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 this paper, we propose a two-stage deep learning framework calledVoxelContext-Net for both static and dynamic point cloud compression. Takingadvantages of both octree based methods and voxel based schemes, our approachemploys the voxel context to compress the octree structured data. Specifically,we first extract the local voxel representation that encodes the spatialneighbouring context information for each node in the constructed octree. Then,in the entropy coding stage, we propose a voxel context based deep entropymodel to compress the symbols of non-leaf nodes in a lossless way. Furthermore,for dynamic point cloud compression, we additionally introduce the local voxelrepresentations from the temporal neighbouring point clouds to exploit temporaldependency. More importantly, to alleviate the distortion from the octreeconstruction procedure, we propose a voxel context based 3D coordinaterefinement method to produce more accurate reconstructed point cloud at thedecoder side, which is applicable to both static and dynamic point cloudcompression. The comprehensive experiments on both static and dynamic pointcloud benchmark datasets(e.g., ScanNet and Semantic KITTI) clearly demonstratethe effectiveness of our newly proposed method VoxelContext-Net for 3D pointcloud geometry compression.

VoxelContext-Net: An Octree based Framework for Point Cloud Compression