Name
Abstract | ||
|---|---|---|
Abstract—Cast shadows can be significant in many computer vision applications, such as lighting-insensitive recognition and surface reconstruction. Nevertheless, most algorithms neglect them, primarily because they involve nonlocal interactions in nonconvex regions, making formal analysis difficult. However, many real instances map closely to canonical configurations like a wall, a V-groove type structure, or a pitted surface. In particular, we experiment with 3D textures like moss, gravel, and a kitchen sponge, whose surfaces include canonical configurations,like V-grooves. This paper takes a first step toward,a formal analysis of cast shadows, showing theoretically that many configurations can be mathematically,analyzed,using convolutions,and Fourier basis functions. Our analysis exposes,the mathematical,convolution,structure of cast shadows,and shows,strong connections,to recent signal-processing frameworks,for reflection and illumination. Index Terms—Cast shadows, convolution, Fourier analysis, eigenmodes, |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/TPAMI.2005.22 | IEEE transactions on pattern analysis and machine intelligence |
Keywords | Field | DocType |
gravel,index terms- cast shadows,signal processing,mathematical convolution structure analysis,algorithms neglect,fourier theory,fourier basis functions,convolution,canonical configurations,lighting insensitive recognition,v-grooves.,3d textures,computer vision application,formal analysis,computer vision,cast shadow,fourier analysis,surface reconstruction,moss,image texture,illumination,mathematical convolution structure,v-grooves,cast shadows,eigenmodes,fourier basis function,canonical configuration,v-groove type structure,kitchen sponge,spherical harmonic,eigenvalues,numerical simulation | Convolution of probability distributions,Computer vision,Computer simulation,Computer science,Convolution,Spherical harmonics,Zernike polynomials,Fourier transform,Artificial intelligence,Basis function,Eigenvalues and eigenvectors | Journal |
Volume | Issue | ISSN |
27 | 2 | 0162-8828 |
Citations | PageRank | References |
33 | 1.37 | 17 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ravi Ramamoorthi | 1 | 4481 | 237.21 |
| Melissa L. Koudelka | 2 | 77 | 5.49 |
| Peter N. Belhumeur | 3 | 12242 | 1001.27 |