A 3D Morphable Model Learnt from 10,000 Faces

By James Booth, Anastasios Roussos, Stefanos P. Zafeiriou, Allan Ponniah, David J. Dunaway. 2016

393 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

A Hybrid Model for Identity Obfuscation by Face Replacement (2018, background): “Higher-quality models have been constructed using more scans [11], or by using information from in-the-wild images [12,13].”
A survey on face data augmentation for the training of deep neural networks (2019, background): “12 shows an example of 3DMM – LSFM [91], which was constructed from 9,663 distinct facial identities.”
Towards Fast, Accurate and Stable 3D Dense Face Alignment (2020, background): “, recognition [45,7,26,24,13,51], animation [10], avatar retargeting [9], tracking [50], attribute classification [4,22,21], image restoration [52,12,11], anti-spoofing [49,55,40,54,25].”
3D Face Morphable Models "In-the-Wild" (2017, methodology): “With the available 3D facial data, it is feasible to learn a powerful statistical model of the facial shape that generalises well for both identity and expression [14, 30, 13].”
3D Morphable Face Models—Past, Present, and Future (2019, neutral): “A recent study rebuilds such a model from a very large dataset containing 9,663 3D scans and revisits best practices [Booth et al. 2016], demonstrating that the originally proposed generator function for shape remains highly relevant in the research community.”
Metaverse: Perspectives from graphics, interactions and visualization (2022, background): “Reconstruction of the face is an important part, which is usually based on 3D Morphable Model (Booth et al., 2016) generated by Principal Component Analysis (PCA) algorithm, but the performance is limited by data quality, difficult to express facial details.”
paGAN (2018, neutral): “More recent techniques [Booth et al. 2017, 2016] are able to learn a linear face model of a neutral expression using around 10,000 scans.”
3D Face Reconstruction by Learning from Synthetic Data (2016, methodology): “r the interior of the mouth, while beards could be mistaken for parts of the background, as shown in Figure 12. Both problems can be solved by incorporating a richer model such as the one proposed in [4] and using better, and more accurate, rendering techniques. Figure 12: Limitations of the reconst”
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors (2023, background): “Direct supervision in the form of 3D shapes or keypoints is a robust way to impose such constraints for a particular domain, like human faces [5, 6], heads [42, 87], hands [61] or full bodies [48, 50].”
Photorealistic Facial Texture Inference Using Deep Neural Networks (2016, background): “Several extensions have been proposed leveraging internet images [24] and large-scale 3D facial scans [6].”
Nonlinear 3D Face Morphable Model (2018, background): “Such a small training set is far from adequate to describe the full variability of human faces [8].”
Multilinear Autoencoder for 3D Face Model Learning (2018, background): “These linear models are often called 3D morphable models (3DMM), and such models have recently been learned from large training sets [5] and with high-quality appearance information [9].”
GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction (2019, methodology): “Recently, large scale statistical models of face and head shape have been made publicly available [7, 10].”
FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (2020, background): “Existing 3D face datasets capture the face geometry us-ing sparse camera array[8, 19, 35] or active depth sensor such as Kinect[12] and coded light[34].”