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

Voxel is an important format to represent geometric data, which has beenwidely used for 3D deep learning in shape analysis due to its generalizationability and regular data format. However, fine-grained tasks like partsegmentation require detailed structural information, which increases voxelresolution and thus causes other issues such as the exhaustion of computationalresources. In this paper, we propose a novel volumetric convolutional neuralnetwork, which could extract discriminative features encoding detailedinformation from voxelized 3D data under a limited resolution. To this purpose,a spatial dense extraction (SDE) module is designed to preserve the spatialresolution during the feature extraction procedure, alleviating the loss ofdetail caused by sub-sampling operations such as max-pooling. An attentionfeature aggregation (AFA) module is also introduced to adaptively selectinformative features from different abstraction scales, leading to segmentationwith both semantic consistency and high accuracy of details. Experiment resultson the large-scale dataset demonstrate the effectiveness of our method in 3Dshape part segmentation.

VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes