A lineart-conditioned multi-view diffusion model generates 3D hair strands from arbitrary style images, supported by a new 457-hairstyle dataset and braid inpainting.
Autohair: Fully automatic hair modeling from a single image
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints
A lineart-conditioned multi-view diffusion model generates 3D hair strands from arbitrary style images, supported by a new 457-hairstyle dataset and braid inpainting.