SyncDreamer is presented, a unified diffusion Transformer framework that generates identity-preserving and emotionally expressive talking avatars from only a single image, speech audio, and text prompt, and an RL-based Cross-Modal Prompt Enhancer grounding textual cues in visual context for fine-grained motion con-trol.
Xemo-Talker is proposed, which first learns a neutral speech-to-motion mapping for stable articulation and lip synchronization, and then introduces a lightweight emotion branch guided by less-principal subspace supervision to enhance emotion control.
Chaolong Yang, Yinuo Guo, Kai Yao et al.· 0 citations
This work proposes AptAvatar, a 14B-parameter long-form audio-driven avatar generation framework that delivers fast and expressive inference, and introduces Endpoint-Anchored Distribution Distillation, a dedicated Anchor Score Estimator trained on the trajectory-endpoint distribution defined from a frozen pretrained 4-...
Hengyuan Zhang, Jing-Na Sun, Mei-Guang Jin et al.· arXiv.org· 1 citation
A self-distillation framework that leverages large-scale 2D talking videos to pre-train a specialized speech encoder that aligns speech representations with expressive visual dynamics, allowing the encoder to extract features highly correlated with facial and head motions directly from audio.
Jiu-Cheng Xie, Ji-Wang Zheng, Yongkang Xia et al.· 0 citations
CETalk is proposed, an audio-driven 3D facial animation framework conditioned on continuous Valence--Arousal (VA) representations for fine-grained emotion control that outperforms state-of-the-art methods in both lip-sync accuracy and emotional expressiveness, while enabling smooth and controllable emotion transitions.
Peng Jia, Li Dai, Zhen Xiao et al.· International Conference on...· 0 citations
STEER factorizes conversational behavior into explicit controls for gaze, head rhythm, and emotion, allowing users to steer how an avatar listens, reacts, and engages with a conversation partner, and embeds in a photorealistic avatar pipeline.
Kartik Teotia, Helge Rhodin, Hyeongwoo Kim et al.· arXiv.org· 1 citation
By releasing the compact 7B generator and 2K Refiner, this work seeks to democratize native audio-video generation and provide an accessible foundation for future research in unified audio-video generative modeling.
Jia-Shu Zhu, Yan-Hao Zheng, Rui Tian et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
