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

Finding correspondences between images or 3D scans is at the heart of manycomputer vision and image retrieval applications and is often enabled bymatching local keypoint descriptors. Various learning approaches have beenapplied in the past to different stages of the matching pipeline, consideringdetector, descriptor, or metric learning objectives. These objectives weretypically addressed separately and most previous work has focused on imagedata. This paper proposes an end-to-end learning framework for keypointdetection and its representation (descriptor) for 3D depth maps or 3D scans,where the two can be jointly optimized towards task-specific objectives withouta need for separate annotations. We employ a Siamese architecture augmented bya sampling layer and a novel score loss function which in turn affects theselection of region proposals. The positive and negative examples are obtainedautomatically by sampling corresponding region proposals based on theirconsistency with known 3D pose labels. Matching experiments with depth data onmultiple benchmark datasets demonstrate the efficacy of the proposed approach,showing significant improvements over state-of-the-art methods.

End-to-end learning of keypoint detector and descriptor for pose invariant 3D matching