Robust Shape Recovery from Occluding Contours Using a Linear Smoother

Recovering the shape of an object from two views fails at occluding contours of smooth objects because the extremal contours are view dependent. For three or more views, shape recovery is possible, and several algorithms have recently been developed for this purpose. We present a new approach to the multiframe stereo problem that does not depend on differential measurements in the image, which may be noise sensitive. Instead, we use a linear smoother to optimally combine all of the measurements available at the contours (and other edges) in all of the images. This allows us to extract a robust and reasonably dense estimate of surface shape, and to integrate shape information from both surface markings and occluding contours. Results are presented, which empirically show that in the presence of noise, smoothing over more than three views reduces the error even when the epipolar curve is nonplanar.