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

Domain adaptation for Cross-LiDAR 3D detection is challenging due to thelarge gap on the raw data representation with disparate point densities andpoint arrangements. By exploring domain-invariant 3D geometric characteristicsand motion patterns, we present an unsupervised domain adaptation method thatovercomes above difficulties. First, we propose the Spatial Geometry Alignmentmodule to extract similar 3D shape geometric features of the same object classto align two domains, while eliminating the effect of distinct pointdistributions. Second, we present Temporal Motion Alignment module to utilizemotion features in sequential frames of data to match two domains. Prototypesgenerated from two modules are incorporated into the pseudo-label reweightingprocedure and contribute to our effective self-training framework for thetarget domain. Extensive experiments show that our method achievesstate-of-the-art performance on cross-device datasets, especially for thedatasets with large gaps captured by mechanical scanning LiDARs and solid-stateLiDARs in various scenes. Project homepage is athttps://github.com/4DVLab/CL3D.git

CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection