2015 19th International Conference on Information Visualisation (iV) (2015)
July 22, 2015 to July 24, 2015
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/iV.2015.75
To better capture the shapes as well as the rich dynamics of hair, image based modelling techniques have been developed for reconstructing their 3D geometry and important visual features. Most hair images contain inevitable noises which impair reconstructed hair models. Therefore we propose to pre-process hair images and provide an orientation map of hair strands to enhance the follow-on modelling. To demonstrate the usage of pre-processing techniques, we apply our pre-processing results for bas-relief stylisation and modelling of hair from image inputs. We compare different techniques to estimate hair orientations, adopting four types of filter mechanisms. Our analysis of their performance sheds insight on designing a suitable pre-processing technique for hair reconstruction from images. Several examples of bas-relief creation validate the effectiveness of the proposed approach.
Hair, Image edge detection, Computational modeling, Noise, Image reconstruction, Three-dimensional displays, Image color analysis
W. Zhang, J. Chang, J. J. Zhang, M. Wang and R. Tong, "Image-Based Hair Pre-processing for Art Creation: A Case Study of Bas-Relief Modelling," 2015 19th International Conference on Information Visualisation (iV)(IV), Barcelona, Spain, 2015, pp. 411-418.