Feature Disentanglement in GANs for Photorealistic Multi-view Hair Transfer

Simple item page
dc.contributor.authorXu, Jiayien_US
dc.contributor.authorWu, Zhengyangen_US
dc.contributor.authorZhang, Chenmingen_US
dc.contributor.authorJin, Xiaogangen_US
dc.contributor.authorJi, Yaohuaen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:02:14Z
dc.date.available2025-10-07T05:02:14Z
dc.date.issued2025
dc.description.abstractFast and highly realistic multi-view hair transfer plays a crucial role in evaluating the effectiveness of virtual hair try-on systems. However, GAN-based generation and editing methods face persistent challenges in feature disentanglement. Achieving pixel-level, attribute-specific modifications-such as changing hairstyle or hair color without affecting other facial features- remains a long-standing problem. To address this limitation, we propose a novel multi-view hair transfer framework that leverages a hair-only intermediate facial representation and a 3D-guided masking mechanism. Our approach disentangles triplane facial features into spatial geometric components and global style descriptors, enabling independent and precise control over hairstyle and hair color. By introducing a dedicated intermediate representation focused solely on hair and incorporating a two-stage feature fusion strategy guided by the generated 3D mask, our framework achieves fine-grained local editing across multiple viewpoints while preserving facial integrity and improving background consistency. Extensive experiments demonstrate that our method produces visually compelling and natural results in side-to-front view hair transfer tasks, offering a robust and flexible solution for high-fidelity hair reconstruction and manipulation.en_US
dc.description.number7
dc.description.sectionheadersDigital Human
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70245
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70245
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70245
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Computer graphics; Image manipulation; Image processing
dc.subjectComputing methodologies → Computer graphics
dc.subjectImage manipulation
dc.subjectImage processing
dc.titleFeature Disentanglement in GANs for Photorealistic Multi-view Hair Transferen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70245.pdf
Size:
8.86 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 7