Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913294663548928 |
|---|---|
| author | Chen, Xiyi Mihajlovic, Marko Wang, Shaofei Prokudin, Sergey Tang, Siyu |
| author_facet | Chen, Xiyi Mihajlovic, Marko Wang, Shaofei Prokudin, Sergey Tang, Siyu |
| contents | Recent advances in generative diffusion models have enabled the previously unfeasible capability of generating 3D assets from a single input image or a text prompt. In this work, we aim to enhance the quality and functionality of these models for the task of creating controllable, photorealistic human avatars. We achieve this by integrating a 3D morphable model into the state-of-the-art multi-view-consistent diffusion approach. We demonstrate that accurate conditioning of a generative pipeline on the articulated 3D model enhances the baseline model performance on the task of novel view synthesis from a single image. More importantly, this integration facilitates a seamless and accurate incorporation of facial expression and body pose control into the generation process. To the best of our knowledge, our proposed framework is the first diffusion model to enable the creation of fully 3D-consistent, animatable, and photorealistic human avatars from a single image of an unseen subject; extensive quantitative and qualitative evaluations demonstrate the advantages of our approach over existing state-of-the-art avatar creation models on both novel view and novel expression synthesis tasks. The code for our project is publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04728 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation Chen, Xiyi Mihajlovic, Marko Wang, Shaofei Prokudin, Sergey Tang, Siyu Computer Vision and Pattern Recognition Artificial Intelligence Recent advances in generative diffusion models have enabled the previously unfeasible capability of generating 3D assets from a single input image or a text prompt. In this work, we aim to enhance the quality and functionality of these models for the task of creating controllable, photorealistic human avatars. We achieve this by integrating a 3D morphable model into the state-of-the-art multi-view-consistent diffusion approach. We demonstrate that accurate conditioning of a generative pipeline on the articulated 3D model enhances the baseline model performance on the task of novel view synthesis from a single image. More importantly, this integration facilitates a seamless and accurate incorporation of facial expression and body pose control into the generation process. To the best of our knowledge, our proposed framework is the first diffusion model to enable the creation of fully 3D-consistent, animatable, and photorealistic human avatars from a single image of an unseen subject; extensive quantitative and qualitative evaluations demonstrate the advantages of our approach over existing state-of-the-art avatar creation models on both novel view and novel expression synthesis tasks. The code for our project is publicly available. |
| title | Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.04728 |