Cited By
View all- Rotger GMoreno-Noguer FLumbreras FAgudo A(2019)Single View Facial Hair 3D ReconstructionPattern Recognition and Image Analysis10.1007/978-3-030-31332-6_37(423-436)Online publication date: 1-Jul-2019
3D braid guide hair reconstruction using electroluminescent wires
Pages 793 - 804
Abstract
In this paper we propose a novel braid acquisition and 3D guide hair reconstruction method. Low-cost electroluminescent wires are woven into the braided hair strands which are thereby illuminated from the inside. Unlike state-of-the-art hair reconstruction approaches, we do not need image texture information, data-driven prior knowledge or manual editing. Instead, our workflow reconstructs braid guide hairs fully automatically using semi-open-end 3D active curves on images recorded from multiple views. The proposed pipeline extracts non-surface, internal 3D information which enables morphing and inter-character hairdo-transfer. In state-of-the-art methods, those abilities typically exist for virtually created hairstyles and not for reconstructed hairstyles. Furthermore, using the new acquisition scheme we provide a novel type of data set to the community.
References
[1]
Bouguet, J.Y.: Camera calibration toolbox for Matlab. http://www.vision.caltech.edu/bouguetj/calib_doc/. Accessed 16 Jan 2018
[2]
Byoungwon, C., Hyeong-Seok, K.: A statistical wisp model and pseudophysical approaches for interactive hairstyle generation. IEEE Trans. Vis. Comput. Gr. 11, 160---170 (2005).
[3]
Chai, M., Luo, L., Sunkavalli, K., Carr, N., Hadap, S., Zhou, K.: High-quality hair modeling from a single portrait photo. ACM Trans. Gr. 34(6), 204:1---204:10 (2015).
[4]
Chai, M., Shao, T., Wu, H., Weng, Y., Zhou, K.: AutoHair: fully automatic hair modeling from a single image. ACM Trans. Gr. 35(4), 116:1---116:12 (2016).
[5]
Chai, M., Wang, L., Weng, Y., Jin, X., Zhou, K.: Dynamic hair manipulation in images and videos. ACM Trans. Gr. 32(4), 75:1---75:8 (2013).
[6]
Chai, M., Wang, L., Weng, Y., Yu, Y., Guo, B., Zhou, K.: Single-view hair modeling for portrait manipulation. ACM Trans. Gr. 31(4), 116:1---116:8 (2012).
[7]
Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Trans. Image Process. 10(2), 266---277 (2001).
[8]
Cohen, L.D.: On active contour models and balloons. CVGIP Image Underst. 53(2), 211---218 (1991).
[9]
Destriau, G.: Recherches sur les scintillations des sulfures de zinc aux rayons. Journal de Chemie Physique 33, 587---625 (1936).
[10]
Hadap, S., Magnenat-Thalmann, N.: Interactive Hair Styler Based on Fluid Flow, pp. 87---99. Springer Vienna, Vienna (2000).
[11]
Herrera, T., Zinke, A., Weber, A.: Lighting hair from the inside: a thermal approach to hair reconstruction. ACM Trans. Gr. (2012).
[12]
Horn, B.K.P., Brooks, M.J. (eds.): Shape from Shading. MIT Press, Cambridge (1989)
[13]
Hu, L., Ma, C., Luo, L., Li, H.: Robust hair capture using simulated examples. ACM Trans. Gr. (2014).
[14]
Hu, L., Ma, C., Luo, L., Li, H.: Single-view hair modeling using a hairstyle database. ACM Trans. Gr. (2015).
[15]
Hu, L., Ma, C., Luo, L., Wei, L.Y., Li, H.: Capturing braided hairstyles. ACM Trans. Gr. 33(6), 225:1---225:9 (2014).
[16]
Ishikawa, T., Kazama, Y., Sugisaki, E., Morishima, S.: Hair motion reconstruction using motion capture system. In: ACM SIGGRAPH 2007 Posters, SIGGRAPH '07. ACM, New York, NY, USA (2007).
[17]
Jakob, W., Moon, J.T., Marschner, S.: Capturing hair assemblies fiber by fiber. ACM Trans. Gr. 28(5), 164:1---164:9 (2009).
[18]
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. 1(4), 321---331 (1988).
[19]
Laurentini, A.: The visual hull concept for Silhouette-based image understanding. IEEE Trans. Pattern Anal. Mach. Intell. 16(2), 150---162 (1994).
[20]
Luo, L., Zhang, C., Zhang, Z., Rusinkiewicz, S.: Wide-baseline hair capture using strand-based refinement. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 265---272 (2013).
[21]
Müller, O., Yang, M.Y., Rosenhahn, B.: Slice sampling particle belief propagation. In: 2013 IEEE International Conference on Computer Vision, pp. 1129---1136 (2013).
[22]
Paris, S., Chang, W., Kozhushnyan, O.I., Jarosz, W., Matusik, W., Zwicker, M., Durand, F.: Hair photobooth: geometric and photometric acquisition of real hairstyles. ACM Trans. Gr. (2008).
[23]
Scheuermann, B., Rosenhahn, B.: Multi-sensor fusion for video segmentation. Int. J. Pattern Recognit. Artif. Intell. 28(7), 14 (2014).
[24]
Smith, M.B., Li, H., Shenand, T., Huang, X., Yusuf, E., Vavylonis, D.V.: Segmentation and tracking of cytoskeletal filaments using open active contours. Cytoskeleton 67, 693---705 (2010).
[25]
von Marcard, T., Rosenhahn, B., Black, M.J., Pons-Moll, G.: Sparse inertial poser: automatic 3D human pose estimation from sparse imus. Comput. Gr. Forum 36(2), 349---360 (2017).
[26]
Wang, L., Yu, Y., Zhou, K., Guo, B.: Example-based hair geometry synthesis. ACM Trans. Gr. 28(3), 56:1---56:9 (2009).
[27]
Ward, K., Bertails, F., Kim, T.Y., Marschner, S.R., Cani, M.P., Lin, M.C.: A survey on hair modeling: styling, simulation, and rendering. In: IEEE Transactions on Visualization and Computer Graphics, pp. 213---234 (2006).
[28]
Xu, C., Prince, J.L.: Snakes, shapes, and gradient vector flow. IEEE Trans. Image Process. 7(3), 359---369 (1998).
[29]
Yu, Y.: Modeling realistic virtual hairstyles. Pac. Conf. Comput. Gr. Appl. 00, 295 (2001).
Index Terms
- 3D braid guide hair reconstruction using electroluminescent wires
Index terms have been assigned to the content through auto-classification.
Recommendations
Human Hair Reconstruction with Strand-Aligned 3D Gaussians
Computer Vision – ECCV 2024AbstractWe 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 ...
Hair meshes
Despite the visual importance of hair and the attention paid to hair modeling in the graphics research, modeling realistic hair still remains a very challenging task that can be performed by very few artists. In this paper we present hair meshes, a new ...
A data-driven approach to four-view image-based hair modeling
We introduce a novel four-view image-based hair modeling method. Given four hair images taken from the front, back, left and right views as input, we first estimate the rough 3D shape of the hair observed in the input using a predefined database of 3D ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © Copyright © 2018 Springer-Verlag GmbH Germany, part of Springer Nature.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 June 2018
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 20 Jan 2025
Other Metrics
Citations
Cited By
View all- Rotger GMoreno-Noguer FLumbreras FAgudo A(2019)Single View Facial Hair 3D ReconstructionPattern Recognition and Image Analysis10.1007/978-3-030-31332-6_37(423-436)Online publication date: 1-Jul-2019