MRF labeling for multi-view range image integration

Song, Ran and Liu, Yonghuai and Martin, Ralph and Rosin, Paul (2010) MRF labeling for multi-view range image integration. In: ACCV, November 8-12, 2010, Queenstown, New Zealand.

Full content URL: http://rd.springer.com/chapter/10.1007%2F978-3-642...

Full text not available from this repository.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Multi-view range image integration focuses on producing a single reasonable 3D point cloud from multiple 2.5D range images for the reconstruction of a watertight manifold surface. However, registration errors and scanning noise usually lead to a poor integration and, as a result, the reconstructed surface cannot have topology and geometry consistent with the data source. This paper proposes a novel method cast in the framework of Markov random fields (MRF) to address the problem. We define a probabilistic description of a MRF labeling based on all input range images and then employ loopy belief propagation to solve this MRF, leading to a globally optimised integration with accurate local details. Experiments show the advantages and superiority of our MRF-based approach over existing methods.

Keywords:Markov Random Field, Range Image Integration
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:13293
Deposited On:06 Feb 2014 16:30

Repository Staff Only: item control page