Scan integration as a labeling problem

Song, Ran and Liu, Yonghuai and Martin, Ralph and Paul, Rosin (2014) Scan integration as a labeling problem. Pattern Recognition, 47 (8). pp. 2768-2782. ISSN 0031-3203

Documents
1-s2.0-S0031320314000600-main.pdf
[img]
[Download]
[img]
Preview
PDF
1-s2.0-S0031320314000600-main.pdf - Whole Document

1MB
Item Type:Article
Item Status:Live Archive

Abstract

Integration is a crucial step in the reconstruction of complete 3D surface model from multiple scans. Ever-present registration errors and scanning noise make integration a nontrivial problem. In this paper, we propose a novel method for multi-view scan integration where we solve it as a labeling problem. Unlike previous methods, which have been based on various \emph{merging} schemes, our labeling-based method is essentially a selection strategy. The overall surface model is composed of surface patches from selected input scans. We formulate the labeling via a higher-order Markov Random Field (MRF) which assigns a label representing an index of some input scan to every point in a base surface. Using a higher-order MRF allows us to more effectively capture spatial relations between 3D points. We employ belief propagation to infer this labeling and experimentally demonstrate that this integration approach provides significantly improved integration via both qualitative and quantitative comparisons.

Keywords:Integration, Multi-View Scans, MRF Labeling, Surface Details, oapop, bmjlink, NotOAChecked
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:13426
Deposited On:24 Feb 2014 17:32

Repository Staff Only: item control page