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

Point cloud is a fundamental 3D representation which is widely used in realworld applications such as autonomous driving. As a newly-developed mediaformat which is characterized by complexity and irregularity, point cloudcreates a need for compression algorithms which are more flexible than existingcodecs. Recently, autoencoders(AEs) have shown their effectiveness in manyvisual analysis tasks as well as image compression, which inspires us to employit in point cloud compression. In this paper, we propose a generalautoencoder-based architecture for lossy geometry point cloud compression. Tothe best of our knowledge, it is the first autoencoder-based geometrycompression codec that directly takes point clouds as input rather than voxelgrids or collections of images. Compared with handcrafted codecs, this approachadapts much more quickly to previously unseen media contents and media formats,meanwhile achieving competitive performance. Our architecture consists of apointnet-based encoder, a uniform quantizer, an entropy estimation block and anonlinear synthesis transformation module. In lossy geometry compression ofpoint cloud, results show that the proposed method outperforms the test modelfor categories 1 and 3 (TMC13) published by MPEG-3DG group on the 125thmeeting, and on average a 73.15\% BD-rate gain is achieved.

Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds