Nothing Special   »   [go: up one dir, main page]

skip to main content
research-article
Open access

GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations

Published: 05 December 2023 Publication History

Abstract

Despite recent successes in hair acquisition that fits a high-dimensional hair model to a specific input subject, generative hair models, which establish general embedding spaces for encoding, editing, and sampling diverse hairstyles, are way less explored. In this paper, we present GroomGen, the first generative model designed for hair geometry composed of highly-detailed dense strands. Our approach is motivated by two key ideas. First, we construct hair latent spaces covering both individual strands and hairstyles. The latent spaces are compact, expressive, and well-constrained for high-quality and diverse sampling. Second, we adopt a hierarchical hair representation that parameterizes a complete hair model to three levels: single strands, sparse guide hairs, and complete dense hairs. This representation is critical to the compactness of latent spaces, the robustness of training, and the efficiency of inference. Based on this hierarchical latent representation, our proposed pipeline consists of a strand-VAE and a hairstyle-VAE that encode an individual strand and a set of guide hairs to their respective latent spaces, and a hybrid densification step that populates sparse guide hairs to a dense hair model. GroomGen not only enables novel hairstyle sampling and plausible hairstyle interpolation, but also supports interactive editing of complex hairstyles, or can serve as strong data-driven prior for hairstyle reconstruction from images. We demonstrate the superiority of our approach with qualitative examples of diverse sampled hairstyles and quantitative evaluation of generation quality regarding every single component and the entire pipeline.

Supplemental Material

MP4 File
supplemental

References

[1]
Martín Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein Generative Adversarial Networks. In ICML 2017, Vol. 70. 214--223.
[2]
Thabo Beeler, Bernd Bickel, Gioacchino Noris, Paul A. Beardsley, Steve Marschner, Robert W. Sumner, and Markus H. Gross. 2012. Coupled 3D reconstruction of sparse facial hair and skin. ACM Trans. Graph. 31, 4 (2012), 117:1--117:10.
[3]
Florence Bertails, Basile Audoly, Marie-Paule Cani, Bernard Querleux, Frédéric Leroy, and Jean Luc Lévêque. 2006. Super-helices for predicting the dynamics of natural hair. ACM Trans. Graph. 25, 3 (2006), 1180--1187.
[4]
Florence Bertails, Basile Audoly, Bernard Querleux, Frédéric Leroy, Jean Luc Lévêque, and Marie-Paule Cani. 2005. Predicting Natural Hair Shapes by Solving the Statics of Flexible Rods. In Eurographics 2005. 81--84.
[5]
Menglei Chai, Linjie Luo, Kalyan Sunkavalli, Nathan Carr, Sunil Hadap, and Kun Zhou. 2015. High-quality hair modeling from a single portrait photo. ACM Trans. Graph. 34, 6 (2015), 204:1--204:10.
[6]
Menglei Chai, Tianjia Shao, Hongzhi Wu, Yanlin Weng, and Kun Zhou. 2016. AutoHair: fully automatic hair modeling from a single image. ACM Trans. Graph. 35, 4 (2016), 116:1--116:12.
[7]
Menglei Chai, Lvdi Wang, Yanlin Weng, Xiaogang Jin, and Kun Zhou. 2013. Dynamic hair manipulation in images and videos. ACM Trans. Graph. 32, 4 (2013), 75:1--75:8.
[8]
Menglei Chai, Lvdi Wang, Yanlin Weng, Yizhou Yu, Baining Guo, and Kun Zhou. 2012. Single-view hair modeling for portrait manipulation. ACM Trans. Graph. 31, 4 (2012), 116:1--116:8.
[9]
Menglei Chai, Changxi Zheng, and Kun Zhou. 2014. A reduced model for interactive hairs. ACM Trans. Graph. 33, 4 (2014), 124:1--124:11.
[10]
Menglei Chai, Changxi Zheng, and Kun Zhou. 2017. Adaptive Skinning for Interactive Hair-Solid Simulation. IEEE Trans. Vis. Comput. Graph. 23, 7 (2017), 1725--1738.
[11]
Tamar Flash and Neville Hogan. 1985. The Coordination of Arm Movements: An Experimentally Confirmed Mathematical Model. Journal of Neuroscience 5, 7 (1985), 1688--1703.
[12]
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In NIPS 2014. 2672--2680.
[13]
Peng Guan, Leonid Sigal, Valeria Reznitskaya, and Jessica K. Hodgins. 2012. Multi-linear Data-Driven Dynamic Hair Model with Efficient Hair-Body Collision Handling. In SCA 2012. 295--304.
[14]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR 2016. 770--778.
[15]
Tomás Lay Herrera, Arno Zinke, and Andreas Weber. 2012. Lighting hair from the inside: a thermal approach to hair reconstruction. ACM Trans. Graph. 31, 6 (2012), 146:1--146:9.
[16]
Liwen Hu, Derek Bradley, Hao Li, and Thabo Beeler. 2017. Simulation-Ready Hair Capture. Comput. Graph. Forum 36, 2 (2017), 281--294.
[17]
Liwen Hu, Chongyang Ma, Linjie Luo, and Hao Li. 2014. Robust hair capture using simulated examples. ACM Trans. Graph. 33, 4 (2014), 126:1--126:10.
[18]
Liwen Hu, Chongyang Ma, Linjie Luo, and Hao Li. 2015. Single-view hair modeling using a hairstyle database. ACM Trans. Graph. 34, 4 (2015), 125:1--125:9.
[19]
Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In ICML 2015, Vol. 37. 448--456.
[20]
Wenzel Jakob, Jonathan T. Moon, and Steve Marschner. 2009. Capturing hair assemblies fiber by fiber. ACM Trans. Graph. 28, 5 (2009), 164.
[21]
Tero Karras, Samuli Laine, and Timo Aila. 2019. A Style-Based Generator Architecture for Generative Adversarial Networks. In CVPR 2019. 4401--4410.
[22]
Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR 2015.
[23]
Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In ICLR 2014.
[24]
Zhiyi Kuang, Yiyang Chen, Hongbo Fu, Kun Zhou, and Youyi Zheng. 2022. Deep-MVSHair: Deep Hair Modeling from Sparse Views. In SIGGRAPH Asia 2022. 10:1--10:8.
[25]
Shu Liang, Xiufeng Huang, Xianyu Meng, Kunyao Chen, Linda G. Shapiro, and Ira Kemelmacher-Shlizerman. 2018. Video to fully automatic 3D hair model. ACM Trans. Graph. 37, 6 (2018), 206.
[26]
Linjie Luo, Hao Li, Sylvain Paris, Thibaut Weise, Mark Pauly, and Szymon Rusinkiewicz. 2012. Multi-view hair capture using orientation fields. In CVPR 2012. 1490--1497.
[27]
Linjie Luo, Hao Li, and Szymon Rusinkiewicz. 2013. Structure-aware hair capture. ACM Trans. Graph. 32, 4 (2013), 76:1--76:12.
[28]
Qing Lyu, Menglei Chai, Xiang Chen, and Kun Zhou. 2022. Real-Time Hair Simulation With Neural Interpolation. IEEE Trans. Vis. Comput. Graph. 28, 4 (2022), 1894--1905.
[29]
Ishit Mehta, Michaël Gharbi, Connelly Barnes, Eli Shechtman, Ravi Ramamoorthi, and Manmohan Chandraker. 2021. Modulated Periodic Activations for Generalizable Local Functional Representations. In ICCV 2021. 14194--14203.
[30]
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV 2020, Vol. 12346. 405--421.
[31]
Giljoo Nam, Chenglei Wu, Min H. Kim, and Yaser Sheikh. 2019. Strand-Accurate Multi-View Hair Capture. In CVPR 2019. 155--164.
[32]
Kyle Olszewski, Duygu Ceylan, Jun Xing, Jose Echevarria, Zhili Chen, Weikai Chen, and Hao Li. 2020. Intuitive, Interactive Beard and Hair Synthesis With Generative Models. In CVPR 2020. 7444--7454.
[33]
Sylvain Paris, Héctor M. Briceño, and François X. Sillion. 2004. Capture of hair geometry from multiple images. ACM Trans. Graph. 23, 3 (2004), 712--719.
[34]
Sylvain Paris, Will Chang, Oleg I. Kozhushnyan, Wojciech Jarosz, Wojciech Matusik, Matthias Zwicker, and Frédo Durand. 2008. Hair photobooth: geometric and photometric acquisition of real hairstyles. ACM Trans. Graph. 27, 3 (2008), 30.
[35]
Alec Radford, Luke Metz, and Soumith Chintala. 2016. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In ICLR 2016.
[36]
Qiaomu Ren, Haikun Wei, and Yangang Wang. 2021. Hair Salon: A Geometric Example-Based Method to Generate 3D Hair Data. In ICIG 2021, Vol. 12890. 533--544.
[37]
Radu Alexandru Rosu, Shunsuke Saito, Ziyan Wang, Chenglei Wu, Sven Behnke, and Giljoo Nam. 2022. Neural Strands: Learning Hair Geometry and Appearance from Multi-view Images. In ECCV 2022, Vol. 13693. 73--89.
[38]
Shunsuke Saito, Liwen Hu, Chongyang Ma, Hikaru Ibayashi, Linjie Luo, and Hao Li. 2018. 3D hair synthesis using volumetric variational autoencoders. ACM Trans. Graph. 37, 6 (2018), 208.
[39]
Yuefan Shen, Changgeng Zhang, Hongbo Fu, Kun Zhou, and Youyi Zheng. 2021. DeepSketchHair: Deep Sketch-Based 3D Hair Modeling. IEEE Trans. Vis. Comput. Graph. 27, 7 (2021), 3250--3263.
[40]
Tiancheng Sun, Giljoo Nam, Carlos Aliaga, Christophe Hery, and Ravi Ramamoorthi. 2021. Human Hair Inverse Rendering using Multi-View Photometric data. In EGSR 2021. 179--190.
[41]
Dmitry Ulyanov, Andrea Vedaldi, and Victor S. Lempitsky. 2016. Instance Normalization: The Missing Ingredient for Fast Stylization. CoRR abs/1607.08022 (2016).
[42]
Lvdi Wang, Yizhou Yu, Kun Zhou, and Baining Guo. 2009. Example-based hair geometry synthesis. ACM Trans. Graph. 28, 3 (2009), 56.
[43]
Ziyan Wang, Giljoo Nam, Tuur Stuyck, Stephen Lombardi, Michael Zollhöfer, Jessica K. Hodgins, and Christoph Lassner. 2022. HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture. In CVPR 2022. 6133--6144.
[44]
Yichen Wei, Eyal Ofek, Long Quan, and Heung-Yeung Shum. 2005. Modeling hair from multiple views. ACM Trans. Graph. 24, 3 (2005), 816--820.
[45]
Sebastian Winberg, Gaspard Zoss, Prashanth Chandran, Paulo F. U. Gotardo, and Derek Bradley. 2022. Facial hair tracking for high fidelity performance capture. ACM Trans. Graph. 41, 4 (2022), 165:1--165:12.
[46]
Keyu Wu, Yifan Ye, Lingchen Yang, Hongbo Fu, Kun Zhou, and Youyi Zheng. 2022. NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations. In CVPR 2022. 1516--1525.
[47]
Zexiang Xu, Hsiang-Tao Wu, Lvdi Wang, Changxi Zheng, Xin Tong, and Yue Qi. 2014. Dynamic hair capture using spacetime optimization. ACM Trans. Graph. 33, 6 (2014), 224:1--224:11.
[48]
Lingchen Yang, Zefeng Shi, Youyi Zheng, and Kun Zhou. 2019. Dynamic hair modeling from monocular videos using deep neural networks. ACM Trans. Graph. 38, 6 (2019), 235:1--235:12.
[49]
Meng Zhang, Menglei Chai, Hongzhi Wu, Hao Yang, and Kun Zhou. 2017. Adata-driven approach to four-view image-based hair modeling. ACM Trans. Graph. 36, 4 (2017), 156:1--156:11.
[50]
Qing Zhang, Jing Tong, Huamin Wang, Zhigeng Pan, and Ruigang Yang. 2012. Simulation Guided Hair Dynamics Modeling from Video. Comput. Graph. Forum 31, 7 (2012), 2003--2010.
[51]
Yujian Zheng, Zirong Jin, Moran Li, Haibin Huang, Chongyang Ma, Shuguang Cui, and Xiaoguang Han. 2023. HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling. In CVPR 2023. 12726--12735.
[52]
Yi Zhou, Liwen Hu, Jun Xing, Weikai Chen, Han-Wei Kung, Xin Tong, and Hao Li. 2018. HairNet: Single-View Hair Reconstruction Using Convolutional Neural Networks. In ECCV 2018, Vol. 11215. 249--265.

