GroomGen:
A High-Quality Generative Hair Model Using Hierarchical Latent Representations

Yuxiao Zhou1, Menglei Chai2, Alessandro Pepe2, Markus Gross1, Thabo Beeler2
1ETH Zurich, 2Google

SIGGRAPH Asia 2023 (ACM Transactions on Graphics)


Abstract

Despite recent successes in hair acquisition that fits a high-dimensional hair model to a specific input subject, generative hair models, which establish general embedding spaces for encoding, editing, and sampling diverse hairstyles, are way less explored. In this paper, we present GroomGen, the first generative model designed for hair geometry composed of highly-detailed dense strands. Our approach is motivated by two key ideas. First, we construct hair latent spaces covering both individual strands and hairstyles. The latent spaces are compact, expressive, and well-constrained for high-quality and diverse sampling. Second, we adopt a hierarchical hair representation that parameterizes a complete hair model to three levels: single strands, sparse guide hairs, and complete dense hairs. This representation is critical to the compactness of latent spaces, the robustness of training, and the efficiency of inference. Based on this hierarchical latent representation, our proposed pipeline consists of a strand-VAE and a hairstyle-VAE that encode an individual strand and a set of guide hairs to their respective latent spaces, a hybrid densification step that populates sparse guide hairs to a dense hair model, and a neural simulator that deforms hair driven by head pose. GroomGen not only enables novel hairstyle sampling and plausible hairstyle interpolation, but could also enable interactive editing of complex hairstyles, or serve as strong data-driven prior for hairstyle reconstruction from images. We demonstrate the superiority of our approach with qualitative examples of diverse sampled hairstyles and quantitative evaluation of generation quality regarding every single component and the entire pipeline.

Diverse Hairstyle Generation

Dense strands generation results

Sparse guide hairs generation results


Pipeline and Scalp Parameterization


Evalutaion of Strand-VAE and Hairstyle-VAE

Reconstruction results of strand-VAE

Reconstruction results of hairstyle-VAE


Evalutaion of Densification

Controllable refinement

Comparisons of upsamplers


Evalutaion of Densification

Controllable refinement

Comparisons of upsamplers


Latent Space Exploration

Hairstyle interpolation

Hairstyle arithmetics


Neural Simulation