Learning a Near-Optimal Estimator for Surface Shape from Shading

Abstract The problem of determining surface shape from shading is formulated in terms of Bayesian estimation. The goal is to select an estimate of surface shape that best fits some criterion on the posterior probability of the surface conditional on the image data. This conditional probability is a function of the imaging function and the prior probability of the surface. A gradient descent technique is used to compute the best linear estimator of the mean of the conditional distribution from a set of random fractal surfaces and their images. Simulations show that the derived estimator works well for a wide range of surfaces, including non-fractals. Once learned, the estimator could be used to implement a fast, non-iterative parallel device for estimating shape from shading with arbitrary light source directions. The estimator has similar perceptual deficits to human observers. In particular, it exhibits a loss of coarse-scale surface shape, while accurately reconstructing fine-scale details.

[1]  Demetri Terzopoulos,et al.  Regularization of Inverse Visual Problems Involving Discontinuities , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  James A. Anderson,et al.  Cognitive and psychological computation with neural models , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  C Koch,et al.  Analog "neuronal" networks in early vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[4]  E. Mingolla,et al.  Perception of surface curvature and direction of illumination from patterns of shading. , 1983, Journal of experimental psychology. Human perception and performance.

[5]  A. Pentland.  Finding the illuminant direction , 1982 .

[6]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  A. Pentland.  Shape information from shading: A theory about human perception , 1989 .

[9]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[10]  Azriel Rosenfeld,et al.  Improved Methods of Estimating Shape from Shading Using the Light Source Coordinate System , 1985, Artif. Intell..

[11]  Alex Pentland,et al.  Local Shading Analysis , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Teuvo Kohonen,et al.  Associative memory. A system-theoretical approach , 1977 .

[13]  Terrence J. Sejnowski,et al.  Network model of shape-from-shading: neural function arises from both receptive and projective fields , 1988, Nature.

[14]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Rama Chellappa,et al.  A Method for Enforcing Integrability in Shape from Shading Algorithms , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Katsushi Ikeuchi,et al.  Numerical Shape from Shading and Occluding Boundaries , 1981, Artif. Intell..

[17]  Michael J. Brooks,et al.  The variational approach to shape from shading , 1986, Comput. Vis. Graph. Image Process..

[18]  Alex Pentland,et al.  Shape Information From Shading: A Theory About Human Perception , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[19]  H H Bülthoff,et al.  Integration of depth modules: stereo and shading. , 1988, Journal of the Optical Society of America. A, Optics and image science.

[20]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[21]  Richard Szeliski,et al.  Regularization Uses Fractal Priors , 1987, AAAI.

[22]  J. A. Anderson,et al.  Associative learning of scene parameters from images. , 1987, Applied optics.

[23]  D C Knill,et al.  Estimating illuminant direction and degree of surface relief. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[24]  T. Poggio,et al.  Synthesizing a color algorithm from examples. , 1988, Science.

[25]  R. Voss.  Random Fractal Forgeries , 1985 .

[26]  Ellen C. Hildreth,et al.  Measurement of Visual Motion , 1984 .

[27]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[28]  B. Mandelbrot,et al.  Fractals: Form, Chance and Dimension , 1978 .

[29]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  K P HornBerthold,et al.  The variational approach to shape from shading , 1986 .

[31]  José L. Marroquín,et al.  Probabilistic solution of inverse problems , 1985 .