TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints

TL;DR

TANGLED is a new method for generating realistic 3D hair strands from images, capable of handling diverse styles, viewpoints, and input views, using a diffusion framework conditioned on multi-view linearts.

Contribution

It introduces a three-step pipeline with a new dataset, a diffusion model conditioned on linearts, and a post-processing module for complex hairstyles, advancing 3D hair generation technology.

Findings

Achieves diverse and realistic 3D hair generation from various inputs.

Handles complex hairstyles with topological accuracy.

Enables applications in avatars, animation, and AR.

Abstract

Hairstyles are intricate and culturally significant with various geometries, textures, and structures. Existing text or image-guided generation methods fail to handle the richness and complexity of diverse styles. We present TANGLED, a novel approach for 3D hair strand generation that accommodates diverse image inputs across styles, viewpoints, and quantities of input views. TANGLED employs a three-step pipeline. First, our MultiHair Dataset provides 457 diverse hairstyles annotated with 74 attributes, emphasizing complex and culturally significant styles to improve model generalization. Second, we propose a diffusion framework conditioned on multi-view linearts that can capture topological cues (e.g., strand density and parting lines) while filtering out noise. By leveraging a latent diffusion model with cross-attention on lineart features, our method achieves flexible and robust 3D hair generation across diverse input conditions. Third, a parametric post-processing module enforces braid-specific constraints to maintain coherence in complex structures. This framework not only advances hairstyle realism and diversity but also enables culturally inclusive digital avatars and novel applications like sketch-based 3D strand editing for animation and augmented reality.