Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. On Rendering Synthetic Images for Training an Object Detector
 
research article

On Rendering Synthetic Images for Training an Object Detector

Rozantsev, Artem  
•
Lepetit, Vincent  
•
Fua, Pascal  
2015
Computer Vision and Image Understanding

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a coarse 3D model of the target object. These parameters can then be reused to generate an unlimited number of training images of the object of interest in arbitrary 3D poses, which can then be used to increase classification performances. A key insight of our approach is that the synthetically generated images should be similar to real images, not in terms of image quality, but rather in terms of features used during the detector training. We show in the context of drone, plane, and car detection that using such synthetically generated images yields significantly better performances than simply perturbing real images or even synthesizing images in such way that they look very realistic, as is often done when only limited amounts of training data are available.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

top.pdf

Type

Preprint

Version

http://purl.org/coar/version/c_71e4c1898caa6e32

Access type

openaccess

Size

5.89 MB

Format

Adobe PDF

Checksum (MD5)

d6f5b11c0c7209f11fc2adeeebc18ca9

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés