User: Guest  Login
Title:

DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition

Document type:
Zeitschriftenaufsatz
Author(s):
Planche, B.; Wu, Z.; Ma, K.; Sun, S.; Kluckner, S.; Chen, T.; Hutter, A.; Zakharov, S.; Kosch, H.; Ernst, J.
Abstract:
Recent progress in computer vision has been dominated by deep neural networks trained over large amount of labeled data. Collecting such datasets is however a tedious, often impossible task; hence a surge in approaches relying solely on synthetic data for their training. For depth images however, discrepancies with real scans still noticeably affect the end performance. We thus propose an end-to-end framework which simulates the whole mechanism of these devices, generating realistic depth data...     »
Keywords:
Acquisition - Sensors,Analysis/Processing - Recognition,Modeling - Representations,Simulation
Journal title:
IEEE International Conference on 3DVision
Year:
2017
 BibTeX