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

We consider the attributes of a point cloud as samples of a vector-valuedvolumetric function at discrete positions. To compress the attributes given thepositions, we compress the parameters of the volumetric function. We model thevolumetric function by tiling space into blocks, and representing the functionover each block by shifts of a coordinate-based, or implicit, neural network.Inputs to the network include both spatial coordinates and a latent vector perblock. We represent the latent vectors using coefficients of theregion-adaptive hierarchical transform (RAHT) used in the MPEG geometry-basedpoint cloud codec G-PCC. The coefficients, which are highly compressible, arerate-distortion optimized by back-propagation through a rate-distortionLagrangian loss in an auto-decoder configuration. The result outperforms RAHTby 2--4 dB. This is the first work to compress volumetric functions representedby local coordinate-based neural networks. As such, we expect it to beapplicable beyond point clouds, for example to compression of high-resolutionneural radiance fields.

LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks