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

Estimating the 3D pose of desktop objects is crucial for applications such asrobotic manipulation. Many existing approaches to this problem require a depthmap of the object for both training and prediction, which restricts them toopaque, lambertian objects that produce good returns in an RGBD sensor. In thispaper we forgo using a depth sensor in favor of raw stereo input. We addresstwo problems: first, we establish an easy method for capturing and labeling 3Dkeypoints on desktop objects with an RGB camera; and second, we develop a deepneural network, called $KeyPose$, that learns to accurately predict objectposes using 3D keypoints, from stereo input, and works even for transparentobjects. To evaluate the performance of our method, we create a dataset of 15clear objects in five classes, with 48K 3D-keypoint labeled images. We trainboth instance and category models, and show generalization to new textures,poses, and objects. KeyPose surpasses state-of-the-art performance in 3D poseestimation on this dataset by factors of 1.5 to 3.5, even in cases where thecompeting method is provided with ground-truth depth. Stereo input is essentialfor this performance as it improves results compared to using monocular inputby a factor of 2. We will release a public version of the data capture andlabeling pipeline, the transparent object database, and the KeyPose models andevaluation code. Project website: https://sites.google.com/corp/view/keypose.

KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects