3D Instance Segmentation via Multi-Task Metric Learning

Abstract

We proposed a method for 3D instance segmentation of voxel-based scenes. Our approach is based on metric learning and the first part assigns all voxels belonging to the same object instance feature vectors that are in close vicinity. Conversely, voxels belonging to different object instances are assigned features that are further apart from each other in the feature space. The second part estimates directional information of object centers, which is used to score the segmentation results generated by the first part.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 27, 2019
Accession Number
AD1141153

Entities

People

  • Bernard Ghanem
  • Jean Lahoud
  • Marc Pollefeys
  • Martin R. Oswald

Organizations

  • ETH Zurich
  • King Abdullah University of Science and Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computer Vision
  • Computers
  • Deep Learning
  • Detection
  • Geometry
  • Image Recognition
  • Image Segmentation
  • Information Processing
  • Information Systems
  • Network Architecture
  • Neural Networks
  • Object Recognition
  • Pattern Recognition
  • Point Clouds
  • Recognition

Fields of Study

  • Computer science

Readers

  • Medical Imaging.
  • Neural Network Machine Learning.

Technology Areas

  • Space