loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Chao Sun ; Zhongrui Li and Won-Sook Lee

Affiliation: University of Ottawa, Canada

Keyword(s): Hair Modeling, Kinect v2 Sensors.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Geometric Computing ; Geometry and Modeling ; Modeling and Algorithms

Abstract: Most existing hair capturing methods reconstruct 3D hair models from multi-view stereo based on complex capturing systems composed of many digital cameras and light sources. In this paper, we introduce a novel hair capturing system using consumer RGB-D (Kinect sensors). Our capture system, consisting of three Kinect v2 sensors, is much simpler than previous hair capturing systems. We directly use the 3D point clouds captured by Kinect v2 sensors as the hair volume. Then we adopt a fast and robust image enhancement algorithm to adaptively improve the clarity of the hair strands geometry based on the estimated local strands orientation and frequency from the hair images captured by the Kinect colour sensors. In addition, we introduced a hair strand grow-and-connect algorithm to generate relatively complete hair strands. Furthermore, by projecting the 2D hair strands onto the 3D point clouds, we can obtain the corresponding 3D hair strands. The experimental results indicate that our met hod can generate plausible 3D models for long, relatively straight hair. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 35.169.107.177

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Sun, C.; Li, Z. and Lee, W. (2015). Reconstruction of Relatively Straight Medium to Long Hair Models using Kinect Sensors. In Proceedings of the 10th International Conference on Computer Graphics Theory and Applications (VISIGRAPP 2015) - GRAPP; ISBN 978-989-758-087-1; ISSN 2184-4321, SciTePress, pages 158-164. DOI: 10.5220/0005312301580164

@conference{grapp15,
author={Chao Sun. and Zhongrui Li. and Won{-}Sook Lee.},
title={Reconstruction of Relatively Straight Medium to Long Hair Models using Kinect Sensors},
booktitle={Proceedings of the 10th International Conference on Computer Graphics Theory and Applications (VISIGRAPP 2015) - GRAPP},
year={2015},
pages={158-164},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005312301580164},
isbn={978-989-758-087-1},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Computer Graphics Theory and Applications (VISIGRAPP 2015) - GRAPP
TI - Reconstruction of Relatively Straight Medium to Long Hair Models using Kinect Sensors
SN - 978-989-758-087-1
IS - 2184-4321
AU - Sun, C.
AU - Li, Z.
AU - Lee, W.
PY - 2015
SP - 158
EP - 164
DO - 10.5220/0005312301580164
PB - SciTePress