# 3D Face Modeling From Diverse Raw Scan Data

arXiv: https://arxiv.org/abs/1902.04943 · HTML: https://mlsanity.com/paper/1902.04943/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2019.

## Built on by (most cited first, 25 of 25)

- [ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations](https://mlsanity.com/paper/2203.14510/) (2022)
- [Instant Multi-View Head Capture through Learnable Registration](https://mlsanity.com/paper/2306.07437/) (2023)
- [DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image](https://mlsanity.com/paper/2204.03688/) (2022)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [ScanTalk: 3D Talking Heads from Unregistered Scans](https://mlsanity.com/paper/2403.10942/) (2024)
- [Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image](https://mlsanity.com/paper/2111.03098/) (2021)
- [GANHead: Towards Generative Animatable Neural Head Avatars](https://mlsanity.com/paper/2304.03950/) (2023)
- [3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction](https://mlsanity.com/paper/2103.08204/) (2021)
- [Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction](https://mlsanity.com/paper/2104.00858/) (2021)
- [ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations](https://mlsanity.com/paper/2312.04028/) (2023)
- [Makeup Prior Models for 3D Facial Makeup Estimation and Applications](https://mlsanity.com/paper/2403.17761/) (2024)
- [FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategy](https://mlsanity.com/paper/2503.17197/) (2025)
- [Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures](https://mlsanity.com/paper/2306.15762/) (2023)
- [VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset](https://mlsanity.com/paper/2407.18245/) (2024)
- [INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields](https://mlsanity.com/paper/2312.16197/) (2023)
- [Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objects](https://mlsanity.com/paper/2212.14276/) (2022)
- [Towards Fine-grained 3D Face Dense Registration: An Optimal Dividing and Diffusing Method](https://mlsanity.com/paper/2109.11204/) (2021)
- [Learning to Deblur and Rotate Motion-Blurred Faces](https://mlsanity.com/paper/2112.07599/) (2021)
- [BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs](https://mlsanity.com/paper/2203.05908/) (2022)
- [3D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency Prior](https://mlsanity.com/paper/2404.16536/) (2024)
- [Feed-forward Gaussian Registration for Head Avatar Creation and Editing](https://mlsanity.com/paper/2603.15811/) (2026)
- [Representing 3D Faces with Learnable B-Spline Volumes](https://mlsanity.com/paper/2604.12894/) (2026)
- [Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence](https://mlsanity.com/paper/2605.01450/) (2026)
- [Improved Detection of Face Presentation Attacks Using Image Decomposition](https://mlsanity.com/paper/2103.12201/) (2021)
- [FreeTalk: Emotional Topology-Free 3D Talking Heads](https://mlsanity.com/paper/2603.15512/) (2026)

## Abstract (arXiv)

Traditional 3D face models learn a latent representation of faces using linear subspaces from limited scans of a single database. The main roadblock of building a large-scale face model from diverse 3D databases lies in the lack of dense correspondence among raw scans. To address these problems, this paper proposes an innovative framework to jointly learn a nonlinear face model from a diverse set of raw 3D scan databases and establish dense point-to-point correspondence among their scans. Specifically, by treating input scans as unorganized point clouds, we explore the use of PointNet architectures for converting point clouds to identity and expression feature representations, from which the decoder networks recover their 3D face shapes. Further, we propose a weakly supervised learning approach that does not require correspondence label for the scans. We demonstrate the superior dense correspondence and representation power of our proposed method, and its contribution to single-image 3D face reconstruction.