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/

Zendy Plus

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

Zendy Tools

Zendy Open

Current 3D segmentation methods heavily rely on large-scale point-clouddatasets, which are notoriously laborious to annotate. Few attempts have beenmade to circumvent the need for dense per-point annotations. In this work, welook at weakly-supervised 3D semantic instance segmentation. The key idea is toleverage 3D bounding box labels which are easier and faster to annotate.Indeed, we show that it is possible to train dense segmentation models usingonly bounding box labels. At the core of our method, \name{}, lies a deepmodel, inspired by classical Hough voting, that directly votes for bounding boxparameters, and a clustering method specifically tailored to bounding boxvotes. This goes beyond commonly used center votes, which would not fullyexploit the bounding box annotations. On ScanNet test, our weakly supervisedmodel attains leading performance among other weakly supervised approaches (+18mAP@50). Remarkably, it also achieves 97% of the mAP@50 score of current fullysupervised models. To further illustrate the practicality of our work, we trainBox2Mask on the recently released ARKitScenes dataset which is annotated with3D bounding boxes only, and show, for the first time, compelling 3D instancesegmentation masks.

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes