Structure preserving implicit shape encoding via flow regularization

Research output: Contribution to conferenceAbstractAcademic

52 Downloads (Pure)

Abstract

Recently, implicit neural representations (INRs) emerged as an effective method for reconstructing shapes. Several of such methods transform templates to target shapes. Current template-based methods lack proper regularization. In this work, we add a novel regularization to a deformable template approach and discuss the benefits of this regularization with a simple test case.
Original languageEnglish
Number of pages4
Publication statusPublished - 18 Nov 2022
EventGeometric Deep Learning in Medical Image Analysis, GeoMedIA 2022 - Hotel CASA, Amsterdam, Netherlands
Duration: 18 Nov 202218 Nov 2022

Conference

ConferenceGeometric Deep Learning in Medical Image Analysis, GeoMedIA 2022
Abbreviated titleGeoMedIA 2022
Country/TerritoryNetherlands
CityAmsterdam
Period18/11/2218/11/22

Keywords

  • Latent space
  • Shape reconstruction
  • Implicit neural representation
  • Neural ODE

Fingerprint

Dive into the research topics of 'Structure preserving implicit shape encoding via flow regularization'. Together they form a unique fingerprint.

Cite this