DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911255376166912 |
|---|---|
| author | Bondurant, Weston Sinha, Arkaprava Le, Hieu Das, Srijan Schuckers, Stephanie |
| author_facet | Bondurant, Weston Sinha, Arkaprava Le, Hieu Das, Srijan Schuckers, Stephanie |
| contents | Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based methods. However, even state-of-the-art models often suffer from fine-grained artifacts and poor identity preservation, particularly under challenging poses and expressions. A key limitation of existing approaches is their failure to meaningfully leverage 3D facial structure, which is crucial for disentangling identity from pose and expression. In this work, we propose DiffSwap++, a novel diffusion-based face-swapping pipeline that incorporates 3D facial latent features during training. By guiding the generation process with 3D-aware representations, our method enhances geometric consistency and improves the disentanglement of facial identity from appearance attributes. We further design a diffusion architecture that conditions the denoising process on both identity embeddings and facial landmarks, enabling high-fidelity and identity-preserving face swaps. Extensive experiments on CelebA, FFHQ, and CelebV-Text demonstrate that DiffSwap++ outperforms prior methods in preserving source identity while maintaining target pose and expression. Additionally, we introduce a biometric-style evaluation and conduct a user study to further validate the realism and effectiveness of our approach. Code will be made publicly available at https://github.com/WestonBond/DiffSwapPP |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05575 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping Bondurant, Weston Sinha, Arkaprava Le, Hieu Das, Srijan Schuckers, Stephanie Computer Vision and Pattern Recognition Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based methods. However, even state-of-the-art models often suffer from fine-grained artifacts and poor identity preservation, particularly under challenging poses and expressions. A key limitation of existing approaches is their failure to meaningfully leverage 3D facial structure, which is crucial for disentangling identity from pose and expression. In this work, we propose DiffSwap++, a novel diffusion-based face-swapping pipeline that incorporates 3D facial latent features during training. By guiding the generation process with 3D-aware representations, our method enhances geometric consistency and improves the disentanglement of facial identity from appearance attributes. We further design a diffusion architecture that conditions the denoising process on both identity embeddings and facial landmarks, enabling high-fidelity and identity-preserving face swaps. Extensive experiments on CelebA, FFHQ, and CelebV-Text demonstrate that DiffSwap++ outperforms prior methods in preserving source identity while maintaining target pose and expression. Additionally, we introduce a biometric-style evaluation and conduct a user study to further validate the realism and effectiveness of our approach. Code will be made publicly available at https://github.com/WestonBond/DiffSwapPP |
| title | DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.05575 |