{"ID":2846359,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.05575","arxiv_id":"2511.05575","title":"DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping","abstract":"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","short_abstract":"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 k...","url_abs":"https://arxiv.org/abs/2511.05575","url_pdf":"https://arxiv.org/pdf/2511.05575v1","authors":"[\"Weston Bondurant\",\"Arkaprava Sinha\",\"Hieu Le\",\"Srijan Das\",\"Stephanie Schuckers\"]","published":"2025-11-04T18:56:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":607430,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2846359,"paper_url":"https://arxiv.org/abs/2511.05575","paper_title":"DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping","repo_url":"https://github.com/WestonBond/DiffSwapPP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}