DR-GAN Frontalization Result

Luan Tran, Xi Yin, Xiaoming Liu

Keywords: Face Recognition, Face Reconstruction

DR-GAN face frontalization demo can be found here.

Source code is available here.

Tensorflow pre-trained model can be download here.

Frontalized faces and feature representations of faces from benchmark datasets may be downloaded at: CFP and IJB-A.

If you use these results, please cite to the papers:

Publications

  • Representation Learning by Rotating Your Faces
    Luan Tran, Xi Yin, Xiaoming Liu
    IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 41, No. 12, pp.3007-3021, , Sep. 2018
    Bibtex | PDF | arXiv | Project Webpage | Code
    • @article{ representation-learning-by-rotating-your-faces,
      author = { Luan Tran and Xi Yin and Xiaoming Liu },
      title = { Representation Learning by Rotating Your Faces },
      journal = { IEEE Transactions on Pattern Analysis and Machine Intelligence },
      volume = { 41 },
      number = { 12 },
      month = { September },
      year = { 2018 },
      pages = { 3007--3021 },
    }
  • Disentangled Representation Learning GAN for Pose-Invariant Face Recognition
    Luan Tran, Xi Yin, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, Jul. 2017 (Oral presentation)
    Bibtex | PDF | Project Webpage | Code
    • @inproceedings{ disentangled-representation-learning-gan-for-pose-invariant-face-recognition,
      author = { Luan Tran and Xi Yin and Xiaoming Liu },
      title = { Disentangled Representation Learning GAN for Pose-Invariant Face Recognition },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Honolulu, HI },
      month = { July },
      year = { 2017 },
    }