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

arXiv: https://arxiv.org/abs/2606.30347 · HTML: https://mlsanity.com/paper/2606.30347/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 63 of its 75 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 30 of 63)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Learning an Animatable Detailed 3D Face Model from In-The-Wild Images](https://mlsanity.com/paper/2012.04012/) (2020)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [StyleRig: Rigging StyleGAN for 3D Control over Portrait Images](https://mlsanity.com/paper/2004.00121/) (2020)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [EMOCA: Emotion Driven Monocular Face Capture and Animation](https://mlsanity.com/paper/2204.11312/) (2022)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [HeadNeRF: A Real-time NeRF-based Parametric Head Model](https://mlsanity.com/paper/2112.05637/) (2021)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [PointAvatar: Deformable Point-based Head Avatars from Videos](https://mlsanity.com/paper/2212.08377/) (2022)
- [VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://mlsanity.com/paper/2205.03409/) (2022)
- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)
- [CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models](https://mlsanity.com/paper/2411.18613/) (2024)
- [Instant Volumetric Head Avatars](https://mlsanity.com/paper/2211.12499/) (2022)
- [L4GM: Large 4D Gaussian Reconstruction Model](https://mlsanity.com/paper/2406.10324/) (2024)
- [MegaPortraits: One-shot Megapixel Neural Head Avatars](https://mlsanity.com/paper/2207.07621/) (2022)
- [Pixel Codec Avatars](https://mlsanity.com/paper/2104.04638/) (2021)
- [RigNeRF: Fully Controllable Neural 3D Portraits](https://mlsanity.com/paper/2206.06481/) (2022)
- [Realistic One-shot Mesh-based Head Avatars](https://mlsanity.com/paper/2206.08343/) (2022)
- [FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding](https://mlsanity.com/paper/2312.02214/) (2023)
- [HeadGAN: One-shot Neural Head Synthesis and Editing](https://mlsanity.com/paper/2012.08261/) (2020)
- [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025)

## Abstract (arXiv)

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.