HairLRM: Strand-based Hair Modeling via Large Reconstruction Models
This work provides a robust solution for high-fidelity 3D hair reconstruction from single images, benefiting computer graphics and vision applications requiring detailed hair modeling.
HairLRM addresses the ill-posedness of strand-based hair modeling from 2D images by integrating Large Reconstruction Model (LRM) priors and a Dual Orientation AutoEncoder, achieving robust reconstruction of complex hairstyles like ponytails and curls.
The fundamental limitation of traditional strand-based modeling is not simply data scarcity, but the ill-posedness of inferring complex 3D fields from 2D imagery without structural constraints. This unconstrained regression leads to catastrophic failures in resolving both global occlusion (e.g., in ponytails) and local directionality (e.g., in curls), resulting in over-smoothed, plausible-but-incorrect geometries. To resolve this, we integrate the strong geometric priors of Large Reconstruction Models (LRMs) into the strand generation pipeline. Using the LRM mesh as a structural anchor, we employ a novel Dual Orientation AutoEncoder to lift coarse geometry into high-fidelity strands. By resolving vector field singularities through latent-space optimization and surface-guided refinement, our method effectively disentangles complex topological structures, setting a new benchmark for robustness and accuracy in hair reconstruction.