{"ID":2827170,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17717","arxiv_id":"2512.17717","title":"FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation","abstract":"We present FlexAvatar, a flexible large reconstruction model for high-fidelity 3D head avatars with detailed dynamic deformation from single or sparse images, without requiring camera poses or expression labels. It leverages a transformer-based reconstruction model with structured head query tokens as canonical anchor to aggregate flexible input-number-agnostic, camera-pose-free and expression-free inputs into a robust canonical 3D representation. For detailed dynamic deformation, we introduce a lightweight UNet decoder conditioned on UV-space position maps, which can produce detailed expression-dependent deformations in real time. To better capture rare but critical expressions like wrinkles and bared teeth, we also adopt a data distribution adjustment strategy during training to balance the distribution of these expressions in the training set. Moreover, a lightweight 10-second refinement can further enhances identity-specific details in extreme identities without affecting deformation quality. Extensive experiments demonstrate that our FlexAvatar achieves superior 3D consistency, detailed dynamic realism compared with previous methods, providing a practical solution for animatable 3D avatar creation.","short_abstract":"We present FlexAvatar, a flexible large reconstruction model for high-fidelity 3D head avatars with detailed dynamic deformation from single or sparse images, without requiring camera poses or expression labels. It leverages a transformer-based reconstruction model with structured head query tokens as canonical anchor...","url_abs":"https://arxiv.org/abs/2512.17717","url_pdf":"https://arxiv.org/pdf/2512.17717v1","authors":"[\"Cheng Peng\",\"Zhuo Su\",\"Liao Wang\",\"Chen Guo\",\"Zhaohu Li\",\"Chengjiang Long\",\"Zheng Lv\",\"Jingxiang Sun\",\"Chenyangguang Zhang\",\"Yebin Liu\"]","published":"2025-12-19T15:51:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}