2022/08/16 by Taewoo Kim, Kim, Taewoo, Chaeyeon Chung +9 · 3 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image Enhancement Techniques #cs.CV
paper · pdf · doi:10.48550/arxiv.2208.07765
Accepted to ECCV 2022
arxiv created 2022/08/16 · openalex publication_date 2022/08/16 · arxiv updated 2022/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.