Papers for

virtual try-on app developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Hair strand models generated automatically from hair cards

HairCS: Reconstructing Strand-Based Hair from Hair Cards

Abstract: We present an automated pipeline that converts hair-card models into high-quality strand-based hairstyles. Given a collection of textured triangular or quad strips as input, our method produces a strand-based representation that preserves the original hairstyle while enriching it with fine-scale geometric detail and adhering to standard production requirements: strands originate from the scalp, roots are uniformly distributed, and the hair volume is plausibly filled. The resulting assets are directly compatible with strand-based rendering, physics-based simulation, and common grooming modifiers (e.g., clumping, curling, noise) for enhanced realism and artistic control. We validate our approach on a large and diverse set of hairstyles, including short and long hair, curly styles, and complex styles such as buns and ponytails.

Tue 15 SeptGraphicsComputer Vision and Pattern Recognition
The gist
Creating realistic hair for digital characters is tricky because it usually involves lots of detailed hair strands, which are hard to make by hand. The authors present a method that starts with a simpler 3D model made of flat pieces called hair cards and automatically turns them into detailed hair strands that look more natural. The new strands follow realistic rules, like starting on the scalp and filling the hair volume properly. This method works well on many different hairstyles, from short and curly to complex styles like buns and ponytails.
Open → 2609.16465v1