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

3D perception, especially point cloud classification, has achievedsubstantial progress. However, in real-world deployment, point cloudcorruptions are inevitable due to the scene complexity, sensor inaccuracy, andprocessing imprecision. In this work, we aim to rigorously benchmark andanalyze point cloud classification under corruptions. To conduct a systematicinvestigation, we first provide a taxonomy of common 3D corruptions andidentify the atomic corruptions. Then, we perform a comprehensive evaluation ona wide range of representative point cloud models to understand theirrobustness and generalizability. Our benchmark results show that although pointcloud classification performance improves over time, the state-of-the-artmethods are on the verge of being less robust. Based on the obtainedobservations, we propose several effective techniques to enhance point cloudclassifier robustness. We hope our comprehensive benchmark, in-depth analysis,and proposed techniques could spark future research in robust 3D perception.

Benchmarking and Analyzing Point Cloud Classification under Corruptions