Publications

Detailed Information

Fully convolutional geometric features

Cited 341 time in Web of Science Cited 386 time in Scopus
Authors

Choy, Christopher; Park, Jaesik; Koltun, Vladlen

Issue Date
2019
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
Proceedings of the IEEE International Conference on Computer Vision, Vol.2019-October, pp.8957-8965
Abstract
Extracting geometric features from 3D scans or point clouds is the first step in applications such as registration, reconstruction, and tracking. State-of-the-art methods require computing low-level features as input or extracting patch-based features with limited receptive field. In this work, we present fully-convolutional geometric features, computed in a single pass by a 3D fully-convolutional network. We also present new metric learning losses that dramatically improve performance. Fully-convolutional geometric features are compact, capture broad spatial context, and scale to large scenes. We experimentally validate our approach on both indoor and outdoor datasets. Fully-convolutional geometric features achieve state-of-the-art accuracy without requiring prepossessing, are compact (32 dimensions), and are 290 times faster than the most accurate prior method.
ISSN
1550-5499
URI
https://hdl.handle.net/10371/201311
DOI
https://doi.org/10.1109/ICCV.2019.00905
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • College of Engineering
  • Dept. of Computer Science and Engineering
Research Area Computer Graphics, Computer Vision, Machine Learning

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share