Synthesizing Obama

@article{Suwajanakorn2017SynthesizingO,
  title={Synthesizing Obama},
  author={Supasorn Suwajanakorn and Steven M. Seitz and Ira Kemelmacher-Shlizerman},
  journal={ACM Transactions on Graphics (TOG)},
  year={2017},
  volume={36},
  pages={1 - 13}
}
  • Supasorn Suwajanakorn, Steven M. Seitz, Ira Kemelmacher-Shlizerman
  • Published 2017
  • Computer Science
  • ACM Transactions on Graphics (TOG)
  • Given audio of President Barack Obama, we synthesize a high quality video of him speaking with accurate lip sync, composited into a target video clip. Trained on many hours of his weekly address footage, a recurrent neural network learns the mapping from raw audio features to mouth shapes. Given the mouth shape at each time instant, we synthesize high quality mouth texture, and composite it with proper 3D pose matching to change what he appears to be saying in a target video to match the input… CONTINUE READING
    326 Citations
    ObamaNet: Photo-realistic lip-sync from text
    • 42
    • Highly Influenced
    • PDF
    Photorealistic Lip Sync with Adversarial Temporal Convolutional Networks
    • 2
    • Highly Influenced
    • PDF
    LumièreNet: Lecture Video Synthesis from Audio
    • 6
    • Highly Influenced
    • PDF
    Neural Voice Puppetry: Audio-driven Facial Reenactment
    • 26
    • Highly Influenced
    • PDF
    Speech-Driven Facial Reenactment Using Conditional Generative Adversarial Networks
    • 13
    • Highly Influenced
    • PDF
    You Said That?: Synthesising Talking Faces from Audio
    • 27
    • PDF
    HeadGAN: Video-and-Audio-Driven Talking Head Synthesis
    • PDF
    Robust One Shot Audio to Video Generation
    • 1
    • Highly Influenced
    • PDF
    Everybody's Talkin': Let Me Talk as You Want
    • 9
    • PDF

    References

    SHOWING 1-10 OF 10 REFERENCES
    A deep bidirectional LSTM approach for video-realistic talking head
    • 40
    • Highly Influential
    • PDF
    Synthesizing photo-real talking head via trajectory-guided sample selection
    • 45
    • Highly Influential
    • PDF
    Expressive Visual Text-to-Speech Using Active Appearance Models
    • 76
    • Highly Influential
    • PDF
    Video Rewrite: driving visual speech with audio
    • 677
    • Highly Influential
    • PDF
    Photo-real talking head with deep bidirectional LSTM
    • 76
    • Highly Influential
    • PDF
    Talking heads synthesis from audio with deep neural networks
    • 13
    • Highly Influential
    Face2Face: real-time face capture and reenactment of RGB videos
    • 573
    • Highly Influential
    • PDF
    An expressive text-driven 3D talking head
    • 7
    • Highly Influential
    • PDF
    Human-assisted motion annotation
    • 185
    • Highly Influential
    • PDF
    Je rey Dean, Ma hieu Devin, and others
    • Tensor ow: Large-scale machine learning on heterogeneous distributed systems
    • 2016