{"ID":2859822,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04706","arxiv_id":"2510.04706","title":"ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion","abstract":"Human-centric generative models designed for AI-driven storytelling must bring together two core capabilities: identity consistency and precise control over human performance. While recent diffusion-based approaches have made significant progress in maintaining facial identity, achieving fine-grained expression control without compromising identity remains challenging. In this work, we present a diffusion-based framework that faithfully reimagines any subject under any particular facial expression. Building on an ID-consistent face foundation model, we adopt a compositional design featuring an expression cross-attention module guided by FLAME blendshape parameters for explicit control. Trained on a diverse mixture of image and video data rich in expressive variation, our adapter generalizes beyond basic emotions to subtle micro-expressions and expressive transitions, overlooked by prior works. In addition, a pluggable Reference Adapter enables expression editing in real images by transferring the appearance from a reference frame during synthesis. Extensive quantitative and qualitative evaluations show that our model outperforms existing methods in tailored and identity-consistent expression generation. Code and models can be found at https://github.com/foivospar/Arc2Face.","short_abstract":"Human-centric generative models designed for AI-driven storytelling must bring together two core capabilities: identity consistency and precise control over human performance. While recent diffusion-based approaches have made significant progress in maintaining facial identity, achieving fine-grained expression control...","url_abs":"https://arxiv.org/abs/2510.04706","url_pdf":"https://arxiv.org/pdf/2510.04706v1","authors":"[\"Foivos Paraperas Papantoniou\",\"Stefanos Zafeiriou\"]","published":"2025-10-06T11:20:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":608671,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2859822,"paper_url":"https://arxiv.org/abs/2510.04706","paper_title":"ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion","repo_url":"https://github.com/foivospar/Arc2Face","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}