Learning to Solve Random-Dot Stereograms of Dense and Transparent Surfaces with Recurrent Backpropagation

Ning Qian and Terrence J. Sejnowski, Proceedings of the 1988 Connectionist Models Summer School , Morgan Kaufmann, 1989, 435-443. Download the full paper (PDF file)

Abstract

Binocular depth perception, or stereopsis, depends on matching corresponding points in two images taken from two vantage points. In random-dot stereograms the features to be matched are individual pixels. We have used recurrent backpropagation learning algorithm of Pineda (1987) to construct network models with lateral and feedback connections that can solve the correspondence problem for random-dot stereograms. The network learned the uniqueness and continuity constraints originally proposed by Marr and Poggio (1976) from a training set of dense random-dot stereograms. We also constructed networks that can solve sparse random-dot stereograms of transparent surfaces. The success of the learning algorithm depended on taking advantage of translation invariance and restrictions on the range of interactions.

Back to Qian Lab Home Page