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

In recent years, sparse voxel-based methods have become the state-of-the-artsfor 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs.Nevertheless, being oblivious to the underlying geometry, voxel-based methodssuffer from ambiguous features on spatially close objects and struggle withhandling complex and irregular geometries due to the lack of geodesicinformation. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3Ddeep architecture that operates on the voxel and mesh representationsleveraging both the Euclidean and geodesic information. Intuitively, theEuclidean information extracted from voxels can offer contextual cuesrepresenting interactions between nearby objects, while the geodesicinformation extracted from meshes can help separate objects that are spatiallyclose but have disconnected surfaces. To incorporate such information from thetwo domains, we design an intra-domain attentive module for effective featureaggregation and an inter-domain attentive module for adaptive feature fusion.Experimental results validate the effectiveness of VMNet: specifically, on thechallenging ScanNet dataset for large-scale segmentation of indoor scenes, itoutperforms the state-of-the-art SparseConvNet and MinkowskiNet (74.6% vs 72.5%and 73.6% in mIoU) with a simpler network structure (17M vs 30M and 38Mparameters). Code release: https://github.com/hzykent/VMNet

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation