Neural computation approach for developing a 3-D shape reconstruction model

IEEE Transactions on Neural Networks

Volumn 12, Issue 5, 2001, Pages 1204-1214

  Cho, S Y ^a   Chow, T W S ^a  

^a CITY UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

Neural based reflectance model; Shape from shading (SFS); Specular reflection

Indexed keywords

COMPUTATIONAL METHODS; COMPUTER SIMULATION; IMAGE RECONSTRUCTION; MATHEMATICAL MODELS; OPTIMIZATION; PROBLEM SOLVING; THREE DIMENSIONAL;

LAMBERTIAN MODELS; REFLECTANCE MODEL; SHAPE FROM SHADING PROBLEM; SHAPE RECONSTRUCTION; SPECULAR REFLECTION;

RADIAL BASIS FUNCTION NETWORKS;

EID: 0035440523     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.950148     Document Type: Article

References (18)

1. Shape from shading: A smooth opaque object from one view
2. Calculating the reflectance map
3. The variational approach to shape from shading
4. Fast shape from shading
5. Direct shape from shading with improved rate of convergence
6. A simple algorithm for shape from shading
7. Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images
8. Learning shape from shading by a multilayer network
9. Local shape from specularity
10. Theory for off-specular reflection from roughened surfaces
11. Shape from shading with a generalized reflectance map model
12. Shape recovery from shading by a new neural-based reflectance model
13. Determining shape and reflectance of hybrid surfaces by photometric sampling
14. On the problem of local minima in backpropagation
15. Universal approximation using radial basis function networks
16. Training multilayer neural networks using fast global learning algorithm: Least squares and penalized optimization methods
17. Estimation of illuminant direction, albedo, and shape from shading