# 3D Face Reconstruction with Geometry Details from a Single Image

arXiv: https://arxiv.org/abs/1702.05619 · HTML: https://mlsanity.com/paper/1702.05619/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2017.

## Built on by (most cited first, 27 of 27)

- [ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model](https://mlsanity.com/paper/2408.16767/) (2024)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [Text and Image Guided 3D Avatar Generation and Manipulation](https://mlsanity.com/paper/2202.06079/) (2022)
- [MonoNPHM: Dynamic Head Reconstruction from Monocular Videos](https://mlsanity.com/paper/2312.06740/) (2023)
- [Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction](https://mlsanity.com/paper/2105.07474/) (2021)
- [DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation](https://mlsanity.com/paper/2203.07931/) (2022)
- [Facial Geometric Detail Recovery via Implicit Representation](https://mlsanity.com/paper/2203.09692/) (2022)
- [HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details](https://mlsanity.com/paper/2303.11225/) (2023)
- [iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis](https://mlsanity.com/paper/2310.16167/) (2023)
- [S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image](https://mlsanity.com/paper/2203.07732/) (2022)
- [Prior-Guided Multi-View 3D Head Reconstruction](https://mlsanity.com/paper/2107.04277/) (2021)
- [DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows](https://mlsanity.com/paper/2304.09479/) (2023)
- [Continuously Controllable Facial Expression Editing in Talking Face Videos](https://mlsanity.com/paper/2209.08289/) (2022)
- [Deep Deformable 3D Caricatures with Learned Shape Control](https://mlsanity.com/paper/2207.14593/) (2022)
- [SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery](https://mlsanity.com/paper/2108.05465/) (2021)
- [ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment](https://mlsanity.com/paper/2203.15835/) (2022)
- [Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions](https://mlsanity.com/paper/2209.04436/) (2022)
- [RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs](https://mlsanity.com/paper/2302.05486/) (2023)
- [Deep Deformation Detail Synthesis for Thin Shell Models](https://mlsanity.com/paper/2102.11541/) (2021)
- [Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape](https://mlsanity.com/paper/2204.04379/) (2022)
- [Adaptive Joint Optimization for 3D Reconstruction with Differentiable Rendering](https://mlsanity.com/paper/2208.07003/) (2022)
- [TDMD: A Database for Dynamic Color Mesh Subjective and Objective Quality Explorations](https://mlsanity.com/paper/2308.01499/) (2023)
- [Structure-aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation](https://mlsanity.com/paper/2207.09019/) (2022)
- [AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction](https://mlsanity.com/paper/2304.13115/) (2023)
- [MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance](https://mlsanity.com/paper/2504.21497/) (2025)
- [Reasoning Structural Relation for Occlusion-Robust Facial Landmark Localization](https://mlsanity.com/paper/2112.10087/) (2021)
- [High-Quality Facial Albedo Generation for 3D Face Reconstruction from a Single Image using a Coarse-to-Fine Approach](https://mlsanity.com/paper/2506.13233/) (2025)

## Abstract (arXiv)

3D face reconstruction from a single image is a classical and challenging problem, with wide applications in many areas. Inspired by recent works in face animation from RGB-D or monocular video inputs, we develop a novel method for reconstructing 3D faces from unconstrained 2D images, using a coarse-to-fine optimization strategy. First, a smooth coarse 3D face is generated from an example-based bilinear face model, by aligning the projection of 3D face landmarks with 2D landmarks detected from the input image. Afterwards, using local corrective deformation fields, the coarse 3D face is refined using photometric consistency constraints, resulting in a medium face shape. Finally, a shape-from-shading method is applied on the medium face to recover fine geometric details. Our method outperforms state-of-the-art approaches in terms of accuracy and detail recovery, which is demonstrated in extensive experiments using real world models and publicly available datasets.