Line-Sweep: Cross-Ratio for Wide-Baseline Matching and 3D Reconstruction

We propose a simple and useful idea based on cross- ratio constraint for wide-baseline matching and 3D recon- struction. Most existing methods exploit feature points and planes from images. Lines have always been considered notorious for both matching and reconstruction due to the lack of good line descriptors. We propose a method to gen- erate and match new points using virtual lines constructed using pairs of keypoints, which are obtained using standard feature point detectors. We use cross-ratio constraints to obtain an initial set of new point matches, which are sub- sequently used to obtain line correspondences. We develop a method that works for both calibrated and uncalibrated camera configurations. We show compelling line-matching and large-scale 3D reconstruction.

figure-pad figure-pad

Fig. 1: Top: The basic idea of line-sweeping. We consider pairs of keypoint correspondences (shown in blue) obtained using standard feature detectors to form virtual lines (white) to identify several hundreds of additional point matches (shown in red) using cross-ratio constraints. Bottom: Using 32 images, we generate line-based 3D reconstruction of the bridge of Sighs in Oxford, where lines are represented as pencil of points.



Line-Sweep: Cross-Ratio for Wide-Baseline Matching and 3D Reconstruction
S. Ramalingam, M. Antunes, D. Snow, G. H. Lee, S. Pillai
Computer Vision and Pattern Recognition (CVPR), 2015
[ pdf, bib, video ]