PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds

Abstract

Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering these correspondences to keep only the most reliable ones to estimate the transformation. Recently, several deep nets have been proposed to solve these steps jointly. We built upon these works and propose PCAM: a neural network whose key element is a pointwise product of crossattention matrices that permits to mix both low-level geometric and high-level contextual information to find point correspondences. These cross-attention matrices also permits the exchange of context information between the point clouds, at each layer, allowing the network construct better matching features within the overlapping regions. The experiments show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets. Our code and trained models are available at https://github.com/valeoai/PCAM.
Fichier principal
Vignette du fichier
2110.01269.pdf (11.41 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03364975 , version 1 (05-10-2021)

Identifiers

  • HAL Id : hal-03364975 , version 1

Cite

Anh-Quan Cao, Gilles Puy, Alexandre Boulch, Renaud Marlet. PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds. ICCV 2021 - International Conference on Computer Vision, Oct 2021, Montreal / Virtual, Canada. ⟨hal-03364975⟩
68 View
48 Download

Share

Gmail Mastodon Facebook X LinkedIn More