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

Range-view based LiDAR segmentation methods are attractive for practicalapplications due to their direct inheritance from efficient 2D CNNarchitectures. In literature, most range-view based methods follow theper-pixel classification paradigm. Recently, in the image segmentation domain,another paradigm formulates segmentation as a mask-classification problem andhas achieved remarkable performance. This raises an interesting question: canthe mask-classification paradigm benefit the range-view based LiDARsegmentation and achieve better performance than the counterpart per-pixelparadigm? To answer this question, we propose a unified mask-classificationmodel, MaskRange, for the range-view based LiDAR semantic and panopticsegmentation. Along with the new paradigm, we also propose a novel dataaugmentation method to deal with overfitting, context-reliance, andclass-imbalance problems. Extensive experiments are conducted on theSemanticKITTI benchmark. Among all published range-view based methods, ourMaskRange achieves state-of-the-art performance with $66.10$ mIoU on semanticsegmentation and promising results with $53.10$ PQ on panoptic segmentationwith high efficiency. Our code will be released.

MaskRange: A Mask-classification Model for Range-view based LiDAR Segmentation