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

Heavily relying on 3D annotations limits the real-world application of 3Dobject detection. In this paper, we propose a method that does not demand any3D annotation, while being able to predict fully oriented 3D bounding boxes.Our method, called Recursive Cross-View (RCV), utilizes the three-viewprinciple to convert 3D detection into multiple 2D detection tasks, requiringonly a subset of 2D labels. We propose a recursive paradigm, in which instancesegmentation and 3D bounding box generation by Cross-View are implementedrecursively until convergence. Specifically, our proposed method involves theuse of a frustum for each 2D bounding box, which is then followed by therecursive paradigm that ultimately generates a fully oriented 3D box, alongwith its corresponding class and score. Note that, class and score are given bythe 2D detector. Estimated on the SUN RGB-D and KITTI datasets, our methodoutperforms existing image-based approaches. To justify that our method can bequickly used to new tasks, we implement it on two real-world scenarios, namely3D human detection and 3D hand detection. As a result, two new 3D annotateddatasets are obtained, which means that RCV can be viewed as a (semi-)automatic 3D annotator. Furthermore, we deploy RCV on a depth sensor, whichachieves detection at 7 fps on a live RGB-D stream. RCV is the first 3Ddetection method that yields fully oriented 3D boxes without consuming 3Dlabels.

Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations