Shading Flows and Scenel Bundles: A New Approach to Shape from Shading

The classical approach to shape from shading problems is to find a numerical solution of the image irradiance partial differential equation. It is always assumed that the parameters of this equation (the light source direction and surface albedo) can be estimated in advance. For images which contain shadows and occluding contours, this decoupling of problems is artificial. We develop a new approach to solving these equations. It is based on modern differential geometry, and solves for light source, surface shape, and material changes concurrently. Local scene elements (scenels) are estimated from the shading flow field, and smoothness, material, and light source compatibility conditions resolve them into consistent scene descriptions. Shadows and related difficulties for the classical approach are discussed.

[1]  Steven W. Zucker,et al.  Efficient Simplex-Like Methods for Equilibria of Nonsymmetric Analog Networks , 1992, Neural Computation.

[2]  Steven W. Zucker,et al.  Two Stages of Curve Detection Suggest Two Styles of Visual Computation , 1989, Neural Computation.

[3]  Jan J. Koenderink,et al.  Solid shape , 1990 .

[4]  M. Spivak.  A comprehensive introduction to differential geometry , 1979 .

[5]  J. Koenderink,et al.  Photometric Invariants Related to Solid Shape , 1980 .

[6]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[8]  J J Koenderink,et al.  What Does the Occluding Contour Tell Us about Solid Shape? , 1984, Perception.

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

[10]  Steven W. Zucker,et al.  Inferring Surface Trace and Differential Structure from 3-D Images , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Berthold K. P. Horn.  Obtaining shape from shading information , 1989 .

[12]  D. Jameson,et al.  Mach bands : quantitative studies on neural networks in the retina , 1966 .

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

[14]  J. Koenderink,et al.  The Shape of Smooth Objects and the Way Contours End , 1982, Perception.

[15]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[16]  Patrick Henry Winston,et al.  The psychology of computer vision , 1976, Pattern Recognit..

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

[18]  J. Oliensis,et al.  Shape from shading as a partially well-constrained problem , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.