Name
Abstract | ||
|---|---|---|
Photometric stereo and depth-map estimation provide a way to construct a depth map from image sets of an object under one viewpoint but with varying illumination directions. While estimating surface normals using the Lambertian model of reflectance is well-established, depth-map estimation methods are an ongoing field of research. Dealing with image noise is one such active topic. This paper introduces a maximum likelihood depth-map estimation technique using the zero-mean Gaussian model of image noise. The technique accounts for the propagation of noise through all steps of the reconstruction process. Based on this model, solving for maximum likelihood depth-map estimates involves executing an independent sequence of nonlinear regression estimates, one for each pixel, followed by a single large and sparse linear regression estimate. The linear system employs anisotropic weights, which arise naturally and differ in value to related work. Depth-map estimation remains efficient and fast, making the technique practical for realistic image sizes. Experiments using synthetic images demonstrate the technique's ability to robustly estimate depth maps under the noise model. Practical benefits of the method on challenging imaging scenarios are illustrated by experiments using the Extended Yale Face Database B and an extensive dataset of 500 reflected light microscopy image sets. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TPAMI.2011.249 | IEEE transactions on pattern analysis and machine intelligence |
Keywords | Field | DocType |
photometric stereo,image noise,realistic image size,light microscopy image sequence,maximum likelihood depth-map estimate,depth-map estimation,maximum likelihood depth-map estimation,new depth-map estimation method,depth map,maximum likelihood estimation,estimation process,noise model,photometry,finite difference method,regression analysis,maximum likelihood estimate,linear regression,covariance matrix,maximum likelihood,light microscopy,gaussian noise,linear system,mathematical model,nonlinear regression,gaussian processes,finite difference methods | Linear system,Pattern recognition,Computer science,Image noise,Pixel,Artificial intelligence,Gaussian process,Covariance matrix,Depth map,Gaussian noise,Photometric stereo | Journal |
Volume | Issue | ISSN |
34 | 7 | 1939-3539 |
Citations | PageRank | References |
6 | 0.44 | 18 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Adam P. Harrison | 1 | 101 | 17.06 |
| Dileepan Joseph | 2 | 49 | 8.48 |