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

Deep neural network (DNN) architectures have been shown to outperformtraditional pipelines for object segmentation and pose estimation using RGBDdata, but the performance of these DNN pipelines is directly tied to howrepresentative the training data is of the true data. Hence a key requirementfor employing these methods in practice is to have a large set of labeled datafor your specific robotic manipulation task, a requirement that is notgenerally satisfied by existing datasets. In this paper we develop a pipelineto rapidly generate high quality RGBD data with pixelwise labels and objectposes. We use an RGBD camera to collect video of a scene from multipleviewpoints and leverage existing reconstruction techniques to produce a 3Ddense reconstruction. We label the 3D reconstruction using a human assistedICP-fitting of object meshes. By reprojecting the results of labeling the 3Dscene we can produce labels for each RGBD image of the scene. This pipelineenabled us to collect over 1,000,000 labeled object instances in just a fewdays. We use this dataset to answer questions related to how much training datais required, and of what quality the data must be, to achieve high performancefrom a DNN architecture.

LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes