EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion

TL;DR

EfficientMonoHair presents a fast, accurate method for strand-level hair reconstruction from monocular video, combining implicit neural networks with multi-view geometric fusion to outperform existing approaches in speed and fidelity.

Contribution

The paper introduces a novel fusion-patch-based multi-view optimization and a parallel hair-growing strategy to enhance efficiency and robustness in hair reconstruction.

Findings

Achieves high-fidelity strand geometries with robustness to noisy data.

Significantly improves runtime efficiency by nearly tenfold compared to state-of-the-art methods.

Maintains reconstruction quality on synthetic benchmarks comparable to existing high-accuracy methods.

Abstract

Strand-level hair geometry reconstruction is a fundamental problem in virtual human modeling and the digitization of hairstyles. However, existing methods still suffer from a significant trade-off between accuracy and efficiency. Implicit neural representations can capture the global hair shape but often fail to preserve fine-grained strand details, while explicit optimization-based approaches achieve high-fidelity reconstructions at the cost of heavy computation and poor scalability. To address this issue, we propose EfficientMonoHair, a fast and accurate framework that combines the implicit neural network with multi-view geometric fusion for strand-level reconstruction from monocular video. Our method introduces a fusion-patch-based multi-view optimization that reduces the number of optimization iterations for point cloud direction, as well as a novel parallel hair-growing strategy that relaxes voxel occupancy constraints, allowing large-scale strand tracing to remain stable and robust even under inaccurate or noisy orientation fields. Extensive experiments on representative real-world hairstyles demonstrate that our method can robustly reconstruct high-fidelity strand geometries with accuracy. On synthetic benchmarks, our method achieves reconstruction quality comparable to state-of-the-art methods, while improving runtime efficiency by nearly an order of magnitude.