DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION

Dvir Ginzburg; Dan Raviv

doi:10.1109/ICIP46576.2022.9897800

DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION

Dvir Ginzburg, Dan Raviv

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

We present a new paradigm for rigid alignment between point clouds based on learnable weighted consensus named Deep Weighted Consensus (DWC). Current models, learnable or axiomatic, work well for constrained orientations and limited noise levels, usually by an end-to-end learner or an iterative scheme. However, real-world tasks require dealing with large rotations and outliers, and all known models fail to deliver. Here we present a different direction. We claim that we can align point clouds out of sampled matched points according to confidence level derived from a dense, soft alignment map. The pipeline is differentiable and converges under large rotations in the full range of the rotation group in R³, even with high noise levels.

Original language	English
Title of host publication	2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
Publisher	IEEE Computer Society
Pages	71-75
Number of pages	5
ISBN (Electronic)	9781665496209
DOIs	https://doi.org/10.1109/ICIP46576.2022.9897800
State	Published - 2022
Event	29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France Duration: 16 Oct 2022 → 19 Oct 2022

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Conference

Conference	29th IEEE International Conference on Image Processing, ICIP 2022
Country/Territory	France
City	Bordeaux
Period	16/10/22 → 19/10/22

Keywords

Geometric deep learning
Rigid alignment
Robust optimization

Access to Document

10.1109/ICIP46576.2022.9897800

Cite this

@inproceedings{25a642ba33d644a0a4d17f47542a0cab,

title = "DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION",

abstract = "We present a new paradigm for rigid alignment between point clouds based on learnable weighted consensus named Deep Weighted Consensus (DWC). Current models, learnable or axiomatic, work well for constrained orientations and limited noise levels, usually by an end-to-end learner or an iterative scheme. However, real-world tasks require dealing with large rotations and outliers, and all known models fail to deliver. Here we present a different direction. We claim that we can align point clouds out of sampled matched points according to confidence level derived from a dense, soft alignment map. The pipeline is differentiable and converges under large rotations in the full range of the rotation group in R3, even with high noise levels.",

keywords = "Geometric deep learning, Rigid alignment, Robust optimization",

author = "Dvir Ginzburg and Dan Raviv",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 29th IEEE International Conference on Image Processing, ICIP 2022 ; Conference date: 16-10-2022 Through 19-10-2022",

year = "2022",

doi = "10.1109/ICIP46576.2022.9897800",

language = "אנגלית",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "71--75",

booktitle = "2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings",

address = "ארצות הברית",

}

Ginzburg, D & Raviv, D 2022, DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION. in 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 71-75, 29th IEEE International Conference on Image Processing, ICIP 2022, Bordeaux, France, 16/10/22. https://doi.org/10.1109/ICIP46576.2022.9897800

DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION. / Ginzburg, Dvir; Raviv, Dan.
2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. IEEE Computer Society, 2022. p. 71-75 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION

AU - Ginzburg, Dvir

AU - Raviv, Dan

PY - 2022

Y1 - 2022

N2 - We present a new paradigm for rigid alignment between point clouds based on learnable weighted consensus named Deep Weighted Consensus (DWC). Current models, learnable or axiomatic, work well for constrained orientations and limited noise levels, usually by an end-to-end learner or an iterative scheme. However, real-world tasks require dealing with large rotations and outliers, and all known models fail to deliver. Here we present a different direction. We claim that we can align point clouds out of sampled matched points according to confidence level derived from a dense, soft alignment map. The pipeline is differentiable and converges under large rotations in the full range of the rotation group in R3, even with high noise levels.

AB - We present a new paradigm for rigid alignment between point clouds based on learnable weighted consensus named Deep Weighted Consensus (DWC). Current models, learnable or axiomatic, work well for constrained orientations and limited noise levels, usually by an end-to-end learner or an iterative scheme. However, real-world tasks require dealing with large rotations and outliers, and all known models fail to deliver. Here we present a different direction. We claim that we can align point clouds out of sampled matched points according to confidence level derived from a dense, soft alignment map. The pipeline is differentiable and converges under large rotations in the full range of the rotation group in R3, even with high noise levels.

KW - Geometric deep learning

KW - Rigid alignment

KW - Robust optimization

UR - http://www.scopus.com/inward/record.url?scp=85146644437&partnerID=8YFLogxK

U2 - 10.1109/ICIP46576.2022.9897800

DO - 10.1109/ICIP46576.2022.9897800

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85146644437

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 71

EP - 75

BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings

PB - IEEE Computer Society

T2 - 29th IEEE International Conference on Image Processing, ICIP 2022

Y2 - 16 October 2022 through 19 October 2022

ER -

DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this