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

In this paper, we propose the USIP detector: an Unsupervised Stable InterestPoint detector that can detect highly repeatable and accurately localizedkeypoints from 3D point clouds under arbitrary transformations without the needfor any ground truth training data. Our USIP detector consists of a featureproposal network that learns stable keypoints from input 3D point clouds andtheir respective transformed pairs from randomly generated transformations. Weprovide degeneracy analysis of our USIP detector and suggest solutions toprevent it. We encourage high repeatability and accurate localization of thekeypoints with a probabilistic chamfer loss that minimizes the distancesbetween the detected keypoints from the training point cloud pairs. Extensiveexperimental results of repeatability tests on several simulated and real-world3D point cloud datasets from Lidar, RGB-D and CAD models show that our USIPdetector significantly outperforms existing hand-crafted and deeplearning-based 3D keypoint detectors. Our code is available at the projectwebsite. https://github.com/lijx10/USIP

USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds