MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917013521170432 |
|---|---|
| author | Taubner, Felix Zhang, Ruihang Tuli, Mathieu Bahmani, Sherwin Lindell, David B. |
| author_facet | Taubner, Felix Zhang, Ruihang Tuli, Mathieu Bahmani, Sherwin Lindell, David B. |
| contents | Digital human avatars aim to simulate the dynamic appearance of humans in virtual environments, enabling immersive experiences across gaming, film, virtual reality, and more. However, the conventional process for creating and animating photorealistic human avatars is expensive and time-consuming, requiring large camera capture rigs and significant manual effort from professional 3D artists. With the advent of capable image and video generation models, recent methods enable automatic rendering of realistic animated avatars from a single casually captured reference image of a target subject. While these techniques significantly lower barriers to avatar creation and offer compelling realism, they lack constraints provided by multi-view information or an explicit 3D representation. So, image quality and realism degrade when rendered from viewpoints that deviate strongly from the reference image. Here, we build a video model that generates animatable multi-view videos of digital humans based on a single reference image and target expressions. Our model, MVP4D, is based on a state-of-the-art pre-trained video diffusion model and generates hundreds of frames simultaneously from viewpoints varying by up to 360 degrees around a target subject. We show how to distill the outputs of this model into a 4D avatar that can be rendered in real-time. Our approach significantly improves the realism, temporal consistency, and 3D consistency of generated avatars compared to previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12785 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars Taubner, Felix Zhang, Ruihang Tuli, Mathieu Bahmani, Sherwin Lindell, David B. Computer Vision and Pattern Recognition Artificial Intelligence Graphics Digital human avatars aim to simulate the dynamic appearance of humans in virtual environments, enabling immersive experiences across gaming, film, virtual reality, and more. However, the conventional process for creating and animating photorealistic human avatars is expensive and time-consuming, requiring large camera capture rigs and significant manual effort from professional 3D artists. With the advent of capable image and video generation models, recent methods enable automatic rendering of realistic animated avatars from a single casually captured reference image of a target subject. While these techniques significantly lower barriers to avatar creation and offer compelling realism, they lack constraints provided by multi-view information or an explicit 3D representation. So, image quality and realism degrade when rendered from viewpoints that deviate strongly from the reference image. Here, we build a video model that generates animatable multi-view videos of digital humans based on a single reference image and target expressions. Our model, MVP4D, is based on a state-of-the-art pre-trained video diffusion model and generates hundreds of frames simultaneously from viewpoints varying by up to 360 degrees around a target subject. We show how to distill the outputs of this model into a 4D avatar that can be rendered in real-time. Our approach significantly improves the realism, temporal consistency, and 3D consistency of generated avatars compared to previous methods. |
| title | MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2510.12785 |