ECHO: Extended Convolution Histogram of Orientations for Local Surface Description

Abstract

This paper presents a novel, highly distinctive and robust local surface feature descriptor. Our descriptor is predicated on a simpleobservation: instead of describing the points in the vicinity of a feature point relative to a reference frame at the feature point, allpoints in the region describe the feature point relative to their own frames. Isometry invariance is a byproduct of this construction.Our descriptor is derived relative to the extended convolution – a generalization of the standard convolution that allows the lterto adaptively transform as it passes over the domain. As such, we name our descriptor the Extended Convolution Histogram ofOrientations (ECHO). It exhibits superior performance compared to popular surface descriptors in both feature matching andshape correspondence experiments. In particular, the ECHO descriptor is highly stable under near-isometric deformations andremains distinctive under signicant levels of noise, tessellation, complex deformations and the kinds of interference commonlyfound in real data.