Non-parametric Local Transforms for Computing Visual Correspondence

We propose a new approach to the correspondence prob lem that makes use of non parametric local transforms as the basis for correlation Non parametric local transforms rely on the relative order ing of local intensity values and not on the intensity values themselves Correlation using such transforms can tolerate a signi cant number of outliers This can result in improved performance near object boundaries when compared with conventional methods such as normalized correla tion We introduce two non parametric local transforms the rank trans form which measures local intensity and the census transform which summarizes local image structure We describe some properties of these transforms and demonstrate their utility on both synthetic and real data