StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

TL;DR

StrandDesigner introduces a novel sketch-based hair strand generation model that provides precise control and realism, leveraging multi-scale latent encoding and adaptive conditioning to outperform existing methods.

Contribution

The paper presents the first sketch-guided strand generation framework with a learnable upsampling strategy and multi-scale transformer conditioning, enhancing control and realism in hair modeling.

Findings

Outperforms existing methods in realism and precision

Effective modeling of complex strand interactions

Qualitative results confirm high-quality hair generation

Abstract

Realistic hair strand generation is crucial for applications like computer graphics and virtual reality. While diffusion models can generate hairstyles from text or images, these inputs lack precision and user-friendliness. Instead, we propose the first sketch-based strand generation model, which offers finer control while remaining user-friendly. Our framework tackles key challenges, such as modeling complex strand interactions and diverse sketch patterns, through two main innovations: a learnable strand upsampling strategy that encodes 3D strands into multi-scale latent spaces, and a multi-scale adaptive conditioning mechanism using a transformer with diffusion heads to ensure consistency across granularity levels. Experiments on several benchmark datasets show our method outperforms existing approaches in realism and precision. Qualitative results further confirm its effectiveness. Code will be released at [GitHub](https://github.com/fighting-Zhang/StrandDesigner).