As a classic statistical model of 3D facial shape and texture, 3D Morphable Model (3DMM) is widely used in facial analysis, including model fitting, image synthesis, etc. Conventional 3DMM is learned from a collection of wellcontrolled 2D face images with associated 3D face scans, and represented by two sets of PCA basis functions. Due to the type and amount of training data, as well as, the linear bases, the representation power of 3DMM can be limited. To address these problems, this paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of unconstrained face images, without collecting 3D face scans. Specifically, given a face image as input, a network encoder estimates the projection, shape and texture parameters. Two network decoders serve as the nonlinear 3DMM to map from the shape and texture parameters to the 3D shape and texture, respectively. With the projection parameter, 3D shape, and texture, a novel analyticallydifferentiable rendering layer is designed to reconstruct the original input face. The entire architecture is end-to-end trainable with only weak supervision. We demonstrate the superior representation power of our nonlinear 3DMM over its linear counterpart, and its contribution to face alignment and 3D face reconstruction.

Overview DR-GAN

Figure 1: Conventional 3DMM employs linear bases models for shape/texture, which are trained with 3D face scans and associated controlled 2D images. We propose a nonlinear 3DMM to model shape/texture via deep neural networks (DNNs). It can be trained from in-the-wild face images without 3D scans, and also better reconstruct the original images due to the model’s nonlinearity.

Demo

Nonlinear 3D Face Morphable Model Source Code

You can download the Nonlinear 3D Face Morphable Model Source Code from here.

Publications

  • On Learning 3D Face Morphable Model from In-the-wild Images
    Luan Tran, Xiaoming Liu
    IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 43, No. 1, pp.157-171, , Jun. 2019
    Bibtex | PDF | arXiv | Code
  • @article{ on-learning-3d-face-morphable-model-from-in-the-wild-images,
      author = { Luan Tran and Xiaoming Liu },
      title = { On Learning 3D Face Morphable Model from In-the-wild Images },
      journal = { IEEE Transactions on Pattern Analysis and Machine Intelligence },
      volume = { 43 },
      number = { 1 },
      month = { June },
      year = { 2019 },
      pages = { 157--171 },
    }
  • Towards High-fidelity Nonlinear 3D Face Morphable Model
    Luan Tran, Feng Liu, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, Jun. 2019
    Bibtex | PDF | arXiv | Poster | Code
  • @inproceedings{ towards-high-fidelity-nonlinear-3d-face-morphable-model,
      author = { Luan Tran and Feng Liu and Xiaoming Liu },
      title = { Towards High-fidelity Nonlinear 3D Face Morphable Model },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Long Beach, CA },
      month = { June },
      year = { 2019 },
    }
  • Nonlinear 3D Face Morphable Model
    Luan Tran, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, Jun. 2018 (Spotlight)
    Bibtex | PDF | arXiv | Poster | Code
  • @inproceedings{ nonlinear-3d-face-morphable-model,
      author = { Luan Tran and Xiaoming Liu },
      title = { Nonlinear 3D Face Morphable Model },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Salt Lake City, UT },
      month = { June },
      year = { 2018 },
    }