# Learning Neural Parametric Head Models

arXiv: https://arxiv.org/abs/2212.02761 · HTML: https://mlsanity.com/paper/2212.02761/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 59 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://mlsanity.com/paper/2003.10983/) (2020)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes](https://mlsanity.com/paper/2104.03953/) (2021)
- [HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields](https://mlsanity.com/paper/2106.13228/) (2021)
- [FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction](https://mlsanity.com/paper/2003.13989/) (2020)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [TAVA: Template-free Animatable Volumetric Actors](https://mlsanity.com/paper/2206.08929/) (2022)
- [Nonlinear 3D Face Morphable Model](https://mlsanity.com/paper/1804.03786/) (2018)
- [Morphable Face Models - An Open Framework](https://mlsanity.com/paper/1709.08398/) (2017)
- [Structured Local Radiance Fields for Human Avatar Modeling](https://mlsanity.com/paper/2203.14478/) (2022)
- [i3DMM: Deep Implicit 3D Morphable Model of Human Heads](https://mlsanity.com/paper/2011.14143/) (2020)
- [Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control](https://mlsanity.com/paper/2106.02019/) (2021)
- [FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset](https://mlsanity.com/paper/2203.14057/) (2022)
- [Learning Formation of Physically-Based Face Attributes](https://mlsanity.com/paper/2004.03458/) (2020)
- [Towards High-fidelity Nonlinear 3D Face Morphable Model](https://mlsanity.com/paper/1904.04933/) (2019)
- [Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation](https://mlsanity.com/paper/1905.02876/) (2019)
- [NPMs: Neural Parametric Models for 3D Deformable Shapes](https://mlsanity.com/paper/2104.00702/) (2021)
- [SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator](https://mlsanity.com/paper/1911.05856/) (2019)
- [H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction](https://mlsanity.com/paper/2107.12512/) (2021)
- [Controlling Neural Level Sets](https://mlsanity.com/paper/1905.11911/) (2019)
- [gDNA: Towards Generative Detailed Neural Avatars](https://mlsanity.com/paper/2201.04123/) (2022)
- [ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations](https://mlsanity.com/paper/2203.14510/) (2022)

## Built on by (most cited first, 30 of 73)

- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Advances in 3D Generation: A Survey](https://mlsanity.com/paper/2401.17807/) (2024)
- [FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models](https://mlsanity.com/paper/2312.08459/) (2023)
- [CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models](https://mlsanity.com/paper/2412.12093/) (2024)
- [HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors](https://mlsanity.com/paper/2408.06019/) (2024)
- [Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction](https://mlsanity.com/paper/2306.05872/) (2023)
- [DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2311.18635/) (2023)
- [Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance](https://mlsanity.com/paper/2401.15687/) (2024)
- [GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion](https://mlsanity.com/paper/2412.10209/) (2024)
- [MonoNPHM: Dynamic Head Reconstruction from Monocular Videos](https://mlsanity.com/paper/2312.06740/) (2023)
- [Gaussian Eigen Models for Human Heads](https://mlsanity.com/paper/2407.04545/) (2024)
- [Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction](https://mlsanity.com/paper/2505.00615/) (2025)
- [MagicPose4D: Crafting Articulated Models with Appearance and Motion Control](https://mlsanity.com/paper/2405.14017/) (2024)
- [Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions](https://mlsanity.com/paper/2410.16395/) (2024)
- [PSAvatar: A Point-based Shape Model for Real-Time Head Avatar Animation with 3D Gaussian Splatting](https://mlsanity.com/paper/2401.12900/) (2024)
- [Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization](https://mlsanity.com/paper/2305.03043/) (2023)
- [SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars](https://mlsanity.com/paper/2410.11682/) (2024)
- [3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations](https://mlsanity.com/paper/2504.14967/) (2025)
- [What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs](https://mlsanity.com/paper/2401.02411/) (2024)
- [HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformation](https://mlsanity.com/paper/2403.09326/) (2024)
- [DPHMs: Diffusion Parametric Head Models for Depth-based Tracking](https://mlsanity.com/paper/2312.01068/) (2023)
- [ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations](https://mlsanity.com/paper/2312.04028/) (2023)
- [GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction](https://mlsanity.com/paper/2407.15070/) (2024)
- [Monocular and Generalizable Gaussian Talking Head Animation](https://mlsanity.com/paper/2504.00665/) (2025)
- [FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision](https://mlsanity.com/paper/2512.15599/) (2025)
- [Category-Agnostic Neural Object Rigging](https://mlsanity.com/paper/2505.20283/) (2025)
- [SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians](https://mlsanity.com/paper/2504.12292/) (2025)
- [PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling](https://mlsanity.com/paper/2506.20936/) (2025)
- [PhoMoH: Implicit Photorealistic 3D Models of Human Heads](https://mlsanity.com/paper/2212.07275/) (2022)

## Abstract (arXiv)

We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. At the core of our model lies a neural parametric representation that disentangles identity and expressions in disjoint latent spaces. To this end, we capture a person's identity in a canonical space as a signed distance field (SDF), and model facial expressions with a neural deformation field. In addition, our representation achieves high-fidelity local detail by introducing an ensemble of local fields centered around facial anchor points. To facilitate generalization, we train our model on a newly-captured dataset of over 5200 head scans from 255 different identities using a custom high-end 3D scanning setup. Our dataset significantly exceeds comparable existing datasets, both with respect to quality and completeness of geometry, averaging around 3.5M mesh faces per scan. Finally, we demonstrate that our approach outperforms state-of-the-art methods in terms of fitting error and reconstruction quality.