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

Segmenting unseen objects in cluttered scenes is an important skill thatrobots need to acquire in order to perform tasks in new environments. In thiswork, we propose a new method for unseen object instance segmentation bylearning RGB-D feature embeddings from synthetic data. A metric learning lossfunction is utilized to learn to produce pixel-wise feature embeddings suchthat pixels from the same object are close to each other and pixels fromdifferent objects are separated in the embedding space. With the learnedfeature embeddings, a mean shift clustering algorithm can be applied todiscover and segment unseen objects. We further improve the segmentationaccuracy with a new two-stage clustering algorithm. Our method demonstratesthat non-photorealistic synthetic RGB and depth images can be used to learnfeature embeddings that transfer well to real-world images for unseen objectinstance segmentation.

Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation