Skip to Main content Skip to Navigation
New interface
Journal articles

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

Thomas Leimkühler 1 George Drettakis 1 
1 GRAPHDECO - GRAPHics and DEsign with hEterogeneous COntent
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : 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 ś due to its precise camera control ś 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.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/hal-03342414
Contributor : Team Reves Connect in order to contact the contributor
Submitted on : Tuesday, September 28, 2021 - 2:13:55 PM
Last modification on : Friday, July 8, 2022 - 10:09:49 AM

File

paper_compressed_author.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Thomas Leimkühler, George Drettakis. FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold. ACM Transactions on Graphics, 2021, ⟨10.1145/3478513.3480538⟩. ⟨hal-03342414v2⟩

Share

Metrics

Record views

75

Files downloads

58