Recovery of superquadric parameters from range images using deep learning

Klemen Grm and Tim Oblak and Aleš Jaklič and Franc Solina (2019) Recovery of superquadric parameters from range images using deep learning. In: BMVA technical meeting: 3D vision with deep learning , 20.2.2019, BCS (British Computer Society) in London. 5 Southampton St WC2E 7HA London United Kingdom . (Unpublished)

There is a more recent version of this item available.

Preview

PDF Download (329Kb)

Abstract

With the recent advancements in deep neural computation, we devise a method to recover superquadric parameters from range images using a convolutional neural network. By training our simple, fullyconvolutional architecture on synthetic data images, containing a single superquadric, we achieve encouraging results. In a fixed rotation scenario, the model could already be used in practice, but we still need to improve on prediction of arbitrary rotational parameters in the future.

Available Versions of this Item.

• Recovery of superquadric parameters from range images using deep learning (deposited 04 Mar 2019 11:27)[Currently Displayed]
  • Recovery of superquadric parameters from range images using deep learning (deposited 11 Mar 2019 10:17)

Actions (login required)