In our effort to compute intrinsic images in a unique and robust way, we have combined information from different sources. In this chapter we discussed how to combine retinal motion with stereo to compute three- dimensional motion without using any correspondences and how to combine shading with retinal motion to compute shape and illuminate direction.
Aloimonos, J., "Computing intrinsic images." Ph.D. thesis, Department of Computer Science, University of Rochester: New York, September, 1986.
Ballard, D. H., "Parameter networks." Artificial Intelligence, 22, 235-267, 1984.
Bandopadhay, A., "A computational study of rigid motion perception." Ph.D. thesis, Dept. of Computer Science, University of Rochester: New York, September, 1986.
Barrow, H. G., & Popplestone, R. J., "Relational descriptions in picture processing." Machine Intelligence, 6, 1971. pp. 377-396.
Brooks, M. J., & Horn, B. K. P. "Shape and source from shading." Proceedings, International Joint Conference on Artificial Intelligence-85: Los Angeles, CA, 932-936, August 1985.
Brown, C. M., Ballard, D. H., & Kimball, O. A., "Constraint interaction in shape-from- shading algorithms." 1982-93 Computer Science and Computer Engineering Research Review, Computer Science Department, University of Rochester: New York, 3-21, 1983.
Davis, L. S., Wu Z., & Sun, H., "Contour based motion estimation." Computer Vision, Graphics and Image Processing, 23, 313-326, 1983.
Fang, J. Q., & Huang, T. S., "Solving three-dimensional small-rotation motion equations: Uniqueness, algorithms, and numerical results." Computer Vision, Graphics and Image Processing, 26, 183-206, 1984.
Freuder, E. C., "A computer vision system for visual recognition using active knowledge." TR 345, MIT AI Lab, 1974.
Hoffman, D. D., "Interpreting time-varying images: The planarity assumption." Proceedings