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

Point cloud based 3D deep model has wide applications in many applicationssuch as autonomous driving, house robot, and so on. Inspired by the recentprompt learning in natural language processing, this work proposes a novelMulti-view Vision-Prompt Fusion Network (MvNet) for few-shot 3D point cloudclassification. MvNet investigates the possibility of leveraging theoff-the-shelf 2D pre-trained models to achieve the few-shot classification,which can alleviate the over-dependence issue of the existing baseline modelstowards the large-scale annotated 3D point cloud data. Specifically, MvNetfirst encodes a 3D point cloud into multi-view image features for a number ofdifferent views. Then, a novel multi-view prompt fusion module is developed toeffectively fuse information from different views to bridge the gap between 3Dpoint cloud data and 2D pre-trained models. A set of 2D image prompts can thenbe derived to better describe the suitable prior knowledge for a large-scalepre-trained image model for few-shot 3D point cloud classification. Extensiveexperiments on ModelNet, ScanObjectNN, and ShapeNet datasets demonstrate thatMvNet achieves new state-of-the-art performance for 3D few-shot point cloudimage classification. The source code of this work will be available soon.

Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?