Rowan, William, Huber, Patrik orcid.org/0000-0002-1474-1040, Pears, N. E. orcid.org/0000-0001-9513-5634 et al. (1 more author) (2023) Text2Face: 3D Morphable Faces from Text. In: International Conference on Learning Representations 2023:Proceedings. International Conference on Learning Representations, 01-05 May 2023 IEEE , RWA
Abstract
We present the first 3D morphable modelling approach, whereby 3D face shape can be directly and completely defined using a textual prompt. Building on work in multi-modal learning, we extend the FLAME head model to a common imageand-text latent space. This allows for direct 3D Morphable Model (3DMM) parameter generation and therefore shape manipulation from textual descriptions. Our method, Text2Face, has many applications; for example: generating police photofits where the input is already in natural language. It further enables multimodal 3DMM image fitting to sketches and sculptures, as well as images.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy. |
Keywords: | 3D morphable model,3D generative face model |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 25 Aug 2023 11:30 |
Last Modified: | 02 Apr 2025 23:34 |
Status: | Published |
Publisher: | IEEE |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:202737 |
Download
Filename: text2face_3d_morphable_faces.pdf
Description: text2face_3d_morphable_faces
Licence: CC-BY 2.5