Distinction of 3D Objects and Scenes via Classification Network and Markov Random Field

Ran Song, Yonghuai Liu, Paul Rosin

Research output: Contribution to journalArticlepeer-review

3 Citations (SciVal)

Abstract

An importance measure of 3D objects inspired by human perception has a range of applications since people want computers to behave like humans in many tasks. This paper revisits a well-defined measure, distinction of 3D mesh, which indicates how important a region of a mesh is with respect to classification. We develop a method to compute it based on a classification network and an MRF. The classification network learns view-based distinction by handling multiple views of a 3D object. Using a classification network has an advantage of avoiding the training data problem which has become a major obstacle of applying deep learning to 3D object understanding tasks. The MRF estimates the parameters of a linear model for combining the view-based distinction maps. The experiments using several publicly accessible datasets show that the distinctive regions detected by our method are not just significantly different from those detected by methods based on handcrafted features, but more consistent with human perception. We also compare it with other perceptual measures and quantitatively evaluate its performance in the context of two applications. Furthermore, due to the view-based nature of our method, we are able to easily extend mesh distinction to 3D scenes containing multiple objects.

Original languageEnglish
Number of pages15
JournalIEEE Transactions on Visualization and Computer Graphics
Early online date07 Dec 2018
DOIs
Publication statusPublished - 07 Dec 2018

Keywords

  • 3D mesh
  • distinction
  • Markov Random Field
  • neural network

Fingerprint

Dive into the research topics of 'Distinction of 3D Objects and Scenes via Classification Network and Markov Random Field'. Together they form a unique fingerprint.

Cite this