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

To apply transformer-based models to point cloud understanding, many previousworks modify the architecture of transformers by using, e.g., local attentionand down-sampling. Although they have achieved promising results, earlier workson transformers for point clouds have two issues. First, the power of plaintransformers is still under-explored. Second, they focus on simple and smallpoint clouds instead of complex real-world ones. This work revisits the plaintransformers in real-world point cloud understanding. We first take a closerlook at some fundamental components of plain transformers, e.g., patchifier andpositional embedding, for both efficiency and performance. To close theperformance gap due to the lack of inductive bias and annotated data, weinvestigate self-supervised pre-training with masked autoencoder (MAE).Specifically, we propose drop patch, which prevents information leakage andsignificantly improves the effectiveness of MAE. Our models achieve SOTAresults in semantic segmentation on the S3DIS dataset and object detection onthe ScanNet dataset with lower computational costs. Our work provides a newbaseline for future research on transformers for point clouds.

Applying Plain Transformers to Real-World Point Clouds