Stereo matching using a neural network

A polynomial is fitted to find a smooth continuous intensity function in a window and the first-order intensity derivatives are estimated. A neural network is then used to implement the matching procedure under the epipolar, photometric and smoothness constraints, using the estimated first-order derivatives. Owing to the dense intensity derivatives, a dense array of disparities is generated with only a few iterations. The method does not require surface interpolation. Computer simulations to demonstrate the efficacy of the method are presented