用草图精准控制头发丝生成，比文本图像更直观可控。
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
- 通过可学习的多尺度上采样，将3D发丝编码到不同层级的隐空间。
- 采用Transformer结构实现多尺度自适应条件控制，保证生成一致性。
- 支持用户草图引导，适合需要精细头发设计的影视与虚拟现实场景。
真实感头发丝生成在计算机图形学和虚拟现实等领域至关重要。尽管扩散模型能根据文本或图像生成发型，但这些输入缺乏精确性和易用性。为此，我们提出首个基于草图的发丝生成模型，既实现更精细的控制又保持用户友好。框架通过两项核心创新解决复杂发丝交互与多样草图模式建模难题：一是可学习的发丝上采样策略，将3D发丝编码至多尺度隐空间；二是基于Transformer与扩散头的多尺度自适应条件机制，确保跨粒度的一致性。在多个基准数据集上的实验表明，本方法在真实感与精度上均优于现有方法。定性结果进一步验证其有效性。代码将发布于[GitHub](https://github.com/fighting-Zhang/StrandDesigner)。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。