GraphDeco

FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold
Presentation | Team members | Collaborations | Publications | Job offers | Contact

 

FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold

ACM Transactions on Graphics (SIGGRAPH Asia Conference Proceedings), Volume 40, Number 6 - dec 2021
Download the publication : freestylegan_paper.pdf [10.3Mo]   freestylegan_supplemental.pdf [3.3Mo]  
Current Generative Adversarial Networks (GANs) produce photorealistic renderings of portrait images. Embedding real images into the latent space of such models enables high-level image editing. While recent methods provide considerable semantic control over the (re-)generated images, they can only generate a limited set of viewpoints and cannot explicitly control the camera. Such 3D camera control is required for 3D virtual and mixed reality applications. In our solution, we use a few images of a face to perform 3D reconstruction, and we introduce the notion of the GAN camera manifold, the key element allowing us to precisely define the range of images that the GAN can reproduce in a stable manner. We train a small face-specific neural implicit representation network to map a captured face to this manifold and complement it with a warping scheme to obtain free-viewpoint novel-view synthesis. We show how our approach – due to its precise camera control – enables the integration of a pre-trained StyleGAN into standard 3D rendering pipelines, allowing e.g., stereo rendering or consistent insertion of faces in synthetic 3D environments. Our solution proposes the first truly free-viewpoint rendering of realistic faces at interactive rates, using only a small number of casual photos as input, while simultaneously allowing semantic editing capabilities, such as facial expression or lighting changes.

Images and movies

 

See also




See also the project webpage.

Acknowledgements and Funding

This research was funded in part by the ERC Advanced grant FUNGRAPH No 788065 (http://fungraph.inria.fr). The authors are grateful to the OPAL infrastructure from Université Côte d'Azur for providing resources and support. The authors thank Ayush Tewari, Ohad Fried, and Siddhant Prakash for help with comparisons, Adrien Bousseau, Ayush Tewari, Julien Philip, Miika Aittala, and Stavros Diolatzis for proofreading earlier drafts, the anonymous reviewers for their valuable feedback, and all participants who helped capture the face datasets.

BibTex references

@Article{LD21,
  author       = "Leimk{\"u}hler, Thomas and Drettakis, George",
  title        = "FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold",
  journal      = "ACM Transactions on Graphics (SIGGRAPH Asia Conference Proceedings)",
  number       = "6",
  volume       = "40",
  month        = "dec",
  year         = "2021",
  keywords     = "image-based rendering, neural networks, portrait rendering, camera models",
  url          = "http://www-sop.inria.fr/reves/Basilic/2021/LD21"
}

Other publications in the database

» Thomas Leimkühler
» George Drettakis