PrincetonComputer SciencePIXL GroupPublications → [Mitchel et al. 2020] Local Access
ECHO: Extended Convolution Histogram of Orientations for Local Surface Description

Computer Graphics Forum, November 2020

Thomas W. Mitchel, Szymon Rusinkiewicz,
Gregory S. Chirikjian, Michael Kazhdan
Visualizations of biharmonic ECHO descriptors computed at corresponding points on two meshes.
Abstract

This paper presents a novel, highly distinctive and robust local surface feature descriptor. Our descriptor is predicated on a simple observation: instead of describing the points in the vicinity of a feature point relative to a reference frame at the feature point, all points 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 filter to adaptively transform as it passes over the domain. As such, we name our descriptor the Extended Convolution Histogram of Orientations (ECHO). It exhibits superior performance compared to popular surface descriptors in both feature matching and shape correspondence experiments. In particular, the ECHO descriptor is highly stable under near-isometric deformations and remains distinctive under significant levels of noise, tessellation, complex deformations and the kinds of interference commonly found in real data.
Paper
Supplemental Material
Links
Citation

Thomas W. Mitchel, Szymon Rusinkiewicz, Gregory S. Chirikjian, and Michael Kazhdan.
"ECHO: Extended Convolution Histogram of Orientations for Local Surface Description."
Computer Graphics Forum, November 2020.

BibTeX

@article{Mitchel:2020:EEC,
   author = "Thomas W. Mitchel and Szymon Rusinkiewicz and Gregory S. Chirikjian and
      Michael Kazhdan",
   title = "{ECHO}: Extended Convolution Histogram of Orientations for Local
      Surface Description",
   journal = "Computer Graphics Forum",
   year = "2020",
   month = nov
}