StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer

by   Sasikarn Khwanmuang, et al.

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:


page 6

page 8

page 15

page 17

page 18

page 19

page 20

page 21


AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning

While substantial progresses have been made in automated 2D portrait sty...

Load Balanced GANs for Multi-view Face Image Synthesis

Multi-view face synthesis from a single image is an ill-posed problem an...

HairFIT: Pose-Invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-Region-Aware Inpainting

Hairstyle transfer is the task of modifying a source hairstyle to a targ...

Multi-view constrained clustering with an incomplete mapping between views

Multi-view learning algorithms typically assume a complete bipartite map...

Shape-aware Multi-Person Pose Estimation from Multi-View Images

In this paper we contribute a simple yet effective approach for estimati...

UMFuse: Unified Multi View Fusion for Human Editing applications

The vision community has explored numerous pose guided human editing met...

Please sign up or login with your details

Forgot password? Click here to reset