English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose ways to speed up the initial pose-graph generation for globalStructure-from-Motion algorithms. To avoid forming tentative pointcorrespondences by FLANN and geometric verification by RANSAC, which are themost time-consuming steps of the pose-graph creation, we propose two newmethods - built on the fact that image pairs usually are matched consecutively.Thus, candidate relative poses can be recovered from paths in the partly-builtpose-graph. We propose a heuristic for the A* traversal, considering globalsimilarity of images and the quality of the pose-graph edges. Given a relativepose from a path, descriptor-based feature matching is made "light-weight" byexploiting the known epipolar geometry. To speed up PROSAC-based sampling whenRANSAC is applied, we propose a third method to order the correspondences bytheir inlier probabilities from previous estimations. The algorithms are testedon 402130 image pairs from the 1DSfM dataset and they speed up the featurematching 17 times and pose estimation 5 times.

Efficient Initial Pose-graph Generation for Global SfM