Strand-based Hairstyle Generation via Large Reconstruction and Multimodal Models

2026-08-13

AI Summary

This study addresses the limitations of single-view hair strand generation, including manual dependency, poor generalization, and incompatibility with production pipelines. We propose a training-free automatic generation framework that integrates large reconstruction models, multimodal large language models, and classical geometric processing to directly output production-ready hair geometry from a single image without additional training. Experiments demonstrate that this pipeline can reconstruct complex hairstyles, such as ponytails, with high fidelity within minutes. By effectively overcoming existing generation bottlenecks and seamlessly integrating into digital human workflows, our approach significantly enhances both the automation efficiency and industrial applicability of hairstyle asset creation.

Abstract

Creating high-quality strand-based hairstyles in current production pipelines remains heavily dependent on skilled artists and time-consuming manual authoring, making it costly and difficult to scale. Existing learning-based methods have advanced image-driven hair reconstruction, but typically require large, diverse training datasets, struggle to generalize to complex styles such as buns and ponytails, and often operate in representations that are not directly compatible with strand-based modeling, editing, and simulation. We present a novel automatic pipeline that combines the capabilities of Large Reconstruction Models (LRMs), Large Multimodal Models (LMMs), and classical geometry processing to generate high-quality strand-based hairstyles from single-view images. Our approach produces detailed, production-ready strand geometry without task-specific training or data collection and can handle a wide variety of hairstyles, including straight and curly hair, short and long styles, and challenging structured configurations such as ponytails and buns. Across this diverse set of examples, our method generates visually compelling strand-level reconstructions within only a few minutes, making it well-suited for integration into modern digital human workflows.

Problem

• Strand-based Hairstyle Generation
• Hair Reconstruction
• Digital Human Workflows
• Generalization

Innovation

• Strand-based Hairstyle Generation
• Large Reconstruction Models
• Large Multimodal Models
• Single-view Reconstruction
• Zero-shot Generalization