EfficientMonoHair：通过多视角方向融合从单目视频快速重建发丝级几何
EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion
把隐式神经表示与多视角方向融合结合，用 fusion-patch 多视角优化减少点云方向场的迭代次数，并用放宽体素占用约束的并行生长策略在噪声方向场下稳定追踪发丝——这套「粗到细方向场 + 并行生长」的思路可迁移到其他细长结构（线缆、纤维、血管）的单目重建。
原文依据 a novel parallel hair-growing strategy that relaxes voxel occupancy constraints, allowing large-scale strand tracing to remain stable and robust
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论发丝级头发几何重建是虚拟人建模与发型数字化的基础问题。然而，现有方法仍在精度与效率之间存在显著的权衡。隐式神经表示能够捕捉整体头发形状，但往往难以保留细粒度的发丝细节；而基于显式优化的方法虽能实现高保真重建，却以沉重的计算代价和较差的可扩展性为代价。为解决这一问题，我们提出 EfficientMonoHair，一个快速且准确的框架，将隐式神经网络与多视角几何融合相结合，从单目视频进行发丝级重建。该方法引入了基于融合块的多视角优化，减少了点云方向所需的优化迭代次数；并提出一种新颖的并行头发生长策略，放宽了体素占用约束，使得大规模发丝追踪在方向场不准确或含噪声时仍能保持稳定与鲁棒。在具有代表性的真实发型上的大量实验表明，本方法能够鲁棒地重建出高保真的发丝几何并保证精度。在合成基准上，本方法的重建质量与最优方法相当，同时将运行效率提升近一个数量级。
英文原文摘要 1391 字符
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.