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

Visual-based 3D semantic occupancy perception is a key technology forrobotics, including autonomous vehicles, offering an enhanced understanding ofthe environment by 3D. This approach, however, typically requires morecomputational resources than BEV or 2D methods. We propose a novel 3D semanticoccupancy perception method, OccupancyDETR, which utilizes a DETR-like objectdetection, a mixed dense-sparse 3D occupancy decoder. Our approachdistinguishes between foreground and background within a scene. Initially,foreground objects are detected using the DETR-like object detection.Subsequently, queries for both foreground and background objects are fed intothe mixed dense-sparse 3D occupancy decoder, performing upsampling in dense andsparse methods, respectively. Finally, a MaskFormer is utilized to infer thesemantics of the background voxels. Our approach strikes a balance betweenefficiency and accuracy, achieving faster inference times, lower resourceconsumption, and improved performance for small object detection. Wedemonstrate the effectiveness of our proposed method on the SemanticKITTIdataset, showcasing an mIoU of 14 and a processing speed of 10 FPS, therebypresenting a promising solution for real-time 3D semantic occupancy perception.

OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction