PIFA implementation may be downloaded from here. The part of AFLW database used for training and testing can be found from here.

If you use PIFA code, please cite to the papers:

Publications

  • Pose-Invariant Face Alignment via CNN-based Dense 3D Model Fitting
    Amin Jourabloo, Xiaoming Liu
    International Journal of Computer Vision, , Apr. 2017 (in press)
    Bibtex | PDF | Project Webpage
  • @article{ pose-invariant-face-alignment-via-cnn-based-dense-3d-model-fitting,
      author = { Amin Jourabloo and Xiaoming Liu },
      title = { Pose-Invariant Face Alignment via CNN-based Dense 3D Model Fitting },
      booktitle = { International Journal of Computer Vision },
      month = { April },
      year = { 2017 },
    }
  • Large-pose Face Alignment via CNN-based Dense 3D Model Fitting
    Amin Jourabloo, Xiaoming Liu
    Proc. IEEE Computer Vision and Pattern Recogntion (CVPR 2016), Las Vegas, NV, Jun. 2016
    Bibtex | PDF | Poster | Project Webpage
  • @inproceedings{ large-pose-face-alignment-via-cnn-based-dense-3d-model-fitting,
      author = { Amin Jourabloo and Xiaoming Liu },
      title = { Large-pose Face Alignment via CNN-based Dense 3D Model Fitting },
      booktitle = { Proc. IEEE Computer Vision and Pattern Recogntion },
      address = { Las Vegas, NV },
      month = { June },
      year = { 2016 },
    }
  • Pose-Invariant 3D Face Alignment
    Amin Jourabloo, Xiaoming Liu
    Proc. International Conference on Computer Vision (ICCV 2015), Santiago, Chile, Dec. 2015
    Bibtex | PDF | Poster | Project Webpage
  • @inproceedings{ pose-invariant-3d-face-alignment,
      author = { Amin Jourabloo and Xiaoming Liu },
      title = { Pose-Invariant 3D Face Alignment },
      booktitle = { Proc. International Conference on Computer Vision },
      address = { Santiago, Chile },
      month = { December },
      year = { 2015 },
    }