Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment

TL;DR

This paper introduces a pose-invariant hairstyle transfer model that leverages latent optimization and local style matching in StyleGAN2 to improve hairstyle transfer quality across different poses, especially with large pose differences.

Contribution

It proposes a novel latent optimization approach with local-style-matching loss for better pose-invariant hairstyle transfer, addressing limitations of previous models.

Findings

Enhanced transfer of hairstyles under large pose differences

Improved preservation of delicate hair textures

Outperforms previous methods in qualitative and quantitative evaluations

Abstract

Editing hairstyle is unique and challenging due to the complexity and delicacy of hairstyle. Although recent approaches significantly improved the hair details, these models often produce undesirable outputs when a pose of a source image is considerably different from that of a target hair image, limiting their real-world applications. HairFIT, a pose-invariant hairstyle transfer model, alleviates this limitation yet still shows unsatisfactory quality in preserving delicate hair textures. To solve these limitations, we propose a high-performing pose-invariant hairstyle transfer model equipped with latent optimization and a newly presented local-style-matching loss. In the StyleGAN2 latent space, we first explore a pose-aligned latent code of a target hair with the detailed textures preserved based on local style matching. Then, our model inpaints the occlusions of the source considering the aligned target hair and blends both images to produce a final output. The experimental results demonstrate that our model has strengths in transferring a hairstyle under larger pose differences and preserving local hairstyle textures.