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

Dvir Ginzburg, Dan Raviv

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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 languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PublisherIEEE Computer Society
Pages71-75
Number of pages5
ISBN (Electronic)9781665496209
DOIs
StatePublished - 2022
Event29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
Duration: 16 Oct 202219 Oct 2022

Publication series

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

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
Country/TerritoryFrance
CityBordeaux
Period16/10/2219/10/22

Keywords

  • Geometric deep learning
  • Rigid alignment
  • Robust optimization

Fingerprint

Dive into the research topics of 'DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION'. Together they form a unique fingerprint.

Cite this