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

We present TransLPC, a novel detection model for large point clouds that isbased on a transformer architecture. While object detection with transformershas been an active field of research, it has proved difficult to apply suchmodels to point clouds that span a large area, e.g. those that are common inautonomous driving, with lidar or radar data. TransLPC is able to remedy theseissues: The structure of the transformer model is modified to allow for largerinput sequence lengths, which are sufficient for large point clouds. Besidesthis, we propose a novel query refinement technique to improve detectionaccuracy, while retaining a memory-friendly number of transformer decoderqueries. The queries are repositioned between layers, moving them closer to thebounding box they are estimating, in an efficient manner. This simple techniquehas a significant effect on detection accuracy, which is evaluated on thechallenging nuScenes dataset on real-world lidar data. Besides this, theproposed method is compatible with existing transformer-based solutions thatrequire object detection, e.g. for joint multi-object tracking and detection,and enables them to be used in conjunction with large point clouds.

Transformers for Object Detection in Large Point Clouds