Refinement of Hair Geometry by Strand Integration
- 1 October 2023
- journal article
- research article
- Published by Wiley in Computer Graphics Forum
- Vol. 42 (7)
Abstract
Reconstructing 3D hair is challenging due to its complex micro‐scale geometry, and is of essential importance for the efficient creation of high‐fidelity virtual humans. Existing hair capture methods based on multi‐view stereo tend to generate results that are noisy and inaccurate. In this study, we propose a refinement method for hair geometry by incorporating the gradient of strands into the computation of their position. We formulate a gradient integration strategy for hair strands. We evaluate the performance of our method using a synthetic multi‐view dataset containing four hairstyles, and show that our refinement produces more accurate hair geometry. Furthermore, we tested our method with a real image input. Our method produces a plausible result. Our source code is publicly available athttps://github.com/elerac/strand_integration.Keywords
This publication has 28 references indexed in Scilit:
- Single-view hair modeling using a hairstyle databaseACM Transactions on Graphics, 2015
- Robust hair capture using simulated examplesACM Transactions on Graphics, 2014
- Structure-aware hair captureACM Transactions on Graphics, 2013
- Lighting hair from the insideACM Transactions on Graphics, 2012
- Single-view hair modeling for portrait manipulationACM Transactions on Graphics, 2012
- Hair meshesACM Transactions on Graphics, 2009
- Hair photoboothACM Transactions on Graphics, 2008
- Capture of hair geometry from multiple imagesACM Transactions on Graphics, 2004
- The variational approach to shape from shadingComputer Vision, Graphics, and Image Processing, 1986
- Photometric Method For Determining Surface Orientation From Multiple ImagesOptical Engineering, 1980