# Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos

arXiv: https://arxiv.org/abs/2304.01436 · HTML: https://mlsanity.com/paper/2304.01436/

## Key facts

- Cited by 44 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 4 Apr 2023.

## 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)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [Few-Shot Adversarial Learning of Realistic Neural Talking Head Models](https://mlsanity.com/paper/1905.08233/) (2019)
- [3D Morphable Face Models -- Past, Present and Future](https://mlsanity.com/paper/1909.01815/) (2019)
- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [Animating Arbitrary Objects via Deep Motion Transfer](https://mlsanity.com/paper/1812.08861/) (2018)
- [Few-shot Video-to-Video Synthesis](https://mlsanity.com/paper/1910.12713/) (2019)
- [FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction](https://mlsanity.com/paper/2003.13989/) (2020)
- [X2Face: A network for controlling face generation by using images, audio, and pose codes](https://mlsanity.com/paper/1807.10550/) (2018)
- [NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing](https://mlsanity.com/paper/2207.11911/) (2022)
- [RigNeRF: Fully Controllable Neural 3D Portraits](https://mlsanity.com/paper/2206.06481/) (2022)
- [FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces](https://mlsanity.com/paper/1803.09179/) (2018)
- [Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars](https://mlsanity.com/paper/2008.10174/) (2020)
- [Structured Local Radiance Fields for Human Avatar Modeling](https://mlsanity.com/paper/2203.14478/) (2022)
- [Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control](https://mlsanity.com/paper/2106.02019/) (2021)
- [FML: Face Model Learning from Videos](https://mlsanity.com/paper/1812.07603/) (2018)
- [Detecting Deep-Fake Videos from Appearance and Behavior](https://mlsanity.com/paper/2004.14491/) (2020)
- [Learning Implicit Templates for Point-Based Clothed Human Modeling](https://mlsanity.com/paper/2207.06955/) (2022)

## Built on by (most cited first, 30 of 44)

- [SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting](https://mlsanity.com/paper/2403.05087/) (2024)
- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar](https://mlsanity.com/paper/2312.04558/) (2023)
- [GPAvatar: Generalizable and Precise Head Avatar from Image(s)](https://mlsanity.com/paper/2401.10215/) (2024)
- [Advances in 3D Generation: A Survey](https://mlsanity.com/paper/2401.17807/) (2024)
- [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)
- [LAM: Large Avatar Model for One-shot Animatable Gaussian Head](https://mlsanity.com/paper/2502.17796/) (2025)
- [MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing](https://mlsanity.com/paper/2404.19026/) (2024)
- [GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion](https://mlsanity.com/paper/2412.10209/) (2024)
- [VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment](https://mlsanity.com/paper/2312.04651/) (2023)
- [AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars](https://mlsanity.com/paper/2306.00547/) (2023)
- [RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars](https://mlsanity.com/paper/2503.12886/) (2025)
- [Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing](https://mlsanity.com/paper/2312.03763/) (2023)
- [Generalizable One-shot Neural Head Avatar](https://mlsanity.com/paper/2306.08768/) (2023)
- [BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesis](https://mlsanity.com/paper/2311.05521/) (2023)
- [VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence](https://mlsanity.com/paper/2405.16204/) (2024)
- [OHTA: One-shot Hand Avatar via Data-driven Implicit Priors](https://mlsanity.com/paper/2402.18969/) (2024)
- [Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatar](https://mlsanity.com/paper/2307.05000/) (2023)
- [GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar](https://mlsanity.com/paper/2311.13655/) (2023)
- [One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation](https://mlsanity.com/paper/2402.11909/) (2024)
- [GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image](https://mlsanity.com/paper/2404.02152/) (2024)
- [Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes](https://mlsanity.com/paper/2404.01543/) (2024)
- [HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars](https://mlsanity.com/paper/2507.19481/) (2025)
- [PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image](https://mlsanity.com/paper/2509.07552/) (2025)
- [GHOST 2.0: generative high-fidelity one shot transfer of heads](https://mlsanity.com/paper/2502.18417/) (2025)
- [MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space](https://mlsanity.com/paper/2404.01296/) (2024)
- [GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation](https://mlsanity.com/paper/2401.05750/) (2024)
- [PAV: Personalized Head Avatar from Unstructured Video Collection](https://mlsanity.com/paper/2407.21047/) (2024)
- [InteractAvatar: Modeling Hand-Face Interaction in Photorealistic Avatars with Deformable Gaussians](https://mlsanity.com/paper/2504.07949/) (2025)

## Abstract (arXiv)

We propose a method to learn a high-quality implicit 3D head avatar from a monocular RGB video captured in the wild. The learnt avatar is driven by a parametric face model to achieve user-controlled facial expressions and head poses. Our hybrid pipeline combines the geometry prior and dynamic tracking of a 3DMM with a neural radiance field to achieve fine-grained control and photorealism. To reduce over-smoothing and improve out-of-model expressions synthesis, we propose to predict local features anchored on the 3DMM geometry. These learnt features are driven by 3DMM deformation and interpolated in 3D space to yield the volumetric radiance at a designated query point. We further show that using a Convolutional Neural Network in the UV space is critical in incorporating spatial context and producing representative local features. Extensive experiments show that we are able to reconstruct high-quality avatars, with more accurate expression-dependent details, good generalization to out-of-training expressions, and quantitatively superior renderings compared to other state-of-the-art approaches.