ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2025)
Auto Hair Card Extraction for Smooth Hair with Differentiable Rendering
Zhongtian Zheng,
Tao Huang,
Haozhe Su,
Xueqi Ma,
Yuefan Shen,
Tongtong Wang,
Yin Yang,
Xifeng Gao,
Zherong Pan,
Kui Wu
Our automatic pipeline can convert a wide variety of strand-based hairstyles with 40K strands into hair card models using a small number of cards (bottom, depending on hairstyles) and 32 individual card textures, while preserving high visual fidelity. Here, we show the input strand model, our generated cards only, and cards rendered with textures.
Abstract
Hair cards remain a widely used representation for hair modeling in real-time applications, offering a practical trade-off between visual fidelity, memory usage, and performance. However, generating high-quality hair card models remains a challenging and labor-intensive task. This work presents an automated pipeline for converting strand-based hair models into hair card models with a limited number of cards and textures while preserving the hairstyle appearance. Our key idea is a novel differentiable representation where each strand is encoded as a projected 2D curve in the texture space, which enables end-to-end optimization with differentiable rendering while respecting the structures of the hair geometry. Based on this representation, we develop a novel algorithm pipeline, where we first cluster hair strands into initial hair cards and project the strands into the texture space. We then conduct a two-stage optimization, where our first stage optimizes the orientation of each hair card separately, and after strand projection, our second stage conducts joint optimization over the entire hair card model for fine-tuning. Our method is evaluated on a range of hairstyles, including straight, wavy, curly, and coily hair. To capture the appearance of short or coily hair, our method comes with support for hair caps and cross-card.
Paper [Preprint]
Video