---
_id: '18286'
abstract:
- lang: eng
  text: We introduce a new framework for learning dense correspondence between deformable
    3D shapes. Existing learning based approaches model shape correspondence as a
    labelling problem, where each point of a query shape receives a label identifying
    a point on some reference domain; the correspondence is then constructed a posteriori
    by composing the label predictions of two input shapes. We propose a paradigm
    shift and design a structured prediction model in the space of functional maps,
    linear operators that provide a compact representation of the correspondence.
    We model the learning process via a deep residual network which takes dense descriptor
    fields defined on two shapes as input, and outputs a soft map between the two
    given objects. The resulting correspondence is shown to be accurate on several
    challenging benchmarks comprising multiple categories, synthetic models, real
    scans with acquisition artifacts, topological noise, and partiality.
article_number: '8237865'
article_processing_charge: No
arxiv: 1
author:
- first_name: Or
  full_name: Litany, Or
  last_name: Litany
- first_name: Tal
  full_name: Remez, Tal
  last_name: Remez
- first_name: Emanuele
  full_name: Rodola, Emanuele
  last_name: Rodola
- first_name: Alexander
  full_name: Bronstein, Alexander
  last_name: Bronstein
- first_name: Michael
  full_name: Bronstein, Michael
  last_name: Bronstein
citation:
  ama: 'Litany O, Remez T, Rodola E, Bronstein A, Bronstein M. Deep functional maps:
    Structured prediction for dense shape correspondence. In: <i>2017 IEEE International
    Conference on Computer Vision (ICCV)</i>. Vol 31. IEEE; 2017. doi:<a href="https://doi.org/10.1109/iccv.2017.603">10.1109/iccv.2017.603</a>'
  apa: 'Litany, O., Remez, T., Rodola, E., Bronstein, A., &#38; Bronstein, M. (2017).
    Deep functional maps: Structured prediction for dense shape correspondence. In
    <i>2017 IEEE International Conference on Computer Vision (ICCV)</i> (Vol. 31).
    IEEE. <a href="https://doi.org/10.1109/iccv.2017.603">https://doi.org/10.1109/iccv.2017.603</a>'
  chicago: 'Litany, Or, Tal Remez, Emanuele Rodola, Alexander Bronstein, and Michael
    Bronstein. “Deep Functional Maps: Structured Prediction for Dense Shape Correspondence.”
    In <i>2017 IEEE International Conference on Computer Vision (ICCV)</i>, Vol. 31.
    IEEE, 2017. <a href="https://doi.org/10.1109/iccv.2017.603">https://doi.org/10.1109/iccv.2017.603</a>.'
  ieee: 'O. Litany, T. Remez, E. Rodola, A. Bronstein, and M. Bronstein, “Deep functional
    maps: Structured prediction for dense shape correspondence,” in <i>2017 IEEE International
    Conference on Computer Vision (ICCV)</i>, 2017, vol. 31.'
  ista: 'Litany O, Remez T, Rodola E, Bronstein A, Bronstein M. 2017. Deep functional
    maps: Structured prediction for dense shape correspondence. 2017 IEEE International
    Conference on Computer Vision (ICCV). 16th IEEE International Conference on Computer
    Vision vol. 31, 8237865.'
  mla: 'Litany, Or, et al. “Deep Functional Maps: Structured Prediction for Dense
    Shape Correspondence.” <i>2017 IEEE International Conference on Computer Vision
    (ICCV)</i>, vol. 31, 8237865, IEEE, 2017, doi:<a href="https://doi.org/10.1109/iccv.2017.603">10.1109/iccv.2017.603</a>.'
  short: O. Litany, T. Remez, E. Rodola, A. Bronstein, M. Bronstein, in:, 2017 IEEE
    International Conference on Computer Vision (ICCV), IEEE, 2017.
conference:
  end_date: 2017-10-29
  name: 16th IEEE International Conference on Computer Vision
  start_date: 2017-10-22
date_created: 2024-10-09T07:48:43Z
date_published: 2017-12-25T00:00:00Z
date_updated: 2024-12-05T14:20:54Z
day: '25'
department:
- _id: E-Lib
doi: 10.1109/iccv.2017.603
extern: '1'
external_id:
  arxiv:
  - '1704.08686'
intvolume: '        31'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.48550/arXiv.1704.08686
month: '12'
oa: 1
oa_version: Preprint
publication: 2017 IEEE International Conference on Computer Vision (ICCV)
publication_identifier:
  eissn:
  - '9781538610329'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Deep functional maps: Structured prediction for dense shape correspondence'
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
volume: 31
year: '2017'
...