Multimodal Conditional 3D Face Geometry Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909764258103296 |
|---|---|
| author | Otto, Christopher Chandran, Prashanth Weiss, Sebastian Gross, Markus Zoss, Gaspard Bradley, Derek |
| author_facet | Otto, Christopher Chandran, Prashanth Weiss, Sebastian Gross, Markus Zoss, Gaspard Bradley, Derek |
| contents | We present a new method for multimodal conditional 3D face geometry generation that allows user-friendly control over the output identity and expression via a number of different conditioning signals. Within a single model, we demonstrate 3D faces generated from artistic sketches, portrait photos, Canny edges, FLAME face model parameters, 2D face landmarks, or text prompts. Our approach is based on a diffusion process that generates 3D geometry in a 2D parameterized UV domain. Geometry generation passes each conditioning signal through a set of cross-attention layers (IP-Adapter), one set for each user-defined conditioning signal. The result is an easy-to-use 3D face generation tool that produces topology-consistent, high-quality geometry with fine-grain user control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01074 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multimodal Conditional 3D Face Geometry Generation Otto, Christopher Chandran, Prashanth Weiss, Sebastian Gross, Markus Zoss, Gaspard Bradley, Derek Computer Vision and Pattern Recognition Graphics We present a new method for multimodal conditional 3D face geometry generation that allows user-friendly control over the output identity and expression via a number of different conditioning signals. Within a single model, we demonstrate 3D faces generated from artistic sketches, portrait photos, Canny edges, FLAME face model parameters, 2D face landmarks, or text prompts. Our approach is based on a diffusion process that generates 3D geometry in a 2D parameterized UV domain. Geometry generation passes each conditioning signal through a set of cross-attention layers (IP-Adapter), one set for each user-defined conditioning signal. The result is an easy-to-use 3D face generation tool that produces topology-consistent, high-quality geometry with fine-grain user control. |
| title | Multimodal Conditional 3D Face Geometry Generation |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2407.01074 |