FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction

• URL: http://arxiv.org/abs/2605.15320v1
• Date: Thu, 14 May 2026 18:33:49 GMT
• Title: FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction
• Abstract summary: Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation.<n>We introduce FFAvatar, a generalizable feed-forward framework that reconstructs high-quality, animatable 3D Gaussian head avatars in seconds.
• Score: 15.685572282342891
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation or on expensive preprocessing that limits scalability. We introduce FFAvatar, a generalizable feed-forward framework that reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds. FFAvatar fuses information from multiple source images into a unified canonical Gaussian representation through Multi-View Query-Former, which is animated via FLAME parameters predicted end-to-end directly from pixels, eliminating the overhead of offline FLAME extraction. We further propose a three-stage training curriculum that achieves both broad generalization and high-fidelity reconstruction: (i) scalable pretraining on extensive monocular video data with over 1M identities to learn strong generalizable priors; (ii) multi-view fine-tuning on a small but high-quality dataset of 360-degree captures to enhance geometric fidelity and extreme-view awareness; and (iii) optional personalization that adapts to specific identities for maximum fidelity within 500 optimization steps. Extensive experiments demonstrate that FFAvatar sets a new standard for identity preservation, geometric consistency, and animation fidelity. On the NeRSemble benchmark, it outperforms the state-of-the-art LAM by a substantial 5.5 PSNR gain. Furthermore, FFAvatar enables real-time deployment, reconstructing avatars in 2 seconds without personalization and 10 seconds with personalization, while supporting 49 FPS animation on a single NVIDIA A100 GPU.

Related papers

• FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images [14.13683759834114]
  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.
  arXiv  Detail & Related papers  (2026-06-29T14:21:33Z)
• F3G-Avatar : Face Focused Full-body Gaussian Avatar [5.5263731799099425]
  F3G-Avatar is a full-body, face-aware avatar synthesis method.<n>It reconstructs animatable human representations from multi-view RGB video and regressed pose/shape parameters.<n>Experiments demonstrate strong rendering quality, with face-view performance reaching PSNR/SSIM/LPIPS of 26.243/0.964/0.084 on the AvatarReX dataset.
  arXiv  Detail & Related papers  (2026-04-10T19:08:46Z)
• 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)
• OMEGA-Avatar: One-shot Modeling of 360° Gaussian Avatars [54.688420347927725]
  OMEGA-Avatar is the first framework that simultaneously generates a generalizable, 360-complete, and animatable 3D Gaussian head from a single image.<n>We show that OMEGA-Avatar achieves state-of-the-art performance, significantly outperforming existing baselines in 360 full-head completeness.
  arXiv  Detail & Related papers  (2026-02-12T08:16:38Z)
• 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)
• Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling [32.480049588166544]
  Photo and animatable human avatars are a key enabler for virtual/augmented reality, telepresence, and digital entertainment.<n>We present the Parametric Gaussian Human Model (PGHM), a generalizable and efficient framework that integrates human priors into 3DGS.<n>Experiments show that PGHM is significantly more efficient than optimization-from-scratch methods, requiring only approximately 20 minutes per subject to produce avatars with comparable visual quality.
  arXiv  Detail & Related papers  (2025-06-07T03:53:30Z)
• FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images [74.86864398919467]
  We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images.<n>We learn a universal prior from over a thousand clothed humans to achieve instant feedforward generation and zero-shot generalization.<n>Our method generates more authentic reconstruction and animation than state-of-the-arts, and can be directly generalized to inputs from casually taken phone photos.
  arXiv  Detail & Related papers  (2025-03-24T23:20:47Z)
• Generalizable and Animatable Gaussian Head Avatar [50.34788590904843]
  We propose Generalizable and Animatable Gaussian head Avatar (GAGAvatar) for one-shot animatable head avatar reconstruction. We generate the parameters of 3D Gaussians from a single image in a single forward pass. Our method exhibits superior performance compared to previous methods in terms of reconstruction quality and expression accuracy.
  arXiv  Detail & Related papers  (2024-10-10T14:29:00Z)
• LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field [58.93692943064746]
  We introduce LightAvatar, the first head avatar model based on neural light fields (NeLFs) LightAvatar renders an image from 3DMM parameters and a camera pose via a single network forward pass, without using mesh or volume rendering.
  arXiv  Detail & Related papers  (2024-09-26T17:00:02Z)
• 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)
• OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering [81.55960827071661]
  Controllability, generalizability and efficiency are the major objectives of constructing face avatars represented by neural implicit field. We propose One-shot Talking face Avatar (OTAvatar), which constructs face avatars by a generalized controllable tri-plane rendering solution.
  arXiv  Detail & Related papers  (2023-03-26T09:12:03Z)

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.