Name
Abstract | ||
|---|---|---|
This paper describes a new approach for self-calibration and color image rendering using radial basis function (RBF) neural network. Most empirical approaches make use of a calibration object. Here, we require no calibration object to both shape recovery and color image rendering. The neural network training data are obtained through the rotations of a target object. The approach can generate realistic virtual images without any calibration object which has the same reflectance properties as the target object. The proposed approach uses a neural network to obtain both surface orientation and albedo, and applies another neural network to generate virtual images for any viewpoint and any direction of light source. Experiments with real data are demonstrated. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-04592-9_87 | KES (2) |
Keywords | Field | DocType |
empirical approach,neural network,target object,neural network training data,color image rendering,realistic virtual image,new approach,rbf neural network,calibration object,radial basis function,color image | Virtual image,Computer vision,Radial basis function,Computer science,Artificial intelligence,Artificial neural network,Rendering (computer graphics),Light source,Photometric stereo,Calibration,Color image | Conference |
Volume | ISSN | Citations |
5712 | 0302-9743 | 4 |
PageRank | References | Authors |
0.49 | 1 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yi Ding | 1 | 8 | 2.02 |
| Yuji Iwahori | 2 | 159 | 56.83 |
| Tsuyoshi Nakamura | 3 | 13 | 3.67 |
| Robert J. Woodham | 4 | 274 | 368.34 |
| Lifeng He | 5 | 441 | 40.97 |
| Hidenori Itoh | 6 | 368 | 252.31 |