# Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

arXiv: https://arxiv.org/abs/2502.20220 · HTML: https://mlsanity.com/paper/2502.20220/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 89 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 30 of 71)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack](https://mlsanity.com/paper/2309.15807/) (2023)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [StyleRig: Rigging StyleGAN for 3D Control over Portrait Images](https://mlsanity.com/paper/2004.00121/) (2020)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [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)
- [FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction](https://mlsanity.com/paper/2003.13989/) (2020)
- [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)
- [Real-Time High-Resolution Background Matting](https://mlsanity.com/paper/2012.07810/) (2020)
- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)

## Built on by (most cited first, 30 of 53)

- [Lyra 2.0: Explorable Generative 3D Worlds](https://mlsanity.com/paper/2604.13036/) (2026)
- [Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation](https://mlsanity.com/paper/2509.19296/) (2025)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [SEGA: Drivable 3D Gaussian Head Avatar from a Single Image](https://mlsanity.com/paper/2504.14373/) (2025)
- [FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision](https://mlsanity.com/paper/2512.15599/) (2025)
- [FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers](https://mlsanity.com/paper/2508.19754/) (2025)
- [PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image](https://mlsanity.com/paper/2509.07552/) (2025)
- [Audio-Driven Universal Gaussian Head Avatars](https://mlsanity.com/paper/2509.18924/) (2025)
- [HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis](https://mlsanity.com/paper/2509.16748/) (2025)
- [UIKA: Fast Universal Head Avatar from Pose-Free Images](https://mlsanity.com/paper/2601.07603/) (2026)
- [VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the Wild](https://mlsanity.com/paper/2511.20366/) (2025)
- [DeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representations](https://mlsanity.com/paper/2512.15524/) (2025)
- [FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation](https://mlsanity.com/paper/2601.13837/) (2026)
- [HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars](https://mlsanity.com/paper/2507.02803/) (2025)
- [VoluMe -- Authentic 3D Video Calls from Live Gaussian Splat Prediction](https://mlsanity.com/paper/2507.21311/) (2025)
- [Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer](https://mlsanity.com/paper/2512.00677/) (2025)
- [DGH: Dynamic Gaussian Hair](https://mlsanity.com/paper/2512.17094/) (2025)
- [FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation](https://mlsanity.com/paper/2512.17717/) (2025)
- [PhysHead: Simulation-Ready Gaussian Head Avatars](https://mlsanity.com/paper/2604.06467/) (2026)
- [HuGeDiff: 3D Human Generation via Diffusion with Gaussian Splatting](https://mlsanity.com/paper/2506.04351/) (2025)
- [VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis](https://mlsanity.com/paper/2507.06060/) (2025)
- [ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars](https://mlsanity.com/paper/2510.05488/) (2025)
- [Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image](https://mlsanity.com/paper/2512.17773/) (2025)
- [LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelines](https://mlsanity.com/paper/2601.12285/) (2026)
- [OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar](https://mlsanity.com/paper/2603.01506/) (2026)
- [Feed-forward Gaussian Registration for Head Avatar Creation and Editing](https://mlsanity.com/paper/2603.15811/) (2026)
- [AvatarPointillist: AutoRegressive 4D Gaussian Avatarization](https://mlsanity.com/paper/2604.04787/) (2026)
- [MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction](https://mlsanity.com/paper/2604.22865/) (2026)
- [Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures](https://mlsanity.com/paper/2605.04035/) (2026)
- [FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction](https://mlsanity.com/paper/2605.15320/) (2026)

## Abstract (arXiv)

Traditionally, creating photo-realistic 3D head avatars requires a studio-level multi-view capture setup and expensive optimization during test-time, limiting the use of digital human doubles to the VFX industry or offline renderings. To address this shortcoming, we present Avat3r, which regresses a high-quality and animatable 3D head avatar from just a few input images, vastly reducing compute requirements during inference. More specifically, we make Large Reconstruction Models animatable and learn a powerful prior over 3D human heads from a large multi-view video dataset. For better 3D head reconstructions, we employ position maps from DUSt3R and generalized feature maps from the human foundation model Sapiens. To animate the 3D head, our key discovery is that simple cross-attention to an expression code is already sufficient. Finally, we increase robustness by feeding input images with different expressions to our model during training, enabling the reconstruction of 3D head avatars from inconsistent inputs, e.g., an imperfect phone capture with accidental movement, or frames from a monocular video. We compare Avat3r with current state-of-the-art methods for few-input and single-input scenarios, and find that our method has a competitive advantage in both tasks. Finally, we demonstrate the wide applicability of our proposed model, creating 3D head avatars from images of different sources, smartphone captures, single images, and even out-of-domain inputs like antique busts. Project website: https://tobias-kirschstein.github.io/avat3r/