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

It is often desired to train 6D pose estimation systems on synthetic databecause manual annotation is expensive. However, due to the large domain gapbetween the synthetic and real images, synthesizing color images is expensive.In contrast, this domain gap is considerably smaller and easier to fill fordepth information. In this work, we present a system that regresses 6D objectpose from depth information represented by point clouds, and a lightweight datasynthesis pipeline that creates synthetic point cloud segments for training. Weuse an augmented autoencoder (AAE) for learning a latent code that encodes 6Dobject pose information for pose regression. The data synthesis pipeline onlyrequires texture-less 3D object models and desired viewpoints, and it is cheapin terms of both time and hardware storage. Our data synthesis process is up tothree orders of magnitude faster than commonly applied approaches that renderRGB image data. We show the effectiveness of our system on the LineMOD, LineMODOcclusion, and YCB Video datasets. The implementation of our system isavailable at: https://github.com/GeeeG/CloudAAE.

CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds