A diffusion-based hairstyle transfer method that uses a region-specific training loss to make cross-attention produce a source-aligned hair mask for pose-robust inpainting.
arXiv preprint arXiv:2304.13509 (2023)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Face segmentation for background removal systematically impacts both face recognition performance and morphing attack detection in unconstrained scenarios.
citing papers explorer
-
H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks
A diffusion-based hairstyle transfer method that uses a region-specific training loss to make cross-attention produce a source-aligned hair mask for pose-robust inpainting.
-
On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detection
Face segmentation for background removal systematically impacts both face recognition performance and morphing attack detection in unconstrained scenarios.