Segmentation Based Features for Wide-Baseline Multi-view Reconstruction

Armin Mustafa, Hansung Kim, Evren Imre, Adrian Hilton
2015 2015 International Conference on 3D Vision  
A common problem in wide-baseline stereo is the sparse and non-uniform distribution of correspondences when using conventional detectors such as SIFT, SURF, FAST and MSER. In this paper we introduce a novel segmentation based feature detector SFD that produces an increased number of 'good' features for accurate wide-baseline reconstruction. Each image is segmented into regions by over-segmentation and feature points are detected at the intersection of the boundaries for three or more regions.
more » ... gmentation-based feature detection locates features at local maxima giving a relatively large number of feature points which are consistently detected across wide-baseline views and accurately localised. A comprehensive comparative performance evaluation with previous feature detection approaches demonstrates that: SFD produces a large number of features with increased scene coverage; detected features are consistent across wide-baseline views for images of a variety of indoor and outdoor scenes; and the number of wide-baseline matches is increased by an order of magnitude compared to alternative detector-descriptor combinations. Sparse scene reconstruction from multiple wide-baseline stereo views using the SFD feature detector demonstrates at least a factor six increase in the number of reconstructed points with reduced error distribution compared to SIFT when evaluated against ground-truth and similar computational cost to SURF/FAST. Text
doi:10.1109/3dv.2015.39 dblp:conf/3dim/MustafaKIH15 fatcat:vqwrxvlwzzhbroag3tcif3n2ku