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 Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Constructing HD semantic maps is a central component of autonomous driving.However, traditional pipelines require a vast amount of human efforts andresources in annotating and maintaining the semantics in the map, which limitsits scalability. In this paper, we introduce the problem of HD semantic maplearning, which dynamically constructs the local semantics based on onboardsensor observations. Meanwhile, we introduce a semantic map learning method,dubbed HDMapNet. HDMapNet encodes image features from surrounding camerasand/or point clouds from LiDAR, and predicts vectorized map elements in thebird's-eye view. We benchmark HDMapNet on nuScenes dataset and show that in allsettings, it performs better than baseline methods. Of note, our camera-LiDARfusion-based HDMapNet outperforms existing methods by more than 50% in allmetrics. In addition, we develop semantic-level and instance-level metrics toevaluate the map learning performance. Finally, we showcase our method iscapable of predicting a locally consistent map. By introducing the method andmetrics, we invite the community to study this novel map learning problem.

HDMapNet: An Online HD Map Construction and Evaluation Framework