# Deep 3D Portrait from a Single Image

arXiv: https://arxiv.org/abs/2004.11598 · HTML: https://mlsanity.com/paper/2004.11598/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2020.

## Built on by (most cited first, 30 of 38)

- [Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars](https://mlsanity.com/paper/2211.11208/) (2022)
- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization](https://mlsanity.com/paper/2211.15662/) (2022)
- [Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer](https://mlsanity.com/paper/2403.13570/) (2024)
- [Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data](https://mlsanity.com/paper/2311.18729/) (2023)
- [CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models](https://mlsanity.com/paper/2412.12093/) (2024)
- [AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars](https://mlsanity.com/paper/2210.06465/) (2022)
- [LAM: Large Avatar Model for One-shot Animatable Gaussian Head](https://mlsanity.com/paper/2502.17796/) (2025)
- [NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting](https://mlsanity.com/paper/2107.12351/) (2021)
- [HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field](https://mlsanity.com/paper/2309.17128/) (2023)
- [FaceController: Controllable Attribute Editing for Face in the Wild](https://mlsanity.com/paper/2102.11464/) (2021)
- [SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer](https://mlsanity.com/paper/2104.10567/) (2021)
- [3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation](https://mlsanity.com/paper/2209.05434/) (2022)
- [InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars](https://mlsanity.com/paper/2312.02222/) (2023)
- [Cross-Domain and Disentangled Face Manipulation with 3D Guidance](https://mlsanity.com/paper/2104.11228/) (2021)
- [AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections](https://mlsanity.com/paper/2309.02186/) (2023)
- [CorresNeRF: Image Correspondence Priors for Neural Radiance Fields](https://mlsanity.com/paper/2312.06642/) (2023)
- [VirtualCube: An Immersive 3D Video Communication System](https://mlsanity.com/paper/2112.06730/) (2021)
- [AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging](https://mlsanity.com/paper/2211.07818/) (2022)
- [Deep Face Video Inpainting via UV Mapping](https://mlsanity.com/paper/2109.00681/) (2021)
- [Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image](https://mlsanity.com/paper/2211.13901/) (2022)
- [HyperStyle3D: Text-Guided 3D Portrait Stylization via Hypernetworks](https://mlsanity.com/paper/2304.09463/) (2023)
- [SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface](https://mlsanity.com/paper/2403.18784/) (2024)
- [FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold](https://mlsanity.com/paper/2109.09378/) (2021)
- [Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions](https://mlsanity.com/paper/2209.04436/) (2022)
- [DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs](https://mlsanity.com/paper/2302.12253/) (2023)
- [AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning](https://mlsanity.com/paper/2303.14297/) (2023)
- [3D-Aware Adversarial Makeup Generation for Facial Privacy Protection](https://mlsanity.com/paper/2306.14640/) (2023)
- [FaceCraft4D: Animated 3D Facial Avatar Generation from a Single Image](https://mlsanity.com/paper/2504.15179/) (2025)
- [Implicit Neural Deformation for Sparse-View Face Reconstruction](https://mlsanity.com/paper/2112.02494/) (2021)

## Abstract (arXiv)

In this paper, we present a learning-based approach for recovering the 3D geometry of human head from a single portrait image. Our method is learned in an unsupervised manner without any ground-truth 3D data. We represent the head geometry with a parametric 3D face model together with a depth map for other head regions including hair and ear. A two-step geometry learning scheme is proposed to learn 3D head reconstruction from in-the-wild face images, where we first learn face shape on single images using self-reconstruction and then learn hair and ear geometry using pairs of images in a stereo-matching fashion. The second step is based on the output of the first to not only improve the accuracy but also ensure the consistency of overall head geometry. We evaluate the accuracy of our method both in 3D and with pose manipulation tasks on 2D images. We alter pose based on the recovered geometry and apply a refinement network trained with adversarial learning to ameliorate the reprojected images and translate them to the real image domain. Extensive evaluations and comparison with previous methods show that our new method can produce high-fidelity 3D head geometry and head pose manipulation results.