23 January 2017 Material appearance acquisition from a single image
Author Affiliations +
Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 103221E (2017) https://doi.org/10.1117/12.2265223
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China
Abstract
The scope of this paper is to present a method of material appearance acquisition(MAA) from a single image. In this paper, material appearance is represented by spatially varying bidirectional reflectance distribution function(SVBRDF). Therefore, MAA can be reduced to the problem of recovery of each pixel’s BRDF parameters from an original input image, which include diffuse coefficient, specular coefficient, normal and glossiness based on the Blinn-Phone model. In our method, the workflow of MAA includes five main phases: highlight removal, estimation of intrinsic images, shape from shading(SFS), initialization of glossiness and refining SVBRDF parameters based on IPOPT. The results indicate that the proposed technique can effectively extract the material appearance from a single image.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xu Zhang, Shulin Cui, Hanwen Cui, Lin Yang, Tao Wu, "Material appearance acquisition from a single image", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103221E (23 January 2017); doi: 10.1117/12.2265223; https://doi.org/10.1117/12.2265223
PROCEEDINGS
5 PAGES


SHARE
Back to Top