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 address 3D object retrieval, substantial efforts have been made togenerate highly discriminative descriptors of 3D objects represented by asingle modality, e.g., voxels, point clouds or multi-view images. It ispromising to leverage the complementary information from multi-modalityrepresentations of 3D objects to further improve retrieval performance.However, multi-modality 3D object retrieval is rarely developed and analyzed onlarge-scale datasets. In this paper, we propose self-and-cross attention basedaggregation of point cloud and multi-view images (SCA-PVNet) for 3D objectretrieval. With deep features extracted from point clouds and multi-viewimages, we design two types of feature aggregation modules, namely theIn-Modality Aggregation Module (IMAM) and the Cross-Modality Aggregation Module(CMAM), for effective feature fusion. IMAM leverages a self-attention mechanismto aggregate multi-view features while CMAM exploits a cross-attentionmechanism to interact point cloud features with multi-view features. The finaldescriptor of a 3D object for object retrieval can be obtained viaconcatenating the aggregated features from both modules. Extensive experimentsand analysis are conducted on three datasets, ranging from small to largescale, to show the superiority of the proposed SCA-PVNet over thestate-of-the-art methods.

SCA-PVNet: Self-and-Cross Attention Based Aggregation of Point Cloud and Multi-View for 3D Object Retrieval