Title :
Occluding Contours for Multi-view Stereo
Author :
Qi Shan ; Curless, Brian ; Furukawa, Yudai ; Hernandez, C. ; Seitz, Steven M.
Author_Institution :
Univ. of Washington, Seattle, WA, USA
Abstract :
This paper leverages occluding contours (aka "internal silhouettes") to improve the performance of multi-view stereo methods. The contributions are 1) a new technique to identify free-space regions arising from occluding contours, and 2) a new approach for incorporating the resulting free-space constraints into Poisson surface reconstruction. The proposed approach outperforms state of the art MVS techniques for challenging Internet datasets, yielding dramatic quality improvements both around object contours and in surface detail.
Keywords :
image reconstruction; stereo image processing; MVS techniques; Poisson surface reconstruction; free-space constraints; free-space regions identification; internal silhouettes; multiview stereo methods; object contours; occluding contours; surface detail; Geometry; Image reconstruction; Internet; Shape; Software; Surface reconstruction; Three-dimensional displays; 3D Reconstruction; Image Contours; Multi-View Stereo;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
DOI :
10.1109/CVPR.2014.511