Equivariant multi-view networks

Carlos Esteves, Yinshuang Xu, Christine Allec-Blanchette, Kostas Daniilidis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

27 Scopus citations

Abstract

Several popular approaches to 3D vision tasks process multiple views of the input independently with deep neural networks pre-trained on natural images, where view permutation invariance is achieved through a single round of pooling over all views. We argue that this operation discards important information and leads to subpar global descriptors. In this paper, we propose a group convolutional approach to multiple view aggregation where convolutions are performed over a discrete subgroup of the rotation group, enabling, thus, joint reasoning over all views in an equivariant (instead of invariant) fashion, up to the very last layer. We further develop this idea to operate on smaller discrete homogeneous spaces of the rotation group, where a polar view representation is used to maintain equivariance with only a fraction of the number of input views. We set the new state of the art in several large scale 3D shape retrieval tasks, and show additional applications to panoramic scene classification.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 International Conference on Computer Vision, ICCV 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1568-1577
Number of pages10
ISBN (Electronic)9781728148038
DOIs
StatePublished - Oct 2019
Externally publishedYes
Event17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of
Duration: Oct 27 2019Nov 2 2019

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2019-October
ISSN (Print)1550-5499

Conference

Conference17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Country/TerritoryKorea, Republic of
CitySeoul
Period10/27/1911/2/19

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Equivariant multi-view networks'. Together they form a unique fingerprint.

Cite this