Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Jongmin, Oh, Hyeontaek, Sun, Zhongtian, Aviles-Rivero, Angelica I, Jeon, Moongu, Yang, Jinhong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.16429
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914275115663360
author Yu, Jongmin
Oh, Hyeontaek
Sun, Zhongtian
Aviles-Rivero, Angelica I
Jeon, Moongu
Yang, Jinhong
author_facet Yu, Jongmin
Oh, Hyeontaek
Sun, Zhongtian
Aviles-Rivero, Angelica I
Jeon, Moongu
Yang, Jinhong
contents Existing face-swapping methods often deliver competitive results in constrained settings but exhibit substantial quality degradation when handling extreme facial poses. To improve facial pose robustness, explicit geometric features are applied, but this approach remains problematic since it introduces additional dependencies and increases computational cost. Diffusion-based methods have achieved remarkable results; however, they are impractical for real-time processing. We introduce AlphaFace, which leverages an open-source vision-language model and CLIP image and text embeddings to apply novel visual and textual semantic contrastive losses. AlphaFace enables stronger identity representation and more precise attribute preservation, all while maintaining real-time performance. Comprehensive experiments across FF++, MPIE, and LPFF demonstrate that AlphaFace surpasses state-of-the-art methods in pose-challenging cases. The project is publicly available on `https://github.com/andrewyu90/Alphaface_Official.git'.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16429
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AlphaFace: High Fidelity and Real-time Face Swapper Robust to Facial Pose
Yu, Jongmin
Oh, Hyeontaek
Sun, Zhongtian
Aviles-Rivero, Angelica I
Jeon, Moongu
Yang, Jinhong
Computer Vision and Pattern Recognition
Artificial Intelligence
Existing face-swapping methods often deliver competitive results in constrained settings but exhibit substantial quality degradation when handling extreme facial poses. To improve facial pose robustness, explicit geometric features are applied, but this approach remains problematic since it introduces additional dependencies and increases computational cost. Diffusion-based methods have achieved remarkable results; however, they are impractical for real-time processing. We introduce AlphaFace, which leverages an open-source vision-language model and CLIP image and text embeddings to apply novel visual and textual semantic contrastive losses. AlphaFace enables stronger identity representation and more precise attribute preservation, all while maintaining real-time performance. Comprehensive experiments across FF++, MPIE, and LPFF demonstrate that AlphaFace surpasses state-of-the-art methods in pose-challenging cases. The project is publicly available on `https://github.com/andrewyu90/Alphaface_Official.git'.
title AlphaFace: High Fidelity and Real-time Face Swapper Robust to Facial Pose
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.16429