HairPort: In-context 3D-aware Hair Import and Transfer for Images
Quick Answer
HairPort introduces a 3D-aware hairstyle transfer framework that enhances hairstyle transfer accuracy and consistency across varying poses and scales.
Quick Take
HairPort introduces a 3D-aware hairstyle transfer framework that enhances hairstyle transfer accuracy and consistency across varying poses and scales. Utilizing a Bald Converter and a new dataset of 6,000 images, it outperforms existing methods in both qualitative and quantitative metrics, making it ideal for applications in virtual try-on systems and augmented reality.
Key Points
- HairPort separates hair removal from transfer for improved results.
- Introduces Bald Converter for realistic bald face adaptations.
- New dataset, Baldy, contains 6,000 paired images for training.
- Supports large pose and scale discrepancies in hairstyle transfer.
- Outperforms existing methods in both qualitative and quantitative assessments.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 12562v1 Announce Type: new Abstract: Transferring hairstyles between images is an important but challenging task in computer graphics, computer vision, and visual effects. It enables users to explore new looks without physically altering their hair, with applications in virtual try-on systems, augmented reality, and entertainment.
Most prior works operate best under small pose gaps, and they fall short under large viewpoint and scale differences, where missing hair content must be synthesized rather than transferred. We propose HairPort, a 3D-aware hairstyle transfer framework that attempts to solve these issues by explicitly separating hair removal from transfer and enforcing geometric consistency before synthesis.
We introduce a Bald Converter, which produces realistic bald versions of faces through LoRA-based in-context adaptation of FLUX. 1 Kontext. To train our Bald Converter, we introduce a new dataset, Baldy, containing 6,000 paired bald and original images across diverse identities and conditions. We also use a 3D-Aware Transfer Pipeline that reconstructs and re-renders the reference hairstyle from the target viewpoint before compositing it onto the source image.
Being 3D aware, our method supports large pose and scale discrepancies between the source and target. Finally, a conditional flow-matching generator synthesizes the transferred result from the bald source and geometry-aligned reference guidance. Together, our method enables accurate, pose-consistent, and identity-preserving hairstyle transfer, outperforming existing methods both qualitatively and quantitatively.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.