Abstract | ||
---|---|---|
We present a method for simultaneously recovering shape and spatially varying reflectance of a surface from photometric stereo images. The distinguishing feature of our approach is its generality; it does not rely on a specific parametric reflectance model and is therefore purely "data- driven". This is achieved by employing novel bi-variate approximations of isotropic reflectance functions. By com- bining this new approximation with recent developments in photometric stereo, we are able to simultaneously estimate an independent surface normal at each point, a global set of non-parametric "basis material" BRDFs, and per-point material weights. Our experimental results validate the ap- proach and demonstrate the utility of bi-variate reflectance functions for general non-parametric appearance capture. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/CVPR.2008.4587656 | CVPR |
Keywords | Field | DocType |
approximation theory,stereo image processing,bivariate approximation,isotropic reflectance function,nonparametric reflectance,photometric stereo images,spatially-varying reflectance | Computer vision,Isotropy,Computer science,Approximation theory,Nonparametric statistics,Parametric statistics,Artificial intelligence,Reflectivity,Normal,Photometric stereo | Conference |
ISSN | Citations | PageRank |
1063-6919 | 83 | 2.30 |
References | Authors | |
18 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Neil G. Alldrin | 1 | 270 | 8.45 |
Todd Zickler | 2 | 1555 | 71.72 |
David Kriegman | 3 | 7693 | 451.96 |