Skip to main navigation Skip to search Skip to main content

Localization and Completion for 3D Object Interactions

  • Shenzhen University
  • Xi'an Jiaotong University
  • University of Edinburgh

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Finding where and what objects to put into an existing scene is a common task for scene synthesis and robot/character motion planning. Existing frameworks require development of hand-crafted features suitable for the task, or full volumetric analysis that could be memory intensive and imprecise. In this paper, we propose a data-driven framework to discover a suitable location and then place the appropriate objects in a scene. Our approach is inspired by computer vision techniques for localizing objects in images: using an all directional depth image (ADD-image) that encodes the 360-degree field of view from samples in the scene, our system regresses the images to the positions where the new object can be located. Given several candidate areas around the host object in the scene, our system predicts the partner object whose geometry fits well to the host object. Our approach is highly parallel and memory efficient, and is especially suitable for handling interactions between large and small objects. We show examples where the system can hang bags on hooks, fit chairs in front of desks, put objects into shelves, insert flowers into vases, and put hangers onto laundry rack.

Original languageEnglish
Article number8611181
Pages (from-to)2634-2644
Number of pages11
JournalIEEE Transactions on Visualization and Computer Graphics
Volume26
Issue number8
DOIs
StatePublished - 1 Aug 2020

Keywords

  • ADD-image
  • Scene synthesis
  • interaction completion
  • localization

Fingerprint

Dive into the research topics of 'Localization and Completion for 3D Object Interactions'. Together they form a unique fingerprint.

Cite this