ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla

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

32 Scopus citations

Abstract

We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net. Specifically, the Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior. Then we design an iterative refinement unit to generate complete shapes with fine-grained details by integrating prior information. Experiments are conducted on the PCN dataset and the Completion3D benchmark, demonstrating the state-of-the-art performance of the proposed ASFM-Net. Our method achieves the 1st place in the leaderboard of Completion3D and outperforms existing methods with a large margin, about 12%. The codes and trained models are released publicly at https://github.com/Yan-Xia/ASFM-Net.

Original languageEnglish
Title of host publicationMM 2021 - Proceedings of the 29th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages1938-1947
Number of pages10
ISBN (Electronic)9781450386517
DOIs
StatePublished - 17 Oct 2021
Event29th ACM International Conference on Multimedia, MM 2021 - Virtual, Online, China
Duration: 20 Oct 202124 Oct 2021

Publication series

NameMM 2021 - Proceedings of the 29th ACM International Conference on Multimedia

Conference

Conference29th ACM International Conference on Multimedia, MM 2021
Country/TerritoryChina
CityVirtual, Online
Period20/10/2124/10/21

Keywords

  • prior information
  • shape completion
  • siamese auto-encoder

Fingerprint

Dive into the research topics of 'ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion'. Together they form a unique fingerprint.

Cite this