtle lip movements by leveraging an audio attention mechanism. In addition, MToV enhances temporal consistency by leveraging an efficient tri-plane representation. Our experiments conducted on standard benchmarks demonstrate that our model achieves superior performance compared to existing models. We also provide comprehensive ablation studies and user study results. |