MegaAvatar: Controllable Talking Avatar Generation
This report presents \textbf{MegaAvatar}, a controllable talking avatar generation framework built on top of the Wan2.2-TI2V-5B model. Compared with previous talking-avatar methods that mainly rely on audio or reference-image conditioning, we introduce additional SMPL-X-derived 3D guidance, enabling global control over body pose and head motion. Specifically, we render the driving SMPL-X sequence into dense mesh frames and encode them with a lightweight 3D convolutional encoder, whose outputs are injected into the latent tokens to provide overall motion control. Furthermore, we extend Wan2.2-TI2V-5B with additional audio and face cross-attention modules to enable fine-grained expression c...
| Authors | Junyao Gao, Sibo Liu, Weidong Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 30 September 2026 |
| Last updated at source | 30 September 2026 |
Connected in the knowledge graph
- Gaojunyao/MegaAvatarDataset · cited by
Models and datasets referencing this paper
- Gaojunyao/MegaAvatarDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.