InstaFace: Identity-Preserving Facial Editing with Single Image Inference
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916645597872128 |
|---|---|
| author | Khan, MD Wahiduzzaman Jia, Mingshan Zhang, Xiaolin Yu, En Shan, Caifeng Musial-Gabrys, Kaska |
| author_facet | Khan, MD Wahiduzzaman Jia, Mingshan Zhang, Xiaolin Yu, En Shan, Caifeng Musial-Gabrys, Kaska |
| contents | Facial appearance editing is crucial for digital avatars, AR/VR, and personalized content creation, driving realistic user experiences. However, preserving identity with generative models is challenging, especially in scenarios with limited data availability. Traditional methods often require multiple images and still struggle with unnatural face shifts, inconsistent hair alignment, or excessive smoothing effects. To overcome these challenges, we introduce a novel diffusion-based framework, InstaFace, to generate realistic images while preserving identity using only a single image. Central to InstaFace, we introduce an efficient guidance network that harnesses 3D perspectives by integrating multiple 3DMM-based conditionals without introducing additional trainable parameters. Moreover, to ensure maximum identity retention as well as preservation of background, hair, and other contextual features like accessories, we introduce a novel module that utilizes feature embeddings from a facial recognition model and a pre-trained vision-language model. Quantitative evaluations demonstrate that our method outperforms several state-of-the-art approaches in terms of identity preservation, photorealism, and effective control of pose, expression, and lighting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20577 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InstaFace: Identity-Preserving Facial Editing with Single Image Inference Khan, MD Wahiduzzaman Jia, Mingshan Zhang, Xiaolin Yu, En Shan, Caifeng Musial-Gabrys, Kaska Computer Vision and Pattern Recognition Facial appearance editing is crucial for digital avatars, AR/VR, and personalized content creation, driving realistic user experiences. However, preserving identity with generative models is challenging, especially in scenarios with limited data availability. Traditional methods often require multiple images and still struggle with unnatural face shifts, inconsistent hair alignment, or excessive smoothing effects. To overcome these challenges, we introduce a novel diffusion-based framework, InstaFace, to generate realistic images while preserving identity using only a single image. Central to InstaFace, we introduce an efficient guidance network that harnesses 3D perspectives by integrating multiple 3DMM-based conditionals without introducing additional trainable parameters. Moreover, to ensure maximum identity retention as well as preservation of background, hair, and other contextual features like accessories, we introduce a novel module that utilizes feature embeddings from a facial recognition model and a pre-trained vision-language model. Quantitative evaluations demonstrate that our method outperforms several state-of-the-art approaches in terms of identity preservation, photorealism, and effective control of pose, expression, and lighting. |
| title | InstaFace: Identity-Preserving Facial Editing with Single Image Inference |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.20577 |