Stochastic Optimization Based 3D Dense Reconstruction from Multiple Views with High Accuracy and Completeness

• Published in: Journal of Information Science and Engineering Vol. 31; no. 1; pp. 131 - 146
• Main Authors: 陳文昭(Wen-Chao Chen), 陳稔(Zen Chen), 宋秉一(Ping-Yi Sung)
• Format: Journal Article
• Language: English
• Published: 社團法人中華民國計算語言學學會 01.01.2015
• Subjects: Accuracy; Algorithms; Completeness; Optimization; Reconstruction; Stochasticity; Swarm intelligence; Three dimensional; patch verification; GLN-PSO; patch priority queue; 3D patch-based reconstruction; patch expansion; patch filtering; multi-view stereo, adaptive matching function
• ISSN: 1016-2364
• DOI: 10.6688/JISE.2015.31.1.7

This paper presents a stochastic optimization based 3D dense reconstruction from multiple views. Accuracy and completeness are two major measure indices for performance evaluation of various multi-view stereo (MVS) algorithms. We shall model the object to be reconstructed by a set of 3D oriented planar patches covering the visible object surface. The adopted multi-view reconstruction is formulated as a patch expansion process under a tree hierarchy. In order to find the optimal patches via multi-view stereo matching we shall employ a PSO (Particle Swarm Optimization) method for the sake of implementation simplicity and avoidance of possible local traps as found in the derivative based optimization methods. To secure a high reconstruction quality we advocate a patch priority queue to select the best patch during the patch expansion. The experimental results indicate that the proposed method is superior or comparable to the top ranked reconstruction methods reported in the public Middlebury MVS evaluation website.