Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
Abstract
With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to the limited control of audio signals in driving human motion, existing methods often add auxiliary spatial signals to stabilize movements, which may compromise the naturalness and freedom of motion. In this paper, we propose an end-to-end audio-only conditioned video diffusion model named Loopy. Specifically, we designed an inter- and intra-clip temporal module and an audio-to-latents module, enabling the model to leverage long-term motion information from the data to learn natural motion patterns and improving audio-portrait movement correlation. This method removes the need for manually specified spatial motion templates used in existing methods to constrain motion during inference. Extensive experiments show that Loopy outperforms recent audio-driven portrait diffusion models, delivering more lifelike and high-quality results across various scenarios.
Community
Incredible work 🚀 That is a real step forward!
hola compañeros! estamos evolucionando mucho en la inteligancia artificial, ya mismo podremos hacer deep fakes tan realistas que me da miedo el asunto
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention (2024)
- LinguaLinker: Audio-Driven Portraits Animation with Implicit Facial Control Enhancement (2024)
- EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions (2024)
- KMTalk: Speech-Driven 3D Facial Animation with Key Motion Embedding (2024)
- FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
"Nadie Pasa Sin Mi Permiso"Intro: "Nadie cruza mi territorio sin pagar el precio. Soy el guardián de
este imperio, y aquí mando yo."
you dont, they didnt release it for ethical reasons which is nonsense.
请问什么时候开源呢?
何时开源!!!!!!!迫不及待!!!!!!!!
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper