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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we present KeyMatchNet, a novel network for zero-shot poseestimation in 3D point clouds. The network is trained to match object keypointswith scene-points, and these matches are then used for pose estimation. Themethod generalizes to new objects by using not only the scene point cloud asinput but also the object point cloud. This is in contrast with conventionalmethods where object features are stored in network weights. By having ageneralized network we avoid the need for training new models for novelobjects, thus significantly decreasing the computational requirements of themethod.  However, as a result of the complexity, zero-shot pose estimation methodsgenerally have lower performance than networks trained for a single object. Toaddress this, we reduce the complexity of the task by including the scenarioinformation during training. This is generally not feasible as collecting realdata for new tasks increases the cost drastically. But, in the zero-shot poseestimation task, no retraining is needed for new objects. The expensive datacollection can thus be performed once, and the scenario information is retainedin the network weights.  The network is trained on 1,500 objects and is tested on unseen objects. Wedemonstrate that the trained network can accurately estimate poses for novelobjects and demonstrate the ability of the network to perform outside of thetrained class. We believe that the presented method is valuable for manyreal-world scenarios. Code, trained network, and dataset will be made availableat publication.

KeyMatchNet: Zero-Shot Pose Estimation in 3D Point Clouds by Generalized Keypoint Matching