Human Hair Reconstruction with Strand-Aligned 3D Gaussians

TL;DR

This paper presents Gaussian Haircut, a novel hair modeling technique that combines classical hair strands with strand-aligned 3D Gaussians, enabling realistic, editable, and renderable hair reconstructions from multi-view data.

Contribution

It introduces a dual representation of hair using strand-aligned 3D Gaussians and classical strands, facilitating realistic and editable hair modeling with differentiable rendering.

Findings

Achieves state-of-the-art accuracy in hair reconstruction

Supports out-of-the-box editing and rendering in graphics engines

Demonstrates effectiveness on synthetic and real data

Abstract

We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians to produce accurate and realistic strand-based reconstructions from multi-view data. In contrast to recent approaches that leverage unstructured Gaussians to model human avatars, our method reconstructs the hair using 3D polylines, or strands. This fundamental difference allows the use of the resulting hairstyles out-of-the-box in modern computer graphics engines for editing, rendering, and simulation. Our 3D lifting method relies on unstructured Gaussians to generate multi-view ground truth data to supervise the fitting of hair strands. The hairstyle itself is represented in the form of the so-called strand-aligned 3D Gaussians. This representation allows us to combine strand-based hair priors, which are essential for realistic modeling of the inner structure of hairstyles, with the differentiable rendering capabilities of 3D Gaussian Splatting. Our method, named Gaussian Haircut, is evaluated on synthetic and real scenes and demonstrates state-of-the-art performance in the task of strand-based hair reconstruction.