IEEE

Foreground-Aware Geometry Compression With Hybrid Attention for Large-Scale Point Clouds

Abstract: Regions of Interest (ROI) play a crucial role in point cloud compression, especially in applications such as autonomous driving and robot navigation, where foreground regions often contain ...
GitHub

A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration

Official PyTorch implementation of the paper ''A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration'' accepted by NeurIPS 2024 as poster. We present a ...
CNET

Point Broadband Internet Review: Plans, Pricing, Speed and Availability

CNET staff -- not advertisers, partners or business interests -- determine how we review the products and services we cover. If you buy through our links, we may get paid. Trisha Jandoc was an ...
IEEE

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

Abstract: Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone ...