Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MonoHair: High-Fidelity Hair Modeling from a Monocular Video

Keyu Wu, Lingchen Yang, Zhiyi Kuang, Yao Feng, Xutao Han, Yuefan Shen, Hongbo Fu, Kun Zhou, Youyi Zheng

TL;DR

This work proposes MonoHair, a generic framework to achieve high-fidelity hair reconstruction from a monocular video, without specific requirements for environments, and exhibits robustness across diverse hairstyles and achieves state-of-the-art performance.

Abstract

Undoubtedly, high-fidelity 3D hair is crucial for achieving realism, artistic expression, and immersion in computer graphics. While existing 3D hair modeling methods have achieved impressive performance, the challenge of achieving high-quality hair reconstruction persists: they either require strict capture conditions, making practical applications difficult, or heavily rely on learned prior data, obscuring fine-grained details in images. To address these challenges, we propose MonoHair,a generic framework to achieve high-fidelity hair reconstruction from a monocular video, without specific requirements for environments. Our approach bifurcates the hair modeling process into two main stages: precise exterior reconstruction and interior structure inference. The exterior is meticulously crafted using our Patch-based Multi-View Optimization (PMVO). This method strategically collects and integrates hair information from multiple views, independent of prior data, to produce a high-fidelity exterior 3D line map. This map not only captures intricate details but also facilitates the inference of the hair's inner structure. For the interior, we employ a data-driven, multi-view 3D hair reconstruction method. This method utilizes 2D structural renderings derived from the reconstructed exterior, mirroring the synthetic 2D inputs used during training. This alignment effectively bridges the domain gap between our training data and real-world data, thereby enhancing the accuracy and reliability of our interior structure inference. Lastly, we generate a strand model and resolve the directional ambiguity by our hair growth algorithm. Our experiments demonstrate that our method exhibits robustness across diverse hairstyles and achieves state-of-the-art performance. For more results, please refer to our project page https://keyuwu-cs.github.io/MonoHair/.

MonoHair: High-Fidelity Hair Modeling from a Monocular Video

TL;DR

This work proposes MonoHair, a generic framework to achieve high-fidelity hair reconstruction from a monocular video, without specific requirements for environments, and exhibits robustness across diverse hairstyles and achieves state-of-the-art performance.

Abstract

Undoubtedly, high-fidelity 3D hair is crucial for achieving realism, artistic expression, and immersion in computer graphics. While existing 3D hair modeling methods have achieved impressive performance, the challenge of achieving high-quality hair reconstruction persists: they either require strict capture conditions, making practical applications difficult, or heavily rely on learned prior data, obscuring fine-grained details in images. To address these challenges, we propose MonoHair,a generic framework to achieve high-fidelity hair reconstruction from a monocular video, without specific requirements for environments. Our approach bifurcates the hair modeling process into two main stages: precise exterior reconstruction and interior structure inference. The exterior is meticulously crafted using our Patch-based Multi-View Optimization (PMVO). This method strategically collects and integrates hair information from multiple views, independent of prior data, to produce a high-fidelity exterior 3D line map. This map not only captures intricate details but also facilitates the inference of the hair's inner structure. For the interior, we employ a data-driven, multi-view 3D hair reconstruction method. This method utilizes 2D structural renderings derived from the reconstructed exterior, mirroring the synthetic 2D inputs used during training. This alignment effectively bridges the domain gap between our training data and real-world data, thereby enhancing the accuracy and reliability of our interior structure inference. Lastly, we generate a strand model and resolve the directional ambiguity by our hair growth algorithm. Our experiments demonstrate that our method exhibits robustness across diverse hairstyles and achieves state-of-the-art performance. For more results, please refer to our project page https://keyuwu-cs.github.io/MonoHair/.
Paper Structure (27 sections, 9 equations, 22 figures, 4 tables, 1 algorithm)

This paper contains 27 sections, 9 equations, 22 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related work
  3. Implicit Representations in 3D Hair Modeling.
  4. Optimization Based Hair Reconstruction.
  5. Hair Reconstruction with Data Prior.
  6. Method
  7. Patch-based Multi-View Optimization
  8. Infer Interior Geometry
  9. Strand Generation
  10. Evalution
  11. Comparison
  12. Ablation Study
  13. Conclusion and Discussion
  14. Implementation Details and Data Preprocessing
  15. Datasets preprocessing
  16. ...and 12 more sections

Figures (22)

  • Figure 1: Quantitative comparison with kuang2022deepmvshairsklyarova2023neural_haircut. Our method achieves the highest precision and F-score.
  • Figure 2: An overview of our 3D hair reconstruction pipeline.
  • Figure 2: Comparison with Neural Haircut sklyarova2023neural_haircut in terms of time consumption. Our method is ten times faster.
  • Figure 3: Visualization of the line map extracted from raw geometry.
  • Figure 3: Quantitative evaluation of individual components of our method on the synthetic dataset yuksel2009hair.
  • ...and 17 more figures