Towards Unified 3D Hair Reconstruction from Single-View Portraits
This addresses a specific challenge in computer vision for applications like virtual avatars or gaming, but it is incremental as it builds on prior methods to handle more hairstyle variations.
The paper tackles the problem of single-view 3D hair reconstruction for diverse hairstyles, including braided and un-braided styles, by proposing a unified pipeline that uses diffusion priors and Gaussian-based optimization, achieving state-of-the-art performance in recovering complex hairstyles with good generalization to real images.
Single-view 3D hair reconstruction is challenging, due to the wide range of shape variations among diverse hairstyles. Current state-of-the-art methods are specialized in recovering un-braided 3D hairs and often take braided styles as their failure cases, because of the inherent difficulty to define priors for complex hairstyles, whether rule-based or data-based. We propose a novel strategy to enable single-view 3D reconstruction for a variety of hair types via a unified pipeline. To achieve this, we first collect a large-scale synthetic multi-view hair dataset SynMvHair with diverse 3D hair in both braided and un-braided styles, and learn two diffusion priors specialized on hair. Then we optimize 3D Gaussian-based hair from the priors with two specially designed modules, i.e. view-wise and pixel-wise Gaussian refinement. Our experiments demonstrate that reconstructing braided and un-braided 3D hair from single-view images via a unified approach is possible and our method achieves the state-of-the-art performance in recovering complex hairstyles. It is worth to mention that our method shows good generalization ability to real images, although it learns hair priors from synthetic data.