StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer
Our paper seeks to transfer the hairstyle of a reference image to an input photo for virtual hair try-on. We target a variety of challenges scenarios, such as transforming a long hairstyle with bangs to a pixie cut, which requires removing the existing hair and inferring how the forehead would look,...
Saved in:
Main Authors | , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
05.04.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Our paper seeks to transfer the hairstyle of a reference image to an input
photo for virtual hair try-on. We target a variety of challenges scenarios,
such as transforming a long hairstyle with bangs to a pixie cut, which requires
removing the existing hair and inferring how the forehead would look, or
transferring partially visible hair from a hat-wearing person in a different
pose. Past solutions leverage StyleGAN for hallucinating any missing parts and
producing a seamless face-hair composite through so-called GAN inversion or
projection. However, there remains a challenge in controlling the
hallucinations to accurately transfer hairstyle and preserve the face shape and
identity of the input. To overcome this, we propose a multi-view optimization
framework that uses "two different views" of reference composites to
semantically guide occluded or ambiguous regions. Our optimization shares
information between two poses, which allows us to produce high fidelity and
realistic results from incomplete references. Our framework produces
high-quality results and outperforms prior work in a user study that consists
of significantly more challenging hair transfer scenarios than previously
studied. Project page: https://stylegan-salon.github.io/. |
---|---|
DOI: | 10.48550/arxiv.2304.02744 |