Modeling Facial Geometry Using Compositional VAEs
By Timur M. Bagautdinov, Chenglei Wu, Jason M. Saragih, Pascal Fua, Yaser Sheikh. 2018
119 citations recorded by the source corpus.
We propose a method for learning non-linear face geometry representations using deep generative models. Our model is a variational autoencoder with multiple levels of hidden variables where lower layers capture global geometry and higher ones encode more local deformations. Based on that, we propose a new parameterization of facial geometry that naturally decomposes the structure of the human face into a set of semantically meaningful levels of detail. This parameterization enables us to do model fitting while capturing varying level of detail under different types of geometrical constraints.
Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Raquel Urtasun
- Luc Van Gool
- Xiaogang Wang
- Dacheng Tao
- Andreas Geiger
- Jitendra Malik
- Ming Liang
- Hongsheng Li
In Control and Systems Engineering
- Ming Liang
- Raquel Urtasun
- Mengye Ren
- Yaron Lipman
- Ruigang Yang
- Matan Atzmon
- Binh Yang
- Neil D. Lawrence
Citations in the corpus
- FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (2020, methodology): “Another direction is to enhance the representation power of 3DMM by using deep neural network to present 3DMM bases [2, 45, 48, 50, 49, 16].”
- 3D Morphable Face Models—Past, Present, and Future (2019, unknown): “Bagautdinov et al. [2018] introduced a VAE that models different levels of detail of facial geometry by representing”
- Physically Realizable Adversarial Examples for LiDAR Object Detection (2020, background): “Furthermore, meshes have previously demonstrated high-fidelity shape generation results on faces and human bodies [3, 22].”
- SAL: Sign Agnostic Learning of Shapes From Raw Data (2019, methodology): “[3] use variational auto-encoder with a constant mesh to learn parametrizations of faces shape space.”