A Sequential Online 3D Reconstruction System Using Dense Stereo Matching

This paper proposes a sequential online 3D reconstruction system using dense stereo matching for a non-expert user, which can sequentially reconstruct accurate and dense 3D point clouds when the new image is captured. The proposed system is based on a novel processing pipeline of sequential online 3D reconstruction with two key techniques: (i) camera parameter estimation of Structure from Motion (SfM) and (ii) dense stereo correspondence matching using Phase-Only Correlation (POC). The user can confirm the reconstruction result and add supplementary images to the system in order to reconstruct a complete 3D model as needed. Through a set of experiments, the proposed system exhibits efficient performance in terms of reconstruction accuracy and computation time compared with the conventional system.