FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

• URL: http://arxiv.org/abs/2606.30347v1
• Date: Mon, 29 Jun 2026 14:21:33 GMT
• Title: FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
• Abstract summary: We present FFAvatar, a Transformer-based 3D Gaussian framework for fast construction of high-quality and animatable 4D head avatars.<n>We introduce a sparse-to-dense learning paradigm to balance visual fidelity and computational efficiency.<n>Experiments demonstrate that FFAvatar efficiently produces high-fidelity and controllable 4D head avatars.
• Score: 14.13683759834114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present FFAvatar, a Transformer-based 3D Gaussian framework for fast construction of high-quality and animatable 4D head avatars from one or more reference portrait images. Unlike existing feed-forward approaches that require a fixed number of input views, FFAvatar supports incremental reconstruction, progressively refining the avatar representation as additional reference images become available. At the core of our method is an alternating attention mechanism that disentangles identity appearance from expression and viewpoint variations, enabling the reconstruction of a canonical 3D appearance that remains consistent across poses and facial expressions. To balance visual fidelity and computational efficiency, we introduce a sparse-to-dense learning paradigm. Coarse appearance features are first learned using sparse primitives anchored to the FLAME vertex level and are subsequently densified in the UV domain to capture fine-grained geometric and texture details. We further propose a plug-and-play motion refinement module that enables subject-specific dynamic personalization by modeling residual motion beyond parametric deformation. Extensive experiments demonstrate that FFAvatar efficiently produces high-fidelity and controllable 4D head avatars, achieving superior flexibility, driving efficiency, and identity-consistent rendering across diverse expressions and viewpoints.

Related papers

• MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction [4.951907187079677]
  MeshLAM is a feed-forward framework for one-shot animatable mesh head reconstruction.<n>Our method produces complete mesh representations with inherent animatability from a single image in a single forward pass.
  arXiv  Detail & Related papers  (2026-04-23T09:01:27Z)
• FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures [13.76145751985277]
  We present FHAvatar, a novel framework for reconstructing 3D Gaussian avatars with composable face and hair components from an arbitrary number of views.<n>Experiments demonstrate that FHAvatar achieves state-of-the-art reconstruction quality from only a few observations of new identities within minutes.
  arXiv  Detail & Related papers  (2026-03-24T15:43:54Z)
• GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction [49.70452913749897]
  We propose a novel framework that leverages geometry-aware diffusion to learn strong geometry priors for high-fidelity head avatar reconstruction.<n>Our approach jointly synthesizes portrait images and corresponding surface normals, while a pose-free expression captures implicit expression representations.<n>Our method substantially outperforms state-of-the-art approaches in visual quality, expression fidelity, and cross-identity generalization.
  arXiv  Detail & Related papers  (2026-02-27T16:41:21Z)
• FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation [26.161556787983496]
  OURS is a feed-forward method to generate high-quality Gaussian head avatars from only a few input images.<n>Our approach directly learns a per-pixel Gaussian representation from the input images.<n>Experiments show that our approach significantly outperforms existing methods in both rendering quality and inference efficiency.
  arXiv  Detail & Related papers  (2026-01-20T10:49:49Z)
• InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting [64.42884719282323]
  InpaintHuman is a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos.<n>Our approach employs direct pixel-level supervision to ensure identity fidelity.
  arXiv  Detail & Related papers  (2026-01-05T13:26:02Z)
• FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation [52.919328336985636]
  We present FlexAvatar, a flexible large reconstruction model for high-fidelity 3D head avatars.<n>It aggregates flexible input-number-agnostic, camera-pose-free and expression-free inputs into a robust canonical 3D representation.<n>It achieves superior 3D consistency, detailed dynamic realism compared with previous methods.
  arXiv  Detail & Related papers  (2025-12-19T15:51:44Z)
• GPAvatar: Generalizable and Precise Head Avatar from Image(s) [71.555405205039]
  GPAvatar is a framework that reconstructs 3D head avatars from one or several images in a single forward pass. The proposed method achieves faithful identity reconstruction, precise expression control, and multi-view consistency.
  arXiv  Detail & Related papers  (2024-01-18T18:56:34Z)
• InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars [40.10906393484584]
  We propose a novel framework that enhances avatar reconstruction performance using an algorithm designed to increase the fidelity from multiple frames. Our architecture emphasizes pixel-aligned image-to-image translation, mitigating the need to learn correspondences between observation and canonical spaces. The proposed paradigm demonstrates state-of-the-art performance on one-shot and few-shot avatar animation tasks.
  arXiv  Detail & Related papers  (2023-12-03T18:59:15Z)
• Generalizable One-shot Neural Head Avatar [90.50492165284724]
  We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. We propose a framework that not only generalizes to unseen identities based on a single-view image, but also captures characteristic details within and beyond the face area.
  arXiv  Detail & Related papers  (2023-06-14T22:33:09Z)
• One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field [81.07651217942679]
  Talking head generation aims to generate faces that maintain the identity information of the source image and imitate the motion of the driving image. We propose HiDe-NeRF, which achieves high-fidelity and free-view talking-head synthesis.
  arXiv  Detail & Related papers  (2023-04-11T09:47:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.