Skip to Main content Skip to Navigation
New interface
Journal articles

A Segmentation Transfer Approach for Rigid Models

Esma Elghoul 1 Anne Verroust-Blondet 1 Mohamed Chaouch 2 
2 LVIC - Laboratoire Vision et Ingénierie des Contenus
DIASI - Département Intelligence Ambiante et Systèmes Interactifs : DRT/LIST/DIASI
Abstract : In this paper, we propose using a segmented example model to perform a semantic oriented segmentation of rigid 3D models of the same class (tables, chairs, etc.). For this, we introduce an alignment method that maps the meaningful parts of the models and we develop a novel approach based on random walks to transfer a consistent segmentation from the example to the target model. The example-driven segmentation is fast and entirely automatic. We demonstrate the effectiveness of our approach through multiple results of inter-shape segmentation transfer presented for different classes of rigid models.
Complete list of metadata
Contributor : Anne Verroust-Blondet Connect in order to contact the contributor
Submitted on : Friday, November 7, 2014 - 4:10:53 PM
Last modification on : Thursday, February 17, 2022 - 10:08:04 AM
Long-term archiving on: : Sunday, February 8, 2015 - 10:50:50 AM


Files produced by the author(s)


  • HAL Id : hal-01081374, version 1


Esma Elghoul, Anne Verroust-Blondet, Mohamed Chaouch. A Segmentation Transfer Approach for Rigid Models. Journal of Information Science and Engineering, 2015, 31 (3), pp.993-1009. ⟨hal-01081374⟩



Record views


Files downloads