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

3D detection plays an indispensable role in environment perception. Due tothe high cost of commonly used LiDAR sensor, stereo vision based 3D detection,as an economical yet effective setting, attracts more attention recently. Forthese approaches based on 2D images, accurate depth information is the key toachieve 3D detection, and most existing methods resort to a preliminary stagefor depth estimation. They mainly focus on the global depth and neglect theproperty of depth information in this specific task, namely, sparsity andlocality, where exactly accurate depth is only needed for these 3D boundingboxes. Motivated by this finding, we propose a stereo-image based anchor-free3D detection method, called structure-aware stereo 3D detector (termed asSIDE), where we explore the instance-level depth information via constructingthe cost volume from RoIs of each object. Due to the information sparsity oflocal cost volume, we further introduce match reweighting and structure-awareattention, to make the depth information more concentrated. Experimentsconducted on the KITTI dataset show that our method achieves thestate-of-the-art performance compared to existing methods without depth mapsupervision.

SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation