Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.14402 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915203723034624 |
|---|---|
| author | Li, Lisha Hou, Jingwen Liu, Weide Fang, Yuming Yan, Jiebin |
| author_facet | Li, Lisha Hou, Jingwen Liu, Weide Fang, Yuming Yan, Jiebin |
| contents | Facial Aesthetics Enhancement (FAE) aims to improve facial attractiveness by adjusting the structure and appearance of a facial image while preserving its identity as much as possible. Most existing methods adopted deep feature-based or score-based guidance for generation models to conduct FAE. Although these methods achieved promising results, they potentially produced excessively beautified results with lower identity consistency or insufficiently improved facial attractiveness. To enhance facial aesthetics with less loss of identity, we propose the Nearest Neighbor Structure Guidance based on Diffusion (NNSG-Diffusion), a diffusion-based FAE method that beautifies a 2D facial image with 3D structure guidance. Specifically, we propose to extract FAE guidance from a nearest neighbor reference face. To allow for less change of facial structures in the FAE process, a 3D face model is recovered by referring to both the matched 2D reference face and the 2D input face, so that the depth and contour guidance can be extracted from the 3D face model. Then the depth and contour clues can provide effective guidance to Stable Diffusion with ControlNet for FAE. Extensive experiments demonstrate that our method is superior to previous relevant methods in enhancing facial aesthetics while preserving facial identity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14402 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion-based Facial Aesthetics Enhancement with 3D Structure Guidance Li, Lisha Hou, Jingwen Liu, Weide Fang, Yuming Yan, Jiebin Computer Vision and Pattern Recognition Facial Aesthetics Enhancement (FAE) aims to improve facial attractiveness by adjusting the structure and appearance of a facial image while preserving its identity as much as possible. Most existing methods adopted deep feature-based or score-based guidance for generation models to conduct FAE. Although these methods achieved promising results, they potentially produced excessively beautified results with lower identity consistency or insufficiently improved facial attractiveness. To enhance facial aesthetics with less loss of identity, we propose the Nearest Neighbor Structure Guidance based on Diffusion (NNSG-Diffusion), a diffusion-based FAE method that beautifies a 2D facial image with 3D structure guidance. Specifically, we propose to extract FAE guidance from a nearest neighbor reference face. To allow for less change of facial structures in the FAE process, a 3D face model is recovered by referring to both the matched 2D reference face and the 2D input face, so that the depth and contour guidance can be extracted from the 3D face model. Then the depth and contour clues can provide effective guidance to Stable Diffusion with ControlNet for FAE. Extensive experiments demonstrate that our method is superior to previous relevant methods in enhancing facial aesthetics while preserving facial identity. |
| title | Diffusion-based Facial Aesthetics Enhancement with 3D Structure Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.14402 |