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

Recently, deep learning methods have shown promising results in point cloudcompression. For octree-based point cloud compression, previous works show thatthe information of ancestor nodes and sibling nodes are equally important forpredicting current node. However, those works either adopt insufficient contextor bring intolerable decoding complexity (e.g. >600s). To address this problem,we propose a sufficient yet efficient context model and design an efficientdeep learning codec for point clouds. Specifically, we first propose awindow-constrained multi-group coding strategy to exploit the autoregressivecontext while maintaining decoding efficiency. Then, we propose a dualtransformer architecture to utilize the dependency of current node on itsancestors and siblings. We also propose a random-masking pre-train method toenhance our model. Experimental results show that our approach achievesstate-of-the-art performance for both lossy and lossless point cloudcompression. Moreover, our multi-group coding strategy saves 98% decoding timecompared with previous octree-based compression method.

ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression