# NPGA: Neural Parametric Gaussian Avatars

arXiv: https://arxiv.org/abs/2405.19331 · HTML: https://mlsanity.com/paper/2405.19331/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 57 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 30 of 32)

- [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)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes](https://mlsanity.com/paper/2104.03953/) (2021)
- [Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://mlsanity.com/paper/2211.11610/) (2022)
- [HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields](https://mlsanity.com/paper/2106.13228/) (2021)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks](https://mlsanity.com/paper/2104.03313/) (2021)
- [HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling](https://mlsanity.com/paper/2301.02238/) (2023)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion](https://mlsanity.com/paper/2305.06356/) (2023)
- [RigNeRF: Fully Controllable Neural 3D Portraits](https://mlsanity.com/paper/2206.06481/) (2022)
- [i3DMM: Deep Implicit 3D Morphable Model of Human Heads](https://mlsanity.com/paper/2011.14143/) (2020)
- [FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset](https://mlsanity.com/paper/2203.14057/) (2022)
- [Multiface: A Dataset for Neural Face Rendering](https://mlsanity.com/paper/2207.11243/) (2022)
- [Fast-SNARF: A Fast Deformer for Articulated Neural Fields](https://mlsanity.com/paper/2211.15601/) (2022)
- [FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models](https://mlsanity.com/paper/2312.08459/) (2023)
- [LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar](https://mlsanity.com/paper/2305.01190/) (2023)
- [RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars](https://mlsanity.com/paper/2305.13353/) (2023)
- [HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field](https://mlsanity.com/paper/2309.17128/) (2023)

## Built on by (most cited first, 30 of 46)

- [Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2502.20220/) (2025)
- [HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors](https://mlsanity.com/paper/2408.06019/) (2024)
- [GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion](https://mlsanity.com/paper/2412.10209/) (2024)
- [HRAvatar: High-Quality and Relightable Gaussian Head Avatar](https://mlsanity.com/paper/2503.08224/) (2025)
- [SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars](https://mlsanity.com/paper/2410.11682/) (2024)
- [Synthetic Prior for Few-Shot Drivable Head Avatar Inversion](https://mlsanity.com/paper/2501.06903/) (2025)
- [3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations](https://mlsanity.com/paper/2504.14967/) (2025)
- [Articulated Kinematics Distillation from Video Diffusion Models](https://mlsanity.com/paper/2504.01204/) (2025)
- [ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions](https://mlsanity.com/paper/2507.10542/) (2025)
- [Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities](https://mlsanity.com/paper/2409.16147/) (2024)
- [SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians](https://mlsanity.com/paper/2504.12292/) (2025)
- [GASP: Gaussian Avatars with Synthetic Priors](https://mlsanity.com/paper/2412.07739/) (2024)
- [HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars](https://mlsanity.com/paper/2507.19481/) (2025)
- [FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses](https://mlsanity.com/paper/2508.18389/) (2025)
- [Audio-Driven Universal Gaussian Head Avatars](https://mlsanity.com/paper/2509.18924/) (2025)
- [BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading](https://mlsanity.com/paper/2506.06271/) (2025)
- [PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing](https://mlsanity.com/paper/2511.02777/) (2025)
- [GHOST 2.0: generative high-fidelity one shot transfer of heads](https://mlsanity.com/paper/2502.18417/) (2025)
- [TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling](https://mlsanity.com/paper/2505.05672/) (2025)
- [STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction](https://mlsanity.com/paper/2511.19854/) (2025)
- [FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation](https://mlsanity.com/paper/2601.13837/) (2026)
- [AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head Avatars](https://mlsanity.com/paper/2507.02419/) (2025)
- [AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars](https://mlsanity.com/paper/2512.06438/) (2025)
- [Text-based Animatable 3D Avatars with Morphable Model Alignment](https://mlsanity.com/paper/2504.15835/) (2025)
- [TexAvatars : Hybrid Texel-3D Representations for Stable Rigging of Photorealistic Gaussian Head Avatars](https://mlsanity.com/paper/2512.21099/) (2025)
- [PhysHead: Simulation-Ready Gaussian Head Avatars](https://mlsanity.com/paper/2604.06467/) (2026)
- [GNM Head: A Generative aNthropometric Model of the human head](https://mlsanity.com/paper/2607.23687/) (2026)
- [LightHeadEd: Relightable & Editable Head Avatars from a Smartphone](https://mlsanity.com/paper/2504.09671/) (2025)
- [AvatarBack: Back-Head Generation for Complete 3D Avatars from Front-View Images](https://mlsanity.com/paper/2508.20623/) (2025)
- [ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars](https://mlsanity.com/paper/2510.05488/) (2025)

## Abstract (arXiv)

The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives. Constructing such avatars is a challenging research problem, due to a high demand for photo-realism and real-time rendering performance. In this work, we propose Neural Parametric Gaussian Avatars (NPGA), a data-driven approach to create high-fidelity, controllable avatars from multi-view video recordings. We build our method around 3D Gaussian splatting for its highly efficient rendering and to inherit the topological flexibility of point clouds. In contrast to previous work, we condition our avatars' dynamics on the rich expression space of neural parametric head models (NPHM), instead of mesh-based 3DMMs. To this end, we distill the backward deformation field of our underlying NPHM into forward deformations which are compatible with rasterization-based rendering. All remaining fine-scale, expression-dependent details are learned from the multi-view videos. For increased representational capacity of our avatars, we propose per-Gaussian latent features that condition each primitives dynamic behavior. To regularize this increased dynamic expressivity, we propose Laplacian terms on the latent features and predicted dynamics. We evaluate our method on the public NeRSemble dataset, demonstrating that NPGA significantly outperforms the previous state-of-the-art avatars on the self-reenactment task by 2.6 PSNR. Furthermore, we demonstrate accurate animation capabilities from real-world monocular videos.