Determining Three-Dimensional Shape from Orientation and Spatial Frequency Disparities

Abstract. Binocular di erences in orientation and foreshortening are systematically related to surface slant and tilt and could potentially be exploited by biological and machine vision systems. Indeed, human stereopsis may possess a mechanism that speci cally makes use of these orientation and spatial frequency disparities, in addition to the usual cue of horizontal disparity. In machine vision algorithms, orientation and spatial frequency disparities are a source of error in nding stereo correspondence because one seeks to nd features or areas which are similar in the two views when, in fact, they are systematically di erent. In other words, it is common to treat as noise what is useful signal. We have been developing a new stereo algorithm based on the outputs of linear spatial lters at a range of orientations and scales. We present a method in this framework, making use of orientation and spatial frequency disparities, to directly recover local surface slant. An implementationof th...

• Type: Conference
• Year: 1992
• Where: ECCV
• Authors: David G. Jones, Jitendra Malik
• Keywords: Accurate Surface Orientation, Computer Vision, ECCV 1992, Linear Spatial Lters, Local Surface Slant, Spatial Frequency Disparities, Surface Slant