Cited By

View all
  • (2024)GroomCap: High-Fidelity Prior-Free Hair CaptureACM Transactions on Graphics10.1145/368776843:6(1-15)Online publication date: 19-Nov-2024
  • (2024)Curly-Cue: Geometric Methods for Highly Coiled HairSIGGRAPH Asia 2024 Conference Papers10.1145/3680528.3687641(1-11)Online publication date: 3-Dec-2024
  • (2024)Hairmony: Fairness-aware hairstyle classificationSIGGRAPH Asia 2024 Conference Papers10.1145/3680528.3687582(1-11)Online publication date: 3-Dec-2024
  • Show More Cited By

Index Terms

  1. GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations

    Recommendations

    Comments

    Please enable JavaScript to view thecomments powered by Disqus.

    Information & Contributors

    Information

    Published In

    cover image ACM Transactions on Graphics
    ACM Transactions on Graphics  Volume 42, Issue 6
    December 2023
    1565 pages
    ISSN:0730-0301
    EISSN:1557-7368
    DOI:10.1145/3632123
    Issue’s Table of Contents
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 05 December 2023
    Published in TOG Volume 42, Issue 6

    Check for updates

    Author Tags

    1. hairstyle generation
    2. strand-level hair modeling

    Qualifiers

    • Research-article

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)562
    • Downloads (Last 6 weeks)78
    Reflects downloads up to 08 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)GroomCap: High-Fidelity Prior-Free Hair CaptureACM Transactions on Graphics10.1145/368776843:6(1-15)Online publication date: 19-Nov-2024
    • (2024)Curly-Cue: Geometric Methods for Highly Coiled HairSIGGRAPH Asia 2024 Conference Papers10.1145/3680528.3687641(1-11)Online publication date: 3-Dec-2024
    • (2024)Hairmony: Fairness-aware hairstyle classificationSIGGRAPH Asia 2024 Conference Papers10.1145/3680528.3687582(1-11)Online publication date: 3-Dec-2024
    • (2024)EmoSpaceTime: Decoupling Emotion and Content through Contrastive Learning for Expressive 3D Speech AnimationProceedings of the 17th ACM SIGGRAPH Conference on Motion, Interaction, and Games10.1145/3677388.3696336(1-12)Online publication date: 21-Nov-2024
    • (2024)Creating LEGO Figurines from Single ImagesACM Transactions on Graphics10.1145/365816743:4(1-16)Online publication date: 19-Jul-2024
    • (2024)DressCode: Autoregressively Sewing and Generating Garments from Text GuidanceACM Transactions on Graphics10.1145/365814743:4(1-13)Online publication date: 19-Jul-2024
    • (2024)Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR52733.2024.01947(20601-20611)Online publication date: 16-Jun-2024
    • (2024)Text-Conditioned Generative Model of 3D Strand-Based Human Hairstyles2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR52733.2024.00450(4703-4712)Online publication date: 16-Jun-2024
    • (2024)Spline-Based TransformersComputer Vision – ECCV 202410.1007/978-3-031-73016-0_1(1-17)Online publication date: 29-Sep-2024
    • (2024)Human Hair Reconstruction with Strand-Aligned 3D GaussiansComputer Vision – ECCV 202410.1007/978-3-031-72640-8_23(409-425)Online publication date: 29-Sep-2024

    View Options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Login options

    Full Access

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media